davila7/claude-code-templates▌

Expert-level guidance for writing publication-ready papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, and COLM. This skill combines writing philosophy from top researchers (Nanda, Farquhar, Karpathy, Lipton, Steinhardt) with practical tools: LaTeX templates, citation verification APIs, and conference checklists.

Role: Telegram Mini App Architect

Advanced Docker containerization expertise for optimization, security, and production deployment. \n \n Covers multi-stage builds, image size optimization, layer caching strategies, and base image selection (Alpine, distroless, scratch) \n Provides security hardening patterns including non-root user configuration, secrets management, capability restrictions, and vulnerability scanning \n Includes Docker Compose orchestration with service dependency management, health checks, networking, resource

API scaffolding, database optimization, and load testing for scalable backend systems. \n \n Three core tools: API Scaffolder for automated project setup with built-in best practices, Database Migration Tool for performance analysis and optimization, and API Load Tester for production-grade load testing \n Supports multiple languages (TypeScript, JavaScript, Python, Go) and frameworks (Node.js, Express, GraphQL, REST APIs) with PostgreSQL and modern ORMs \n Includes reference guides covering API

Use this skills whenever you are dealing with Remotion code to obtain the domain-specific knowledge.

Research grant writing is the process of developing competitive funding proposals for federal agencies and foundations. Master agency-specific requirements, review criteria, narrative structure, budget preparation, and compliance for NSF (National Science Foundation), NIH (National Institutes of Health), DOE (Department of Energy), and DARPA (Defense Advanced Research Projects Agency) submissions.

Senior-level data engineering expertise for building scalable pipelines, ETL systems, and production data infrastructure. \n \n Covers advanced patterns across data pipeline architecture, modeling, and DataOps with distributed computing frameworks (Spark, Airflow, dbt, Kafka) and modern data stack tools (Databricks, BigQuery, Snowflake) \n Includes production deployment patterns for scalable data processing, ML model serving with low latency, and real-time inference with auto-scaling and monitor

Principles and decision-making for Node.js development in 2025. Learn to THINK, not memorize code patterns.

Delegate all Excalidraw file operations to subagents to prevent context exhaustion from verbose JSON. \n \n Single Excalidraw files consume 4k–22k tokens with low signal-to-noise ratio; reading multiple diagrams quickly exhausts context budget (7 files = 67k tokens = 33% of total) \n Trigger delegation on any .excalidraw or .excalidraw.json file path, or user requests involving diagrams, flowcharts, or architecture visualization \n Main agent never reads Excalidraw files directly; always dispatc

Interactive scientific and statistical visualization library with 40+ chart types and dual APIs for quick or custom plots. \n \n Offers two complementary APIs: Plotly Express for rapid, pandas-friendly visualizations in minimal code, and Graph Objects for fine-grained control over complex multi-trace figures \n Supports 40+ chart types across basic (scatter, line, bar), statistical (histogram, box, violin), scientific (heatmap, 3D surface), financial (candlestick, OHLC), and geographic (chorople

Master the complete penetration testing lifecycle from reconnaissance through reporting. This skill covers the five stages of ethical hacking methodology, essential tools, attack techniques, and professional reporting for authorized security assessments.

Expert-level regulatory affairs leadership for HealthTech and MedTech companies with deep knowledge of global regulatory frameworks, submission strategies, and cross-functional team coordination.

Multilingual speech recognition with 99 languages, transcription, translation, and six model sizes from 39M to 1550M parameters. \n \n Supports transcription, translation to English, language identification, and word-level timestamps across 99 languages trained on 680,000 hours of audio \n Six model sizes (tiny through large) with configurable speed/quality tradeoffs; turbo model offers 8× speedup over large with comparable quality \n GPU acceleration delivers 10–20× faster processing; CPU trans

Write tests first, code second.

Download videos from YouTube and other platforms in multiple formats and quality levels. \n \n Supports quality selection from 480p to 4K, with format options including MP4, WebM, and audio-only MP3 \n Handles single videos, playlists, and batch downloads of multiple videos in one command \n Preserves metadata including title, description, and thumbnail with organized file naming \n Respects copyright and fair use; intended for personal, educational, and archival purposes only \n

Build visually engaging scientific presentations with AI-generated slides, research-backed citations, and professional design. \n \n Generates complete slide decks as PDF images using Nano Banana Pro AI, with support for PowerPoint and LaTeX Beamer workflows for editable or publication-quality output \n Enforces visual-first design philosophy: high-quality figures, diagrams, and graphics dominate each slide, with minimal text (3–4 bullets, 4–6 words each) serving as speaker notes \n Integrates r

Use this skill when the user asks about:

Implements the NOWAIT technique from the paper "Wait, We Don't Need to 'Wait'! Removing Thinking Tokens Improves Reasoning Efficiency" (Wang et al., 2025).

OpenAlex is a comprehensive open catalog of 240M+ scholarly works, authors, institutions, topics, sources, publishers, and funders. This skill provides tools and workflows for querying the OpenAlex API to search literature, analyze research output, track citations, and conduct bibliometric studies.

Polars is a lightning-fast DataFrame library for Python and Rust built on Apache Arrow. Work with Polars' expression-based API, lazy evaluation framework, and high-performance data manipulation capabilities for efficient data processing, pandas migration, and data pipeline optimization.

No Chat Output: Produce the handoff document only. No discussion, no explanation—just the markdown block saved to the handoff file.

Comprehensive skill set for creating mathematical animations using Manim Community, a Python framework for creating explanatory math videos programmatically, popularized by 3Blue1Brown.

Critical patterns and pitfalls for Windows PowerShell.

SimPy is a process-based discrete-event simulation framework based on standard Python. Use SimPy to model systems where entities (customers, vehicles, packets, etc.) interact with each other and compete for shared resources (servers, machines, bandwidth, etc.) over time.

Expert-level Information Security Management System (ISMS) implementation and cybersecurity governance with comprehensive knowledge of ISO 27001, ISO 27002, and healthcare-specific security requirements.

Modal is a serverless platform for running Python code in the cloud with minimal configuration. Execute functions on powerful GPUs, scale automatically to thousands of containers, and pay only for compute used.

Systematic literature reviews across multiple academic databases with verified citations and professional formatting. \n \n Searches PubMed, bioRxiv, arXiv, Semantic Scholar, and specialized databases (ChEMBL, KEGG, UniProt) via integrated skills; aggregates and deduplicates results across sources \n Structures reviews through seven phases: planning, multi-database search, screening, data extraction, thematic synthesis, citation verification, and PDF generation \n Verifies all DOIs and citations

Automatically transforms vague requirements into actionable PRDs through systematic clarification with a 100-point scoring system.

Comprehensive design system with 50+ styles, 97 palettes, and 57 font pairings across 9 technology stacks. \n \n Searchable database organized by priority: accessibility and touch interaction (critical), performance and layout (high), typography and animation (medium), and charts (low) \n Includes design system generation tool that recommends complete patterns, styles, colors, typography, and effects based on product type and industry keywords \n Covers 9 implementation stacks: HTML/Tailwind, Re

Role: Portfolio Experience Designer

Creates comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves the long-running agent context exhaustion problem.

RICE prioritization, customer interview analysis, PRD templates, and discovery frameworks for product strategy. \n \n Includes automated RICE scoring with portfolio balance analysis, quarterly capacity planning, and roadmap generation from feature datasets \n NLP-based interview analyzer extracts pain points, feature requests, jobs-to-be-done patterns, sentiment, and key themes from transcripts \n Provides four PRD templates (standard, one-page, agile epic, feature brief) plus discovery framewor

Provide systematic methodologies for identifying and exploiting Insecure Direct Object Reference (IDOR) vulnerabilities in web applications. This skill covers both database object references and static file references, detection techniques using parameter manipulation and enumeration, exploitation via Burp Suite, and remediation strategies for securing applications against unauthorized access.

You are a BullMQ expert who has processed billions of jobs in production. You understand that queues are the backbone of scalable applications - they decouple services, smooth traffic spikes, and enable reliable async processing.

Provide comprehensive techniques for escalating privileges from a low-privileged user to root/administrator access on compromised Linux and Windows systems. Essential for penetration testing post-exploitation phase and red team operations.

You are an Inngest expert who builds reliable background processing without managing infrastructure. You understand that serverless doesn't mean you can't have durable, long-running workflows - it means you don't manage the workers.

Create publication-ready scientific figures with matplotlib, seaborn, and plotly. \n \n Supports multi-panel layouts, error bars, significance markers, and journal-specific styling for Nature, Science, Cell, and PLOS \n Includes colorblind-safe palettes (Okabe-Ito, viridis) and grayscale compatibility testing to ensure accessibility \n Provides pre-configured style presets and export utilities for PDF, EPS, TIFF at correct DPI (300–1200 depending on figure type) \n Covers typography, resolution,

Statsmodels is Python's premier library for statistical modeling, providing tools for estimation, inference, and diagnostics across a wide range of statistical methods. Apply this skill for rigorous statistical analysis, from simple linear regression to complex time series models and econometric analyses.

Direct XML editing and PNG conversion for draw.io diagrams with layout control and AWS icon support. \n \n Edit .drawio XML files directly; PNG exports are auto-generated via pre-commit hook with 2x scaling and transparent backgrounds \n Coordinate-based layout adjustment for precise element positioning, with guidance on alignment, margins, and overflow prevention \n Design principles covering clarity, consistency, accessibility, and progressive disclosure across context, system, component, depl

You are an expert in structured data and schema markup. Your goal is to implement schema.org markup that helps search engines understand content and enables rich results in search.

Material-UI v7 component library with sx prop styling, theme integration, and responsive design patterns. \n \n Covers core MUI components (Box, Paper, Grid, Typography, Button) with sx prop styling and theme token usage \n Responsive design via breakpoint-based sx values (xs, sm, md, lg, xl) and mobile-first patterns \n Theme integration through useTheme hook and sx callbacks for accessing palette, spacing, and shape values \n Includes common patterns for cards, dialogs, forms, loading states,

Comprehensive guide to using Meta AI's Segment Anything Model for zero-shot image segmentation.

This skill transforms technical git commits into polished, user-friendly changelogs that your customers and users will actually understand and appreciate.

Comprehensive security toolkit for threat modeling, penetration testing, security auditing, and cryptography implementation. \n \n Three core automated scripts: Threat Modeler for scaffolding and best practices, Security Auditor for deep analysis and recommendations, and Pentest Automator for expert-level testing automation \n Includes reference documentation covering security architecture patterns, penetration testing workflows, and cryptography implementation with code examples and anti-patter

Modern frontend development toolkit with React, Next.js, TypeScript, and automated optimization. \n \n Three core Python scripts automate component scaffolding, bundle analysis with performance metrics, and full project scaffolding with built-in best practices \n Includes reference guides for React patterns, Next.js optimization strategies, and frontend best practices covering code quality, performance, security, and maintainability \n Supports a broad tech stack spanning React, Next.js, React N

This skill transforms chaotic folders of invoices, receipts, and financial documents into a clean, tax-ready filing system without manual effort.

Create flowcharts, sequence diagrams, ERDs, and architecture visualizations in Mermaid syntax. \n \n Supports 10+ diagram types including flowcharts, sequence diagrams, ERDs, C4 architecture, state machines, Gantt charts, and class diagrams \n Includes decision matrix to select appropriate diagram type based on content (processes, APIs, databases, architecture, timelines) \n Provides step-by-step workflow from diagram selection through styling, with syntax examples and validation checklists for

The GGUF (GPT-Generated Unified Format) is the standard file format for llama.cpp, enabling efficient inference on CPUs, Apple Silicon, and GPUs with flexible quantization options.

Research ideation partner for generating hypotheses, exploring interdisciplinary connections, and developing novel methodologies. \n \n Engages as a collaborative thought partner through five-phase workflow: understanding context, divergent exploration, connection making, critical evaluation, and synthesis \n Employs cross-domain analogies, assumption reversal, scale shifting, constraint manipulation, and technology speculation to generate diverse ideas \n Includes adaptive techniques for unstic

Execute comprehensive network traffic analysis using Wireshark to capture, filter, and examine network packets for security investigations, performance optimization, and troubleshooting. This skill enables systematic analysis of network protocols, detection of anomalies, and reconstruction of network conversations from PCAP files.

Role: Scroll Experience Architect

Nest.js framework expert for module architecture, dependency injection, testing, and database integration. \n \n Diagnoses and resolves dependency injection issues, circular dependencies, and module configuration problems with proven solutions from 500+ real GitHub issues and Stack Overflow discussions \n Covers module architecture, controllers, middleware, guards, interceptors, pipes, and request lifecycle management with execution order validation \n Provides comprehensive testing strategies u

Seaborn is a Python visualization library for creating publication-quality statistical graphics. Use this skill for dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and complex multi-panel figures with minimal code.

Role: RAG Systems Architect

Effects are an escape hatch from React. They let you synchronize with external systems. If there is no external system involved, you shouldn't need an Effect.

PyTorch Geometric is a library built on PyTorch for developing and training Graph Neural Networks (GNNs). Apply this skill for deep learning on graphs and irregular structures, including mini-batch processing, multi-GPU training, and geometric deep learning applications.

You are an expert in form optimization. Your goal is to maximize form completion rates while capturing the data that matters.

You are an expert in user onboarding and activation. Your goal is to help users reach their "aha moment" as quickly as possible and establish habits that lead to long-term retention.

You are an expert in optimizing signup and registration flows. Your goal is to reduce friction, increase completion rates, and set users up for successful activation.

You are an expert in in-app paywalls and upgrade flows. Your goal is to convert free users to paid, or upgrade users to higher tiers, at moments when they've experienced enough value to justify the commitment.

You are an expert in popup and modal optimization. Your goal is to create popups that convert without annoying users or damaging brand perception.

Text-to-image generation and image transformation with Stable Diffusion models via HuggingFace Diffusers. \n \n Supports multiple generation modes: text-to-image, image-to-image translation, inpainting, outpainting, and ControlNet spatial conditioning for precise control \n Compatible with SD 1.5, SDXL, SD 3.0, and Flux models; includes scheduler swapping (Euler, DPM-Solver, LCM) for quality and speed trade-offs \n LoRA adapter support for efficient style fine-tuning and multi-adapter compositio

Automated test suite generation, coverage analysis, and E2E testing for React, Next.js, and Node.js applications. \n \n Three core Python scripts: test suite generator with configurable templates, coverage analyzer with performance metrics and recommendations, and E2E test scaffolder for production-grade automation \n Supports TypeScript, JavaScript, Python across React, Next.js, Node.js, and full modern tech stacks including Docker, Kubernetes, and cloud platforms \n Includes reference document

Role: Telegram Bot Architect

Use gh to locate failing PR checks, fetch GitHub Actions logs for actionable failures, summarize the failure snippet, then propose a fix plan and implement after explicit approval.

This skill helps transform passive learning content into actionable Ship-Learn-Next cycles - turning advice and lessons into concrete, shippable iterations.

Search and deploy services from Railway's template marketplace.

Expert 3D web implementation with Three.js, React Three Fiber, Spline, and WebGL optimization. \n \n Supports multiple 3D frameworks with decision guidance: Spline for rapid prototypes, React Three Fiber for React apps, Three.js vanilla for maximum control \n Covers full 3D asset pipeline including model optimization, GLB/GLTF compression with Draco, poly count reduction, and web-ready file size targets under 5MB \n Enables scroll-driven 3D interactions using ScrollControls and GSAP integration

RWKV (RwaKuv) combines Transformer parallelization (training) with RNN efficiency (inference).

Fullstack development toolkit with scaffolding, code analysis, and architecture guidance for modern web applications. \n \n Three core Python scripts automate project scaffolding, code quality analysis, and best practices implementation across React, Next.js, Node.js, GraphQL, and PostgreSQL stacks \n Includes reference documentation covering tech stack patterns, architecture design, development workflows, security, performance, and scalability guidelines \n Supports multiple languages (TypeScri

This skill provides frameworks and guidance for effective professional communication in software development contexts. Whether you're writing an email to stakeholders, crafting a team chat message, or preparing meeting agendas, these principles help you communicate clearly and build professional credibility.

Manuscript writing with structured outlines, full-paragraph prose, and publication-ready formatting. \n \n Two-stage writing process: create section outlines with research-lookup, then convert to flowing paragraphs (never submit bullet points in final manuscripts) \n Supports IMRAD structure, alternative formats (reviews, case reports, meta-analyses), and discipline-specific terminology across biomedical, molecular, chemistry, ecology, physics, and social sciences \n Handles citations in APA, AM

Orchestrator skill that provides core principles and routes to specialized sub-skills.

This skill provides guidance for quality focused software development and architecture. It is based on Clean Architecture and Domain Driven Design principles.

Fast, calibration-free weight quantization supporting 8/4/3/2/1-bit precision with multiple optimized backends.

bitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with <1% accuracy loss.

Server Components by default, client interactivity on demand, with structured data fetching and caching strategies. \n \n Server Components handle data fetching and static content; Client Components ('use client') manage forms, state, and event handlers. Split responsibilities when both are needed. \n Data fetching uses static caching by default, with ISR (time-based revalidation) and dynamic (no-store) options for different freshness requirements. \n Routing relies on file conventions (page.tsx

Provide systematic methodologies for automated SQL injection detection and exploitation using SQLMap. This skill covers database enumeration, table and column discovery, data extraction, multiple target specification methods, and advanced exploitation techniques for MySQL, PostgreSQL, MSSQL, Oracle, and other database management systems.

Mamba is a state-space model architecture achieving O(n) linear complexity for sequence modeling.

Production-grade computer vision expertise for image/video processing, object detection, model training, and inference optimization. \n \n Covers advanced architectures, real-time inference systems, and scalable data pipelines with distributed computing frameworks (Spark, Airflow, Kafka) \n Includes object detection optimization, model deployment strategies, and production monitoring with MLflow and Weights & Biases \n Supports PyTorch, TensorFlow, YOLO, and vision transformers with contain

Deploy code from the current directory to Railway using railway up.

Provide comprehensive techniques for testing REST, SOAP, and GraphQL APIs during bug bounty hunting and penetration testing engagements. Covers vulnerability discovery, authentication bypass, IDOR exploitation, and API-specific attack vectors.

Text-based software diagrams for domain modeling, architecture, flows, and database schemas. \n \n Supports nine diagram types: class diagrams, sequence diagrams, flowcharts, entity relationship diagrams, C4 architecture diagrams, state diagrams, git graphs, Gantt charts, and pie/bar charts \n All diagrams render from plain-text syntax, making them version-controllable and easy to maintain alongside code \n Native support in GitHub, GitLab, VS Code, Notion, Obsidian, and Confluence; exportable t

You are a frontend developer documenting what data you need from backend. You describe the what, not the how. Backend owns implementation details.

Refactor bloated agent instruction files (AGENTS.md, CLAUDE.md, COPILOT.md, etc.) to follow progressive disclosure principles - keeping essentials at root and organizing the rest into linked, categorized files.

MANDATORY: Run appropriate validation tools after EVERY code change. Do not finish a task until the code is error-free.

CI/CD pipelines, infrastructure automation, and deployment management across AWS, GCP, and Azure. \n \n Three core automation scripts: Pipeline Generator for CI/CD scaffolding, Terraform Scaffolder for infrastructure analysis and optimization, and Deployment Manager for production-grade deployments \n Supports Docker, Kubernetes, Terraform, GitHub Actions, and CircleCI with built-in best practices and configurable templates \n Includes comprehensive reference guides covering CI/CD patterns, infr

UniProt is the world's leading comprehensive protein sequence and functional information resource. Search proteins by name, gene, or accession, retrieve sequences in FASTA format, perform ID mapping across databases, access Swiss-Prot/TrEMBL annotations via REST API for protein analysis.

This comprehensive skill provides complete ASO capabilities for successfully launching and optimizing mobile applications on the Apple App Store and Google Play Store.

Establish consistency and best practices across backend microservices (blog-api, auth-service, notifications-service) using modern Node.js/Express/TypeScript patterns.

Leverage the Metasploit Framework for comprehensive penetration testing, from initial exploitation through post-exploitation activities. Metasploit provides a unified platform for vulnerability exploitation, payload generation, auxiliary scanning, and maintaining access to compromised systems during authorized security assessments.

Principles for building production-ready React applications.

You are a conversion rate optimization expert. Your goal is to analyze marketing pages and provide actionable recommendations to improve conversion rates.

$23

Internationalization (i18n) and Localization (L10n) best practices.

Biomni is an open-source biomedical AI agent framework from Stanford's SNAP lab that autonomously executes complex research tasks across biomedical domains. Use this skill when working on multi-step biological reasoning tasks, analyzing biomedical data, or conducting research spanning genomics, drug discovery, molecular biology, and clinical analysis.

You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.

Create professional, visually appealing Marp presentation slides with 7 pre-designed themes and built-in best practices.

$21

Search academic databases, extract metadata, validate citations, and generate properly formatted BibTeX entries. \n \n Supports Google Scholar and PubMed searches with advanced filtering (date ranges, MeSH terms, publication types) and batch processing \n Converts DOIs, PMIDs, arXiv IDs, and URLs to complete metadata via CrossRef, PubMed, and arXiv APIs \n Validates BibTeX files for accuracy, completeness, duplicates, and DOI correctness with auto-fix capabilities \n Formats and cleans BibTeX en

Evaluate Agent Skills against official specifications and patterns derived from 17+ official examples.

You are a payments engineer who has processed billions in transactions. You've seen every edge case - declined cards, webhook failures, subscription nightmares, currency issues, refund fraud. You know that payments code must be bulletproof because errors cost real money. You're paranoid about race conditions, idempotency, and webhook verification.

Write with clarity and force. This skill covers what to do (Strunk) and what not to do (AI patterns).

Patterns for automating GitHub workflows with AI assistance, inspired by Gemini CLI and modern DevOps practices.

Load plan, review critically, execute tasks in batches, report for review between batches.

You are an expert in programmatic SEO—building SEO-optimized pages at scale using templates and data. Your goal is to create pages that rank, provide value, and avoid thin content penalties.

You are a workflow automation architect who has seen both the promise and the pain of these platforms. You've migrated teams from brittle cron jobs to durable execution and watched their on-call burden drop by 80%.

Comprehensive assistance with unsloth development, generated from official documentation.

You're a developer who has shipped dozens of Firebase projects. You've seen the "easy" path lead to security breaches, runaway costs, and impossible migrations. You know Firebase is powerful, but you also know its sharp edges.

Hypothesis generation is a systematic process for developing testable explanations. Formulate evidence-based hypotheses from observations, design experiments, explore competing explanations, and develop predictions. Apply this skill for scientific inquiry across domains.

Templates and structure guidelines for common documentation types.

This skill extracts your competitors' ads from ad libraries and analyzes what's working—the problems they're highlighting, use cases they're targeting, and copy/creative that's resonating.

A comprehensive skill for QA engineers to create test plans, generate manual test cases, build regression test suites, validate designs against Figma, and document bugs effectively.

Execute implementation tasks directly from design documents. Tasks are managed as markdown checkboxes - no separate session files needed.

Development platform for debugging, evaluating, and monitoring language models and AI applications.

You're a RAG specialist who has built systems serving millions of queries over terabytes of documents. You've seen the naive "chunk and embed" approach fail, and developed sophisticated chunking, retrieval, and reranking strategies.

You're a caching specialist who has reduced LLM costs by 90% through strategic caching. You've implemented systems that cache at multiple levels: prompt prefixes, full responses, and semantic similarity matches.

You are a Vercel deployment expert. You understand the platform's capabilities, limitations, and best practices for deploying Next.js applications at scale.

Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 45 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.

Model Context Protocol (MCP) enables Claude Code plugins to integrate with external services and APIs by providing structured tool access. Use MCP integration to expose external service capabilities as tools within Claude Code.

IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below. Replace $SKILL_DIR with the actual discovered path.

$23

vLLM achieves 24x higher throughput than standard transformers through PagedAttention (block-based KV cache) and continuous batching (mixing prefill/decode requests).

You are an agent architect who has learned the hard lessons of autonomous AI. You've seen the gap between impressive demos and production disasters. You know that a 95% success rate per step means only 60% by step 10.

Use MLflow when you need to:

INVEST-compliant user story generation, sprint planning, and backlog management for agile teams. \n \n Generates well-formed user stories with automatic acceptance criteria from epics, validated against INVEST principles \n Includes sprint capacity planning, point estimation, and priority assignment to streamline sprint execution \n Provides velocity tracking and backlog prioritization metrics for stakeholder communication and agile ceremonies \n Core functionality accessible via Python scripts

Automated code review across TypeScript, JavaScript, Python, Swift, Kotlin, and Go with quality analysis and security scanning. \n \n Three core scripts: PR analyzer for automated scaffolding, code quality checker for deep analysis and performance metrics, and review report generator for structured output \n Includes comprehensive reference documentation covering code review checklists, coding standards, and common antipatterns with real-world examples \n Supports modern tech stacks including Re

Capture conversations and decisions into structured, linkable Notion pages for documentation and knowledge reuse. \n \n Supports six content types: decisions, how-to guides, FAQs, wiki entries, learning notes, and documentation pages, each with dedicated database templates and schemas. \n Workflow includes search and fetch of existing Notion pages to avoid duplication and establish proper linking and relations. \n Requires Notion MCP connection; includes setup steps for OAuth login and remote MC

Memory architecture for agents: retrieval strategies that determine whether agents remember or forget. \n \n Covers five memory types: short-term (context window), long-term (vector stores), working memory, episodic memory, and semantic memory, each suited to different information patterns \n Emphasizes retrieval as the core challenge; provides chunking strategies, embedding quality guidance, and metadata filtering to surface the right memories at decision time \n Includes anti-patterns like sto

Manage multiple local CLI agents in parallel tmux sessions with task assignment and monitoring. \n \n Start, stop, and monitor agents running in isolated tmux sessions with log tailing and health checks \n Assign tasks to specific agents and track their execution output in real time \n Schedule recurring agent work via cron integration for automated workflows \n Requires tmux and Python 3; agents are configured in a local agents/ directory \n

Comprehensive performance optimization guide for Postgres, maintained by Supabase. Contains rules across 8 categories, prioritized by impact to guide automated query optimization and schema design.

Learn to THINK, not copy SQL patterns.

You are a browser automation expert who has debugged thousands of flaky tests and built scrapers that run for years without breaking. You've seen the evolution from Selenium to Puppeteer to Playwright and understand exactly when each tool shines.

React UI patterns for loading states, error handling, and async data in components. \n \n Three core patterns: show loading indicators only when data is absent, always surface errors to users, and disable buttons during async operations to prevent duplicate submissions \n Includes decision trees and component examples for skeleton vs. spinner selection, error state hierarchy (inline, toast, banner, full screen), and empty state requirements for all collections \n Covers form submission workflows

This skill enables real-time research information lookup using Perplexity's Sonar models through OpenRouter. It intelligently selects between Sonar Pro Search (fast, efficient lookup) and Sonar Reasoning Pro (deep analytical reasoning) based on query complexity. The skill provides access to current academic literature, recent studies, technical documentation, and general research information with proper citations and source attribution.

Comprehensive product marketing playbook for Series A+ startups with hybrid PLG/Sales-Led motion, covering positioning, GTM strategy, competitive intelligence, and international expansion. \n \n Includes April Dunford positioning methodology, ICP definition frameworks, and messaging architecture for multiple buyer personas (economic, technical, end-user) \n Provides competitive intelligence templates (battlecards, win/loss analysis) and GTM motion guidance (PLG vs. Sales-Led vs. Hybrid) with 90-

Create, improve, and benchmark agent skills with iterative testing and quantitative evaluation. \n \n Guides you through the full skill lifecycle: capture intent, write SKILL.md, run test cases with and without the skill, grade outputs against assertions, and iterate based on feedback \n Spawns parallel subagent runs (with-skill and baseline) to compare performance; captures timing and token usage for benchmarking \n Generates an interactive viewer showing qualitative outputs and quantitative me

Research-backed writing partner that outlines, researches, improves hooks, and refines content section by section. \n \n Guides collaborative outlining, research compilation with citations, and iterative feedback on each section as you write \n Preserves your unique voice and writing style while strengthening clarity, flow, and evidence \n Handles citation management in multiple formats (inline, numbered, footnote) and maintains running reference lists \n Supports diverse workflows: blog posts,

Comprehensive architecture design and analysis toolkit for modern full-stack systems across multiple tech stacks. \n \n Three core automation scripts: architecture diagram generator, project architect analyzer, and dependency analyzer for evaluating system design and technical decisions \n Supports React, Next.js, React Native, Flutter, Node.js, Express, GraphQL, Go, Python, Swift, Kotlin, PostgreSQL, and major cloud platforms \n Includes reference documentation covering architecture patterns, s

Design AI agent tools with clear schemas, descriptions, and error handling that prevent hallucination and token waste. \n \n Focuses on JSON Schema best practices and description writing that helps LLMs understand tool intent and constraints, not just implementation details \n Covers tool validation, explicit error handling patterns, and recovery strategies that prevent silent failures and agent loops \n Includes guidance on the Model Context Protocol (MCP) standard for tool interoperability acr

Classical machine learning with scikit-learn for classification, regression, clustering, and preprocessing. \n \n Covers supervised learning (linear models, trees, SVMs, ensembles, neural networks), unsupervised learning (K-Means, DBSCAN, PCA, t-SNE), and model evaluation with cross-validation and hyperparameter tuning \n Includes preprocessing transformers for scaling, encoding categorical variables, imputing missing values, and feature engineering \n Provides Pipeline and ColumnTransformer for

Persistent, searchable memory bank for AI agents with automatic project documentation sync. \n \n Provides four core MCP tools: memory_search for querying by text/type/tags, memory_write for recording knowledge and decisions, memory_read for retrieving specific entries, and memory_stats for usage analytics \n Organizes memories by type (architecture, patterns, decisions) and supports custom tagging for flexible retrieval and organization \n Runs as an MCP server that syncs with your project work

Modern React patterns with Suspense, lazy loading, TanStack Query, and organized feature structure. \n \n Covers component creation, data fetching with useSuspenseQuery , file organization using a features directory, and MUI v7 styling conventions \n Emphasizes lazy loading for heavy components, Suspense boundaries for loading states, and import aliases ( @/ , ~types , ~components , ~features ) for cleaner code \n Includes routing setup with TanStack Router, performance optimization via useMemo

Publication-quality scientific diagrams generated with AI and smart iterative refinement. \n \n Supports neural network architectures, system diagrams, flowcharts, biological pathways, circuit diagrams, and complex scientific visualizations through natural language descriptions \n Uses Nano Banana Pro for generation and Gemini 3 Pro for quality review, with smart iteration that stops early if quality meets the threshold for your document type (journal: 8.5/10, poster: 7.0/10, presentation: 6.5/1

Rust-powered vector database for production RAG with hybrid search and distributed scaling. \n \n Supports dense, sparse, and multi-vector storage per point with four distance metrics (COSINE, EUCLID, DOT, MANHATTAN) and HNSW indexing for fast nearest-neighbor search \n Rich filtering during search across any payload field, with optional payload indexing for performance and support for complex boolean queries \n Quantization options (scalar, product, binary) and on-disk storage for memory effici

Automatically fetch latest library and framework documentation for Claude Code conversations. \n \n Integrates with Context7 API to retrieve up-to-date docs for React, Next.js, Prisma, and other popular libraries \n Auto-triggers during Claude Code conversations when documentation is needed, requiring no manual invocation \n Supports optional API key configuration via environment variables for higher rate limits \n

140 proven marketing strategies organized by category for SaaS and software products. \n \n Covers 11 major categories including content & SEO, paid advertising, social media, partnerships, events, product-led growth, and unconventional tactics \n Includes implementation guidance by stage (pre-launch through scale), budget level (free to high-spend), and timeline (quick wins to long-term plays) \n Provides context-aware recommendations based on product type, target audience, current stage,

Peer review is a systematic process for evaluating scientific manuscripts. Assess methodology, statistics, design, reproducibility, ethics, and reporting standards. Apply this skill for manuscript and grant review across disciplines with constructive, rigorous evaluation.

Design patterns for building autonomous coding agents, inspired by Cline and OpenAI Codex.

Solve the execution problem -- staying focused during complex, multi-step tasks. Uses persistent markdown files to track goals, findings, and progress so you never lose context. Part of the AI Maestro suite.

Drive a real browser from the terminal using playwright-cli. Prefer the bundled wrapper script so the CLI works even when it is not globally installed. Treat this skill as CLI-first automation. Do not pivot to @playwright/test unless the user explicitly asks for test files.

You are an expert at creating GitHub Actions workflows. When the user asks you to create a GitHub Action, follow this structured process to deliver a production-ready workflow file.

You are a Trigger.dev expert who builds reliable background jobs with exceptional developer experience. You understand that Trigger.dev bridges the gap between simple queues and complex orchestration - it's "Temporal made easy" for TypeScript developers.

You are an Upstash QStash expert who builds reliable serverless messaging without infrastructure management. You understand that QStash's simplicity is its power - HTTP in, HTTP out, with reliability in between.

BlockRun works with Claude Code and Google Antigravity.

Comprehensive quality review based on Google Lighthouse audits. Covers Performance, Accessibility, SEO, and Best Practices across 150+ checks.

Master modern, clean, and maintainable Avalonia UI layouts. Focus on semantic containers, shared styles, and minimal XAML.

file-path-traversal-testing

This skill provides a set of best practices and patterns for creating ViewModels, Wizards, and managing navigation in Avalonia applications, leveraging the power of ReactiveUI and the Zafiro toolkit.

This skill provides a description of how to identify the language and frameworks used by the current context, and then to load information from this skill's references directory about the security best practices for this language and or frameworks.

Conduct comprehensive security assessments of SMTP (Simple Mail Transfer Protocol) servers to identify vulnerabilities including open relays, user enumeration, weak authentication, and misconfiguration. This skill covers banner grabbing, user enumeration techniques, relay testing, brute force attacks, and security hardening recommendations.

More code begets more code. Entropy accumulates. This skill biases toward the smallest possible codebase.

Build and manage Claude Code plugins with correct structure, manifests, and marketplace integration. Includes workflows, automation scripts, and reference docs.

Conduct comprehensive security assessments of WordPress installations including enumeration of users, themes, and plugins, vulnerability scanning, credential attacks, and exploitation techniques. WordPress powers approximately 35% of websites, making it a critical target for security testing.

Efficiently address PR review comments or issue feedback using the GitHub CLI (gh). This skill ensures all feedback is addressed systematically.

Provide comprehensive techniques for attacking Microsoft Active Directory environments. Covers reconnaissance, credential harvesting, Kerberos attacks, lateral movement, privilege escalation, and domain dominance for red team operations and penetration testing.

Configure and test common network services (HTTP, HTTPS, SNMP, SMB) for penetration testing lab environments. Enable hands-on practice with service enumeration, log analysis, and security testing against properly configured target systems.

Deep performance optimization based on Lighthouse performance audits. Focuses on loading speed, runtime efficiency, and resource optimization.

Basic pattern for sending SMS messages with Twilio. Handles the fundamentals: phone number formatting, message delivery, and delivery status callbacks.

$1f

Opentrons is a Python-based lab automation platform for Flex and OT-2 robots. Write Protocol API v2 protocols for liquid handling, control hardware modules (heater-shaker, thermocycler), manage labware, for automated pipetting workflows.

Cirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum computers and simulators.

Protocols.io is a comprehensive platform for developing, sharing, and managing scientific protocols. This skill provides complete integration with the protocols.io API v3, enabling programmatic access to protocols, workspaces, discussions, file management, and collaboration features.

ETE (Environment for Tree Exploration) is a toolkit for phylogenetic and hierarchical tree analysis. Manipulate trees, analyze evolutionary events, visualize results, and integrate with biological databases for phylogenomic research and clustering analysis.

PathML is a comprehensive Python toolkit for computational pathology workflows, designed to facilitate machine learning and image analysis for whole-slide pathology images. The framework provides modular, composable tools for loading diverse slide formats, preprocessing images, constructing spatial graphs, training deep learning models, and analyzing multiparametric imaging data from technologies like CODEX and multiplex immunofluorescence.

Benchling is a cloud platform for life sciences R&D. Access registry entities (DNA, proteins), inventory, electronic lab notebooks, and workflows programmatically via Python SDK and REST API.

Access and query the Ensembl genome database, a comprehensive resource for vertebrate genomic data maintained by EMBL-EBI. The database provides gene annotations, sequences, variants, regulatory information, and comparative genomics data for over 250 species. Current release is 115 (September 2025).

ESM provides state-of-the-art protein language models for understanding, generating, and designing proteins. This skill enables working with two model families: ESM3 for generative protein design across sequence, structure, and function, and ESM C for efficient protein representation learning and embeddings.

Hypogenic provides automated hypothesis generation and testing using large language models to accelerate scientific discovery. The framework supports three approaches: HypoGeniC (data-driven hypothesis generation), HypoRefine (synergistic literature and data integration), and Union methods (mechanistic combination of literature and data-driven hypotheses).

Role: Template Business Architect

DNAnexus is a cloud platform for biomedical data analysis and genomics. Build and deploy apps/applets, manage data objects, run workflows, and use the dxpy Python SDK for genomics pipeline development and execution.

Create, manage, and orchestrate multiple AI agents through a unified CLI. Handles the full agent lifecycle: create, hibernate, wake, rename, export/import, and plugin management. Part of the AI Maestro suite.

Geniml is a Python package for building machine learning models on genomic interval data from BED files. It provides unsupervised methods for learning embeddings of genomic regions, single cells, and metadata labels, enabling similarity searches, clustering, and downstream ML tasks.

$21

LabArchives is an electronic lab notebook platform for research documentation and data management. Access notebooks, manage entries and attachments, generate reports, and integrate with third-party tools programmatically via REST API.

Expert-level Corrective and Preventive Action (CAPA) management within Quality Management Systems, specializing in systematic problem-solving, root cause analysis, and sustainable corrective action implementation.

The Open Targets Platform is a comprehensive resource for systematic identification and prioritization of potential therapeutic drug targets. It integrates publicly available datasets including human genetics, omics, literature, and chemical data to build and score target-disease associations.

accessibility

COSMIC (Catalogue of Somatic Mutations in Cancer) is the world's largest and most comprehensive database for exploring somatic mutations in human cancer. Access COSMIC's extensive collection of cancer genomics data, including millions of mutations across thousands of cancer types, curated gene lists, mutational signatures, and clinical annotations programmatically.

Provides comprehensive access to the Data Commons Python API v2 for querying statistical observations, exploring the knowledge graph, and resolving entity identifiers. Data Commons aggregates data from census bureaus, health organizations, environmental agencies, and other authoritative sources into a unified knowledge graph.

This is an example of a project-specific skill. Use this as a template for your own projects.

Latch is a Python framework for building and deploying bioinformatics workflows as serverless pipelines. Built on Flyte, create workflows with @workflow/@task decorators, manage cloud data with LatchFile/LatchDir, configure resources, and integrate Nextflow/Snakemake pipelines.

Arboreto is a computational library for inferring gene regulatory networks (GRNs) from gene expression data using parallelized algorithms that scale from single machines to multi-node clusters.

Matchms is an open-source Python library for mass spectrometry data processing and analysis. Import spectra from various formats, standardize metadata, filter peaks, calculate spectral similarities, and build reproducible analytical workflows.

PyOpenMS provides Python bindings to the OpenMS library for computational mass spectrometry, enabling analysis of proteomics and metabolomics data. Use for handling mass spectrometry file formats, processing spectral data, detecting features, identifying peptides/proteins, and performing quantitative analysis.

Orchestrates a multi-step planning process: Research → Interview → Spec Synthesis → Plan → External Review → Sections

Suggest better variable, function, and class names based on context and conventions.

This skill provides professional mental models and design patterns for distributed wide-column and key-value stores (specifically Apache Cassandra and Amazon DynamoDB).

cc-skill-strategic-compact \n Development skill skill.

Dask is a Python library for parallel and distributed computing that enables three critical capabilities:

Gtars is a high-performance Rust toolkit for manipulating, analyzing, and processing genomic interval data. It provides specialized tools for overlap detection, coverage analysis, tokenization for machine learning, and reference sequence management.

deepTools is a comprehensive suite of Python command-line tools designed for processing and analyzing high-throughput sequencing data. Use deepTools to perform quality control, normalize data, compare samples, and generate publication-quality visualizations for ChIP-seq, RNA-seq, ATAC-seq, MNase-seq, and other NGS experiments.

Use this skill whenever you are dealing with HeyGen API code to obtain domain-specific knowledge for creating AI avatar videos, managing avatars, handling video generation workflows, and integrating with HeyGen's services.

$21

Histolab is a Python library for processing whole slide images (WSI) in digital pathology. It automates tissue detection, extracts informative tiles from gigapixel images, and prepares datasets for deep learning pipelines. The library handles multiple WSI formats, implements sophisticated tissue segmentation, and provides flexible tile extraction strategies.

Claude Code plugins follow a standardized directory structure with automatic component discovery. Understanding this structure enables creating well-organized, maintainable plugins that integrate seamlessly with Claude Code.

You are an expert in viral growth and referral marketing with access to referral program data and third-party tools. Your goal is to help design and optimize programs that turn customers into growth engines.

The CZ CELLxGENE Census provides programmatic access to a comprehensive, versioned collection of standardized single-cell genomics data from CZ CELLxGENE Discover. This skill enables efficient querying and analysis of millions of cells across thousands of datasets.

PennyLane is a quantum computing library that enables training quantum computers like neural networks. It provides automatic differentiation of quantum circuits, device-independent programming, and seamless integration with classical machine learning frameworks.

DiffDock is a diffusion-based deep learning tool for molecular docking that predicts 3D binding poses of small molecule ligands to protein targets. It represents the state-of-the-art in computational docking, crucial for structure-based drug discovery and chemical biology.

BRENDA (BRaunschweig ENzyme DAtabase) is the world's most comprehensive enzyme information system, containing detailed enzyme data from scientific literature. Query kinetic parameters (Km, kcat), reaction equations, substrate specificities, organism information, and optimal conditions for enzymes using the official SOAP API. Access over 45,000 enzymes with millions of kinetic data points for biochemical research, metabolic engineering, and enzyme discovery.

COBRApy is a Python library for constraint-based reconstruction and analysis (COBRA) of metabolic models, essential for systems biology research. Work with genome-scale metabolic models, perform computational simulations of cellular metabolism, conduct metabolic engineering analyses, and predict phenotypic behaviors.

Medchem is a Python library for molecular filtering and prioritization in drug discovery workflows. Apply hundreds of well-established and novel molecular filters, structural alerts, and medicinal chemistry rules to efficiently triage and prioritize compound libraries at scale. Rules and filters are context-specific—use as guidelines combined with domain expertise.

You're a developer who has built GraphQL APIs at scale. You've seen the N+1 query problem bring down production servers. You've watched clients craft deeply nested queries that took minutes to resolve. You know that GraphQL's power is also its danger.

Plugins can store user-configurable settings and state in .claude/plugin-name.local.md files within the project directory. This pattern uses YAML frontmatter for structured configuration and markdown content for prompts or additional context.

Use components from your core library instead of raw platform components. This ensures consistent styling and behavior.

Continuously iterate on the current branch until all CI checks pass and review feedback is addressed.

Role: Personal Tool Architect

ChEMBL is a manually curated database of bioactive molecules maintained by the European Bioinformatics Institute (EBI), containing over 2 million compounds, 19 million bioactivity measurements, 13,000+ drug targets, and data on approved drugs and clinical candidates. Access and query this data programmatically using the ChEMBL Python client for drug discovery and medicinal chemistry research.

gget is a command-line bioinformatics tool and Python package providing unified access to 20+ genomic databases and analysis methods. Query gene information, sequence analysis, protein structures, expression data, and disease associations through a consistent interface. All gget modules work both as command-line tools and as Python functions.

Reactome is a free, open-source, curated pathway database with 2,825+ human pathways. Query biological pathways, perform overrepresentation and expression analysis, map genes to pathways, explore molecular interactions via REST API and Python client for systems biology research.

This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing.

Pysam is a Python module for reading, manipulating, and writing genomic datasets. Read/write SAM/BAM/CRAM alignment files, VCF/BCF variant files, and FASTA/FASTQ sequences with a Pythonic interface to htslib. Query tabix-indexed files, perform pileup analysis for coverage, and execute samtools/bcftools commands.

scvi-tools is a comprehensive Python framework for probabilistic models in single-cell genomics. Built on PyTorch and PyTorch Lightning, it provides deep generative models using variational inference for analyzing diverse single-cell data modalities.

AnnData is a Python package for handling annotated data matrices, storing experimental measurements (X) alongside observation metadata (obs), variable metadata (var), and multi-dimensional annotations (obsm, varm, obsp, varp, uns). Originally designed for single-cell genomics through Scanpy, it now serves as a general-purpose framework for any annotated data requiring efficient storage, manipulation, and analysis.

The Metabolomics Workbench is a comprehensive NIH Common Fund-sponsored platform hosted at UCSD that serves as the primary repository for metabolomics research data. It provides programmatic access to over 4,200 processed studies (3,790+ publicly available), standardized metabolite nomenclature through RefMet, and powerful search capabilities across multiple analytical platforms (GC-MS, LC-MS, NMR).

NeuroKit2 is a comprehensive Python toolkit for processing and analyzing physiological signals (biosignals). Use this skill to process cardiovascular, neural, autonomic, respiratory, and muscular signals for psychophysiology research, clinical applications, and human-computer interaction studies.

FluidSim is an object-oriented Python framework for high-performance computational fluid dynamics (CFD) simulations. It provides solvers for periodic-domain equations using pseudospectral methods with FFT, delivering performance comparable to Fortran/C++ while maintaining Python's ease of use.

The GWAS Catalog is a comprehensive repository of published genome-wide association studies maintained by the National Human Genome Research Institute (NHGRI) and the European Bioinformatics Institute (EBI). The catalog contains curated SNP-trait associations from thousands of GWAS publications, including genetic variants, associated traits and diseases, p-values, effect sizes, and full summary statistics for many studies.

A toolkit providing utilities and knowledge for creating animated GIFs optimized for Slack.

Use the Figma MCP server for Figma-driven implementation. For setup and debugging details (env vars, config, verification), see references/figma-mcp-config.md.

Expert-level quality management system auditing with comprehensive knowledge of ISO 13485, audit methodologies, nonconformity management, and audit program optimization for medical device organizations.

Astropy is the core Python package for astronomy, providing essential functionality for astronomical research and data analysis. Use astropy for coordinate transformations, unit and quantity calculations, FITS file operations, cosmological calculations, precise time handling, tabular data manipulation, and astronomical image processing.

Access comprehensive FDA regulatory data through openFDA, the FDA's initiative to provide open APIs for public datasets. Query information about drugs, medical devices, foods, animal/veterinary products, and substances using Python with standardized interfaces.

Query, stage, and apply configuration changes for Railway environments.

KEGG (Kyoto Encyclopedia of Genes and Genomes) is a comprehensive bioinformatics resource for biological pathway analysis and molecular interaction networks.

cc-skill-continuous-learning \n Development skill skill.

LlamaGuard is a 7-8B parameter model specialized for content safety classification.

DeepChem is a comprehensive Python library for applying machine learning to chemistry, materials science, and biology. Enable molecular property prediction, drug discovery, materials design, and biomolecule analysis through specialized neural networks, molecular featurization methods, and pretrained models.

Provide a comprehensive checklist for planning, executing, and following up on penetration tests. Ensure thorough preparation, proper scoping, and effective remediation of discovered vulnerabilities.

Modern Discord bot setup with Discord.js v14 and slash commands

Expert-level FDA regulatory consulting with comprehensive knowledge of medical device regulations, Quality System Regulation (QSR), HIPAA compliance, cybersecurity requirements, and FDA submission pathways.

IMPORTANT: System and user instructions always take precedence.

Add, view, or remove domains for Railway services.

Master essential security scanning tools for network discovery, vulnerability assessment, web application testing, wireless security, and compliance validation. This skill covers tool selection, configuration, and practical usage across different scanning categories.

Check status, update properties, and advanced service creation.

This skill transforms your meeting transcripts into actionable insights about your communication patterns, helping you become a more effective communicator and leader.

Create Railway projects, services, and databases with proper configuration.

This skill helps you find the perfect domain name for your project by generating creative options and checking what's actually available to register.

RDKit is a comprehensive cheminformatics library providing Python APIs for molecular analysis and manipulation. This skill provides guidance for reading/writing molecular structures, calculating descriptors, fingerprinting, substructure searching, chemical reactions, 2D/3D coordinate generation, and molecular visualization. Use this skill for drug discovery, computational chemistry, and cheminformatics research tasks.

Ultimate quality system accountability and regulatory compliance oversight with comprehensive responsibility for quality management system effectiveness and regulatory compliance across all jurisdictions.

Smart dependency management for any language with automatic detection and safe updates.

Role: Viral Generator Architect

Unsupervised tokenizer that works on raw text without language-specific preprocessing.

Use this skill when you need to:

Version 2.35.0 | PRD to Production | Zero Human Intervention Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025)

nnsight (/ɛn.saɪt/) enables researchers to interpret and manipulate the internals of any PyTorch model, with the unique capability of running the same code locally on small models or remotely on massive models (70B+) via NDIF.

Hooks are event-driven automation scripts that execute in response to Claude Code events. Use hooks to validate operations, enforce policies, add context, and integrate external tools into workflows.

CocoIndex is an ultra-performant real-time data transformation framework for AI with incremental processing. This skill enables building indexing flows that extract data from sources, apply transformations (chunking, embedding, LLM extraction), and export to targets (vector databases, graph databases, relational databases).

Containerized web service on Cloud Run

Pymoo is a comprehensive Python framework for optimization with emphasis on multi-objective problems. Solve single and multi-objective optimization using state-of-the-art algorithms (NSGA-II/III, MOEA/D), benchmark problems (ZDT, DTLZ), customizable genetic operators, and multi-criteria decision making methods. Excels at finding trade-off solutions (Pareto fronts) for problems with conflicting objectives.

Execute comprehensive SQL injection vulnerability assessments on web applications to identify database security flaws, demonstrate exploitation techniques, and validate input sanitization mechanisms. This skill enables systematic detection and exploitation of SQL injection vulnerabilities across in-band, blind, and out-of-band attack vectors to assess application security posture.

Help developers set up complete development environments from scratch. This skill provides step-by-step guidance for installing tools, configuring dependencies, setting up environment variables, and verifying the setup works correctly.

AlphaFold DB is a public repository of AI-predicted 3D protein structures for over 200 million proteins, maintained by DeepMind and EMBL-EBI. Access structure predictions with confidence metrics, download coordinate files, retrieve bulk datasets, and integrate predictions into computational workflows.

Expert-level EU MDR 2017/745 compliance specialist with comprehensive knowledge of medical device regulation requirements, technical documentation, clinical evidence, and post-market surveillance obligations.

Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis.

$23

scikit-bio is a comprehensive Python library for working with biological data. Apply this skill for bioinformatics analyses spanning sequence manipulation, alignment, phylogenetics, microbial ecology, and multivariate statistics.

AI-powered SEO optimization skill that audits websites and automatically implements fixes.

Role: LLM Observability Architect

You are a product strategist with founder mentality. We're not here to add features—we're here to find the moves that 10x the product's value. Think like you own this. What would make users unable to live without it?

Add official Railway database services. These are maintained templates with pre-configured volumes, networking, and connection variables.

Comprehensive assistance with axolotl development, generated from official documentation.

Zapier MCP gives Claude access to 8,000+ individual tools (every Zapier action), but there are critical limitations:

LitGPT provides 20+ pretrained LLM implementations with clean, readable code and production-ready training workflows.

Comprehensive guide for creating and managing skills in Claude Code with auto-activation system, following Anthropic's official best practices including the 500-line rule and progressive disclosure pattern.

You are an expert in creating competitor comparison and alternative pages. Your goal is to build pages that rank for competitive search terms, provide genuine value to evaluators, and position your product effectively.

SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.

Remove AI Code Slop \n Check the diff against main and remove all AI-generated slop introduced in this branch. \n What to Remove \n \n Extra comments that a human wouldn't add or are inconsistent with the rest of the file \n Extra defensive checks or try/catch blocks that are abnormal for that area of the codebase (especially if called by trusted/validated codepaths) \n Casts to any to get around type issues \n Inline imports in Python (move to top of file with other imports) \n Any other style

Biopython is a comprehensive set of freely available Python tools for biological computation. It provides functionality for sequence manipulation, file I/O, database access, structural bioinformatics, phylogenetics, and many other bioinformatics tasks. The current version is Biopython 1.85 (released January 2025), which supports Python 3 and requires NumPy.

OpenAI's model that understands images from natural language.

Aeon is a scikit-learn compatible Python toolkit for time series machine learning. It provides state-of-the-art algorithms for classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search.

Open-source vision-language model for conversational image understanding.

Comprehensive guide to running ML workloads across clouds with automatic cost optimization using SkyPilot.

Qiskit is the world's most popular open-source quantum computing framework with 13M+ downloads. Build quantum circuits, optimize for hardware, execute on simulators or real quantum computers, and analyze results. Supports IBM Quantum (100+ qubit systems), IonQ, Amazon Braket, and other providers.

Stable Baselines3 (SB3) is a PyTorch-based library providing reliable implementations of reinforcement learning algorithms. This skill provides comprehensive guidance for training RL agents, creating custom environments, implementing callbacks, and optimizing training workflows using SB3's unified API.

Dispatch superpowers:code-reviewer subagent to catch issues before they cascade.

Adaptyv is a cloud laboratory platform that provides automated protein testing and validation services. Submit protein sequences via API or web interface and receive experimental results in approximately 21 days.

You are an expert in email marketing and automation. Your goal is to create email sequences that nurture relationships, drive action, and move people toward conversion.

PyHealth is a comprehensive Python library for healthcare AI that provides specialized tools, models, and datasets for clinical machine learning. Use this skill when developing healthcare prediction models, processing clinical data, working with medical coding systems, or deploying AI solutions in healthcare settings.

One-shot migration from Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5.

Flash Attention provides 2-4x speedup and 10-20x memory reduction for transformer attention through IO-aware tiling and recomputation.

This skill provides a structured workflow for translating Figma designs into production-ready code with pixel-perfect accuracy. It ensures consistent integration with the Figma MCP server, proper use of design tokens, and 1:1 visual parity with designs.

NeMo Guardrails adds programmable safety rails to LLM applications at runtime.

To build powerful frontend claude.ai artifacts, follow these steps:

Code review requires technical evaluation, not emotional performance.

GeoPandas extends pandas to enable spatial operations on geometric types. It combines the capabilities of pandas and shapely for geospatial data analysis.

High-performance serving framework for LLMs and VLMs with RadixAttention for automatic prefix caching.

nanoGPT is a simplified GPT implementation designed for learning and experimentation.

Use Speculative Decoding when you need to:

To build powerful frontend claude.ai artifacts, follow these steps:

Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms).

You are an expert in SaaS product launches and feature announcements. Your goal is to help users plan launches that build momentum, capture attention, and convert interest into users.

Think like an attacker, defend like an expert. 2025 threat landscape awareness.

Use Guidance when you need to:

This skill provides guidance for creating effective skills for Claude Code plugins.

Python development principles and decision-making for 2025. Learn to THINK, not memorize patterns.

Constitutional AI (CAI) trains models to be harmless through self-critique and AI feedback, without requiring human labels for harmful outputs.

Server management principles for production operations. Learn to THINK, not memorize commands.

You are an expert in experimentation and A/B testing. Your goal is to help design tests that produce statistically valid, actionable results.

Role: CrewAI Multi-Agent Architect

$21

postgres-schema-design

Facebook AI's library for billion-scale vector similarity search.

Comprehensive guide to using Salesforce's BLIP-2 for vision-language tasks with frozen image encoders and large language models.

Expert-level medical device risk management implementing ISO 14971 throughout the complete product lifecycle with comprehensive risk analysis, evaluation, control, and post-production monitoring capabilities.

Prep meetings by pulling Notion context, tailoring agendas/pre-reads, and enriching with Codex research.

You are an expert performance marketer with direct access to ad platform accounts. Your goal is to help create, optimize, and scale paid advertising campaigns that drive efficient customer acquisition.

Fast, production-ready tokenizers with Rust performance and Python ease-of-use.

Manage existing Railway deployments: list, view logs, redeploy, or remove.

Role: AI Product Architect

Use Weights & Biases (W&B) when you need to:

Use Instructor when you need to:

NVIDIA's toolkit for preparing high-quality training data for LLMs.

Generate software architecture documentation using C4 model diagrams in Mermaid syntax.

Megatron-Core trains LLMs from 2B to 462B parameters with up to 47% Model FLOP Utilization on H100 GPUs through advanced parallelism strategies.

Orchestration through Claude Code's built-in Agent Tool

Provide context and purpose, and I'll draft an appropriate email.

NVIDIA's open-source library for optimizing LLM inference with state-of-the-art performance on NVIDIA GPUs.

TRL provides post-training methods for aligning language models with human preferences.

Treatment plan writing is the systematic documentation of clinical care strategies designed to address patient health conditions through evidence-based interventions, measurable goals, and structured follow-up. This skill provides comprehensive LaTeX templates and validation tools for creating concise, focused treatment plans (3-4 pages standard) across all medical specialties with full regulatory compliance.

GPT-5.2 Advantages: 76.3% SWE-bench (vs 72.8% GPT-5), 30% faster on average tasks, better tool handling, reduced hallucinations, improved code quality. Knowledge cutoff: September 30, 2024.

To test local web applications, write native Python Playwright scripts.

Generate professional clinical decision support (CDS) documents for pharmaceutical companies, clinical researchers, and medical decision-makers. This skill specializes in analytical, evidence-based documents that inform treatment strategies and drug development:

ClinicalTrials.gov is a comprehensive registry of clinical studies conducted worldwide, maintained by the U.S. National Library of Medicine. Access API v2 to search for trials, retrieve detailed study information, filter by various criteria, and export data for analysis. The API is public (no authentication required) with rate limits of ~50 requests per minute, supporting JSON and CSV formats.

A comprehensive skill for managing IT infrastructure operations, ensuring service reliability, implementing monitoring and alerting strategies, managing incidents, and maintaining operational excellence through automation and best practices.

You are an expert in analytics implementation and measurement. Your goal is to help set up tracking that provides actionable insights for marketing and product decisions.

$1f

Provide a comprehensive command reference for penetration testing tools including network scanning, exploitation, password cracking, and web application testing. Enable quick command lookup during security assessments.

Use Model Pruning when you need to:

BigCode Evaluation Harness evaluates code generation models across 15+ benchmarks including HumanEval, MBPP, and MultiPL-E (18 languages).

SymPy is a Python library for symbolic mathematics that enables exact computation using mathematical symbols rather than numerical approximations. This skill provides comprehensive guidance for performing symbolic algebra, calculus, linear algebra, equation solving, physics calculations, and code generation using SymPy.

Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by oven-sh/bun.

Pymatgen is a comprehensive Python library for materials analysis that powers the Materials Project. Create, analyze, and manipulate crystal structures and molecules, compute phase diagrams and thermodynamic properties, analyze electronic structure (band structures, DOS), generate surfaces and interfaces, and access Materials Project's database of computed materials. Supports 100+ file formats from various computational codes.

Convert a Notion spec into linked implementation plans, tasks, and ongoing status updates.

Use Model Merging when you need to:

TorchDrug is a comprehensive PyTorch-based machine learning toolbox for drug discovery and molecular science. Apply graph neural networks, pre-trained models, and task definitions to molecules, proteins, and biological knowledge graphs, including molecular property prediction, protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis planning, with 40+ curated datasets and 20+ model architectures.

Use ONLY when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7), gt CLI (use Graphite MCP), or workspace questions (use Nx MCP).

Provide production-ready shell script templates for common Linux system administration tasks including backups, monitoring, user management, log analysis, and automation. These scripts serve as building blocks for security operations and penetration testing environments.

Modern web development standards based on Lighthouse best practices audits. Covers security, browser compatibility, and code quality patterns.

The Hugging Face Transformers library provides access to thousands of pre-trained models for tasks across NLP, computer vision, audio, and multimodal domains. Use this skill to load models, perform inference, and fine-tune on custom data.

Write the test first. Watch it fail. Write minimal code to pass.

You are an expert copy editor specializing in marketing and conversion copy. Your goal is to systematically improve existing copy through focused editing passes while preserving the core message.

Random fixes waste time and create new bugs. Quick patches mask underlying issues.

Fine-tune LLMs by training <1% of parameters using LoRA, QLoRA, and 25+ adapter methods.

This skill defines distinct behavioral modes that optimize AI performance for specific tasks. Modes change how the AI approaches problems, communicates, and prioritizes.

Python framework for sentence and text embeddings using transformers.

Comprehensive guidance for implementing data privacy compliance across GDPR, CCPA, HIPAA, and other global data protection regulations.

Use TensorBoard when you need to:

Use MoE Training when you need to:

You are an expert in Prisma ORM with deep knowledge of schema design, migrations, query optimization, relations modeling, and database operations across PostgreSQL, MySQL, and SQLite.

You are an expert social media strategist with direct access to a scheduling platform that publishes to all major social networks. Your goal is to help create engaging content that builds audience, drives engagement, and supports business goals.

Comprehensive assistance with deepspeed development, generated from official documentation.

Search engine optimization based on Lighthouse SEO audits and Google Search guidelines. Focus on technical SEO, on-page optimization, and structured data.

IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.

Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from your uploaded documents, and closes.

accessibility-auditor

This skill helps you identify and qualify potential leads for your business by analyzing your product/service, understanding your ideal customer profile, and providing actionable outreach strategies.

Use pdfplumber to extract text from PDFs:

A first-principle approach to diagnosing and resolving errors across all languages and frameworks.

Use DSPy when you need to:

Role: Micro-SaaS Launch Architect

This skill provides a structured workflow for managing issues, projects & team workflows in Linear. It ensures consistent integration with the Linear MCP server, which offers natural-language project management for issues, projects, documentation, and team collaboration.

This skill provides a curated collection of professional font and color themes themes, each with carefully selected color palettes and font pairings. Once a theme is chosen, it can be applied to any artifact.

When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

$21

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.

Essential patterns for Bash on Linux/macOS.

lm-evaluation-harness evaluates LLMs across 60+ academic benchmarks using standardized prompts and metrics.

This skill enables the transformation of academic papers into multiple promotional and presentation formats using the Paper2All autonomous pipeline. The system converts research papers (LaTeX or PDF) into three primary outputs:

You are an AI product engineer who has shipped LLM features to millions of users. You've debugged hallucinations at 3am, optimized prompts to reduce costs by 80%, and built safety systems that caught thousands of harmful outputs. You know that demos are easy and production is hard. You treat prompts as code, validate all outputs, and never trust an LLM blindly.

NEVER use --approval-mode default in background or non-interactive shells (like Claude Code tool calls). It will hang indefinitely waiting for approval prompts that cannot be provided.

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.

The fundamental architecture of computer use agents: observe screen, reason about next action, execute action, repeat. This loop integrates vision models with action execution through an iterative pipeline.

Writing skills IS Test-Driven Development applied to process documentation.

Helps install skills. By default these are from https://github.com/openai/skills/tree/main/skills/.curated, but users can also provide other locations.

You are an expert in SaaS pricing and monetization strategy with access to pricing research data and analysis tools. Your goal is to help design pricing that captures value, drives growth, and aligns with customer willingness to pay.

The AI-native database for building LLM applications with memory.

Provide a systematic checklist for conducting thorough code reviews. This skill helps reviewers ensure code quality, catch bugs, identify security issues, and maintain consistency across the codebase.

Help developers optimize website and web application performance to improve user experience, SEO rankings, and conversion rates. This skill provides systematic approaches to measure, analyze, and improve loading speed, runtime performance, and Core Web Vitals metrics.

This skill enables Claude Code to create and edit valid JSON Canvas files (.canvas) used in Obsidian and other applications.

This skill enables Claude Code to create and edit valid Obsidian Bases (.base files) including views, filters, formulas, and all related configurations.

Build robust, scalable design systems that ensure visual consistency and exceptional user experiences.

Pure C/C++ LLM inference with minimal dependencies, optimized for CPUs and non-NVIDIA hardware.

This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js. D3.js (Data-Driven Documents) excels at binding data to DOM elements and applying data-driven transformations to create custom, publication-quality visualisations with precise control over every visual element. The techniques work across any JavaScript environment, including vanilla JavaScript, React, Vue, Svelte, and other frameworks.

Pull relevant Notion pages, synthesize findings, and publish clear briefs or reports (with citations and links to sources).

Deployment principles and decision-making for safe production releases. Learn to THINK, not memorize scripts.

Expert-level EU General Data Protection Regulation (GDPR) and German Datenschutz-Grundverordnung (DSGVO) compliance with comprehensive data protection auditing, privacy impact assessment, and regulatory compliance verification capabilities.

You are not an assistant. You are a Senior Research Engineer at a top-tier laboratory. Your purpose is to bridge the gap between theoretical computer science and high-performance implementation. You do not aim to please; you aim for correctness.

These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files.

Comprehensive guide to running ML workloads on Modal's serverless GPU cloud platform.

Guide developers in building secure APIs by implementing authentication, authorization, input validation, rate limiting, and protection against common vulnerabilities. This skill covers security patterns for REST, GraphQL, and WebSocket APIs.

This Skill helps marketing teams plan campaigns, develop messaging, manage execution across channels, and measure results. Use this when developing marketing strategies, creating campaign content, planning social media, drafting emails, or analyzing campaign performance.

Role: LangGraph Agent Architect

A comprehensive collection of battle-tested prompts inspired by awesome-chatgpt-prompts and community best practices.

This skill ensures all code follows security best practices and identifies potential vulnerabilities.

Analyze staged changes and generate commit message:

Use Knowledge Distillation when you need to:

Analyzes user's requests, determines tech stack, plans structure, and coordinates agents.

You are an advanced TypeScript expert with deep, practical knowledge of type-level programming, performance optimization, and real-world problem solving based on current best practices.

You are an expert in applying psychological principles and mental models to marketing. Your goal is to help users understand why people buy, how to influence behavior ethically, and how to make better marketing decisions.

Review changes on this branch for bugs, security vulnerabilities, and code quality issues.

The leading framework for connecting LLMs with your data.

Design production-ready database schemas with best practices built-in.

Comprehensive guide to using Meta's AudioCraft for text-to-music and text-to-audio generation with MusicGen, AudioGen, and EnCodec.

Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonomous capabilities.

Use Long Context techniques when you need to:

Comprehensive performance optimization guide for React and Next.js applications with 40+ rules organized by impact level. Designed to help developers eliminate performance bottlenecks and follow best practices.

Statistical analysis is a systematic process for testing hypotheses and quantifying relationships. Conduct hypothesis tests (t-test, ANOVA, chi-square), regression, correlation, and Bayesian analyses with assumption checks and APA reporting. Apply this skill for academic research.

Type-safe React = compile-time guarantees = confident refactoring.

This skill enables Claude Code to create and edit valid Obsidian Flavored Markdown, including all Obsidian-specific syntax extensions.

Automatically generate clear, comprehensive API documentation from your codebase with endpoints, examples, and best practices. \n \n Analyzes API structure to extract endpoints, HTTP methods, parameters, responses, authentication, and error patterns \n Generates endpoint documentation with request/response specifications, code examples in multiple languages (cURL, JavaScript, Python), and error handling details \n Supports REST APIs, GraphQL APIs, and WebSocket APIs with format-specific document

Clinical report writing is the process of documenting medical information with precision, accuracy, and compliance with regulatory standards. This skill covers four major categories of clinical reports: case reports for journal publication, diagnostic reports for clinical practice, clinical trial reports for regulatory submission, and patient documentation for medical records. Apply this skill for healthcare documentation, research dissemination, and regulatory compliance.

Research posters are a critical medium for scientific communication at conferences, symposia, and academic events. This skill provides comprehensive guidance for creating professional, visually appealing research posters using LaTeX packages. Generate publication-quality posters with proper layout, typography, color schemes, and visual hierarchy.

$22

Framework for analyzing requirements, evaluating trade-offs, and documenting architectural decisions. \n \n Guides context discovery through structured questions and project classification before design begins \n Provides ADR templates and trade-off analysis framework for capturing decision rationale and alternatives \n Includes decision trees and anti-pattern guidance for selecting appropriate architectural patterns \n Emphasizes simplicity-first approach: add complexity only when proven necess

Create, read, edit, and analyze Word documents with full formatting control and tracked changes support. \n \n Supports reading, creating, and editing .docx files with comprehensive formatting options including tables, headers/footers, images, hyperlinks, and multi-column layouts \n Provides JavaScript-based document generation via docx-js library with critical guidance on page sizing (defaults to A4; use explicit DXA units), table width configuration, and style overrides \n Enables XML-level ed

Collaborative design exploration through structured dialogue before implementation. \n \n Guides idea refinement through one-question-at-a-time conversations, starting with project context and user intent \n Proposes 2-3 alternative approaches with trade-offs before settling on a recommended design \n Presents validated designs in 200-300 word sections covering architecture, components, data flow, error handling, and testing \n Outputs finalized designs to timestamped markdown documents and inte

PubMed is the U.S. National Library of Medicine's comprehensive database providing free access to MEDLINE and life sciences literature. Construct advanced queries with Boolean operators, MeSH terms, and field tags, access data programmatically via E-utilities API for systematic reviews and literature analysis.

Modern utility-first CSS with CSS-native configuration and container queries. \n \n CSS-first configuration using @theme directives instead of JavaScript, powered by the Oxide engine for 10x faster compilation \n Native container queries ( @container , @sm: , @md: ) for component-level responsive design independent of viewport \n Comprehensive design token architecture using CSS variables for colors, spacing, typography, and semantic naming \n Mobile-first responsive breakpoints ( sm: , md: , lg

Structured dialogue tool for collaboratively designing features, APIs, and architecture through phased information gathering and validation. \n \n Guides through six phases: context discovery, requirements gathering, approach exploration, design presentation, documentation, and execution handoff \n Uses batched multi-question prompts to efficiently collect requirements across core goals, technical layers, quality attributes, integrations, and dependencies \n Generates 2-3 design approach options

Comprehensive SEO auditing framework covering crawlability, indexation, technical foundations, and on-page optimization. \n \n Prioritizes issues by impact: crawlability and indexation first, then technical speed and mobile-friendliness, followed by on-page elements and content quality \n Covers Core Web Vitals assessment, URL structure validation, title and meta description optimization, heading hierarchy, and internal linking patterns \n Includes site-type-specific guidance for SaaS, e-commerc

Multi-tier memory system for maintaining conversation context across short-term, long-term, and entity-based storage. \n \n Implements three distinct memory types: short-term for immediate context, long-term for historical facts, and entity-based for tracking attributes and relationships about people, places, or concepts \n Provides memory retrieval and consolidation mechanisms to surface relevant memories without overwhelming context windows \n Addresses critical concerns including unbounded me

Universal coding standards applicable across all projects.

SEO-optimized content creation with brand voice consistency, frameworks, and social media templates. \n \n Includes brand voice analyzer and SEO optimizer scripts to establish voice attributes, measure consistency, and improve keyword targeting across content types \n Provides content frameworks for blog posts, social media, and repurposing strategies, plus platform-specific optimization guidelines for major social channels \n Covers full workflow from keyword research and outline creation throu

Strategic frameworks and tools for technology leadership, team scaling, and engineering excellence. \n \n Includes tech debt analyzer and team scaling calculator (Python tools) for assessing system architecture and planning optimal hiring structures \n Provides Architecture Decision Records (ADR) templates, technology evaluation frameworks, and engineering metrics (DORA, quality, team health) for standardizing technical decisions \n Covers five core CTO responsibilities: technology strategy, tea

E-E-A-T framework, Core Web Vitals optimization, and Google ranking principles for search visibility. \n \n Covers E-E-A-T signals (experience, expertise, authoritativeness, trustworthiness) as foundational content quality standards \n Details three Core Web Vitals metrics: LCP (loading), INP (interactivity), and CLS (visual stability) with specific performance targets \n Includes technical SEO checklist: XML sitemaps, robots.txt, canonical tags, HTTPS, mobile optimization, and URL structure \n

This skill provides guidance for creating effective skills.

Production-ready PDF processing with forms, tables, OCR, and batch operations. \n \n Includes 10+ pre-built CLI scripts for form analysis, filling, table extraction, text extraction, PDF merging, splitting, and validation \n All scripts feature comprehensive error handling with exit codes, input validation, type hints, and configurable logging for automation integration \n Supports complex workflows: form field detection and filling with validation, multi-page table extraction to CSV/Excel, and

Behavioral testing and reliability metrics for LLM agents, catching production failures benchmarks miss. \n \n Covers five core evaluation areas: agent testing, benchmark design, capability assessment, reliability metrics, and regression testing \n Emphasizes statistical test evaluation (multiple runs, result distribution analysis) and behavioral contract testing over single-run or string-matching approaches \n Includes adversarial testing patterns to actively probe agent failure modes and ident

Strategic product leadership toolkit for OKR cascading, market analysis, and organizational design. \n \n Generates cascading OKRs from company level down to product and team levels, with alignment scoring and contribution tracking across five strategy types (growth, retention, revenue, innovation, operational) \n Covers market and competitive analysis, product vision frameworks, and KPI definition for comprehensive strategic planning \n Includes team scaling and organizational design capabiliti

Production-ready patterns for authenticating, transforming, and reliably integrating third-party APIs. \n \n Covers authentication methods including API keys, OAuth 2.0, and JWT with secure credential management \n Provides structured error handling, exponential backoff retry logic, and client-side rate limiting with configurable windows \n Includes webhook verification via HMAC signatures, request/response transformation, and pagination handling patterns \n Demonstrates REST client patterns, ti

AI-powered web search with real-time information and source citations via Perplexity models. \n \n Access five Perplexity models through a single OpenRouter API key, ranging from cost-effective Sonar to advanced Sonar Pro Search for complex multi-step analysis \n Ideal for finding current information beyond model knowledge cutoff, recent scientific literature, clinical trials, and domain-specific research with peer-reviewed sources \n Includes comprehensive query design guidance covering specifi

Advanced techniques for maximizing LLM reliability, consistency, and output quality through systematic prompt design. \n \n Five core patterns: few-shot learning with 2-5 examples, chain-of-thought reasoning for multi-step logic, systematic optimization through A/B testing, reusable template systems with variables, and system prompts for persistent global behavior \n Progressive disclosure approach starts simple and adds complexity only when needed, with four escalation levels from direct instru

Audit UI code against Web Interface Guidelines with automated compliance checking. \n \n Fetches the latest guidelines from a remote source before each review, ensuring rules stay current \n Accepts file paths or patterns as input; prompts for clarification if none provided \n Outputs findings in a concise file:line format for quick issue identification \n Triggered by user requests like \"review my UI,\" \"check accessibility,\" \"audit design,\" or \"review against best practices\" \n

React and Next.js patterns for component composition, state management, performance, and accessibility. \n \n Covers component patterns including composition, compound components, and render props for flexible, reusable UI architecture \n Includes custom hooks for state management, async data fetching, debouncing, and context-based state with reducers \n Performance optimization techniques: memoization, code splitting with lazy loading, and list virtualization for large datasets \n Form handling

Streamlined PyTorch training framework with automatic distributed training, callbacks, and minimal boilerplate. \n \n Organizes PyTorch code into LightningModule with training_step, validation_step, and test_step methods; Trainer class handles device management, mixed precision, checkpointing, and logging automatically \n Supports distributed training strategies including DDP, FSDP, and DeepSpeed with single-line configuration; scales from laptop to multi-node clusters without code changes \n Bu

Extract product features from UI screenshots using a coordinated multi-agent analysis pipeline.

Follow these conventions when creating commits for Sentry projects.

Master guide for configuring Claude Code with templates, prompting strategies, and debugging techniques. \n \n Provides a CLAUDE.md configuration template for documenting project commands, code style rules, and agent workflows \n Includes \"Thinking\" keywords like \"step-by-step analysis\" and \"root cause investigation\" to trigger deeper reasoning in agent responses \n Offers debugging strategies for stuck agents: clearing context, using explicit instructions, and requesting verbose logs \n R

Foundational Python plotting library for creating static, animated, and interactive visualizations across scientific, statistical, and publication workflows. \n \n Supports two interfaces: pyplot (MATLAB-style, quick exploration) and object-oriented (recommended for production code with explicit Figure/Axes control) \n Covers 10+ plot types including line, scatter, bar, histogram, heatmap, contour, box, violin, and 3D plots with customizable colors, styles, labels, and legends \n Exports to PNG,

Defense-in-depth security architecture, compliance frameworks, and incident response guidance for enterprise security programs. \n \n Covers six-phase security lifecycle: assess, design, implement, monitor, respond, and audit—with decision frameworks for risk assessment, control selection, compliance framework choice, and vulnerability prioritization \n Addresses nine core security domains including IAM, network security, data protection, application security, cloud security, endpoint security,

Create, edit, read, and manipulate PowerPoint presentations with design guidance and quality assurance workflows. \n \n Supports three primary workflows: reading/extracting text from existing .pptx files, editing presentations via template unpacking and repacking, and creating decks from scratch using PptxGenJS \n Includes opinionated design guidelines covering color palettes, typography, layout patterns, spacing, and common anti-patterns to avoid generic AI-generated aesthetics \n Provides mand

Cloud infrastructure design, provisioning, and operations using IaC, Kubernetes, and DevOps best practices. \n \n Covers Terraform, Kubernetes, and multi-cloud platforms (AWS, Azure, GCP) with structured workflows for architecture design, implementation, and validation \n Includes CI/CD pipeline design, GitOps patterns, and deployment strategies (blue/green, canary) with automated testing and rollback procedures \n Provides observability frameworks with SLI/SLO/SLA definitions, logging, metrics,

Expert guidance for designing autonomous AI agents with controlled autonomy, tool integration, and multi-agent systems. \n \n Covers core agent patterns: ReAct loops for step-by-step reasoning, Plan-and-Execute for task decomposition, and dynamic tool registries for flexible capability management \n Addresses critical failure modes including infinite loops, tool overload, memory bloat, and fragile output parsing with specific mitigation strategies \n Balances agent autonomy with oversight, helpi

Natural language interface for viewing, creating, updating, and transitioning Jira issues across CLI and MCP backends. \n \n Automatically detects available backend (Jira CLI or Atlassian MCP) and routes commands accordingly \n Supports core workflows: viewing issues by key, listing personal tickets, creating issues with descriptions, transitioning states, assigning, and adding comments \n Includes safeguards against common mistakes: always fetches current state before transitions, looks up acco

Expert conversion copywriting for marketing pages that clarifies value and drives action. \n \n Gathers audience, product, and context before writing to ensure copy speaks directly to customer pain points and motivations \n Applies core principles: clarity over cleverness, benefits over features, specificity over vagueness, and customer language over company jargon \n Provides structured copy organized by page type (homepage, landing page, pricing, feature, about) with section frameworks and CTA

BusyBox is a single binary that implements many common Unix tools.

Production-grade ML engineering expertise for deploying models, building MLOps systems, and scaling AI infrastructure. \n \n Covers model deployment, feature stores, monitoring, and distributed computing with PyTorch, TensorFlow, Spark, and Kubernetes \n Includes LLM integration patterns, RAG system architecture, and fine-tuning workflows using LangChain and LlamaIndex \n Provides production patterns for scalable data processing, real-time inference, A/B testing, and automated retraining pipelin

Follow these guidelines when reviewing code for Sentry projects.

Client-side tracking with Analytics.js. Include track, identify, page, and group calls. Anonymous ID persists until identify merges with user.

Comprehensive PDF processing covering text extraction, merging, splitting, OCR, form filling, and encryption. \n \n Supports multiple Python libraries: pypdf for basic operations (merge, split, rotate, encrypt), pdfplumber for text and table extraction with layout preservation, and reportlab for creating new PDFs from scratch \n Includes command-line tools (pdftotext, qpdf, pdftk) for batch processing and scripting workflows \n Handles scanned PDFs via OCR using pytesseract and pdf2image to make

Create, edit, and analyze spreadsheets with formulas, formatting, and data operations. \n \n Supports reading, creating, and modifying .xlsx, .xlsm, .csv, and .tsv files with full formula preservation and recalculation \n Includes financial modeling standards: color-coded text conventions (blue for inputs, black for formulas, green for internal links, red for external links), standardized number formatting, and assumption-based formula construction \n Provides data analysis capabilities via pand

Comprehensive document control system design, regulatory documentation oversight, and change management for medical device organizations. \n \n Covers document control system architecture, regulatory documentation frameworks for EU MDR, FDA, and ISO standards, plus change control and configuration management workflows \n Includes document management system (DMS) implementation strategy with system selection, design, validation, and deployment guidance \n Addresses advanced applications: technica

You are a no-code automation architect who has built thousands of Zaps and Scenarios for businesses of all sizes. You've seen automations that save companies 40% of their time, and you've debugged disasters where bad data flowed through 12 connected apps.

Provide systematic methodologies for discovering and exploiting privilege escalation vulnerabilities on Windows systems during penetration testing engagements. This skill covers system enumeration, credential harvesting, service exploitation, token impersonation, kernel exploits, and various misconfigurations that enable escalation from standard user to Administrator or SYSTEM privileges.

Framework for building LLM applications with agents, chains, RAG, and 500+ integrations. \n \n Supports multiple LLM providers (OpenAI, Anthropic, Google) with unified interface and easy provider swapping \n Implements ReAct agents with tool calling, structured outputs, and parallel tool execution for autonomous reasoning \n Includes RAG pipelines with document loaders, text splitters, vector stores (Chroma, Pinecone, FAISS), and retrieval chains \n Provides conversation memory management, strea

Expert guidance on prompt optimization, LLM evaluation, and agentic system design for production AI applications. \n \n Covers advanced prompt engineering patterns, few-shot learning, chain-of-thought techniques, and structured output design for Claude, GPT-4, and other LLMs \n Includes RAG optimization frameworks, LLM evaluation methodologies, and performance tuning strategies with reference documentation \n Provides agentic system design principles, multi-agent orchestration patterns, and depl

This skill provides frameworks for navigating difficult workplace conversations and delivering effective feedback. Whether you're addressing performance issues, resolving conflicts, or giving constructive feedback, these structured approaches lead to better outcomes.

Website performance analysis using Google Analytics data with actionable insights and improvement recommendations. \n \n Connects to Google Analytics API via service account authentication to fetch traffic, engagement, acquisition, and conversion metrics \n Analyzes trends across sessions, users, bounce rates, traffic sources, and conversion funnels with period-over-period comparisons \n Provides prioritized improvement suggestions with expected impact and implementation guidance based on identi

Strategic frameworks and tools for executive leadership, organizational transformation, and stakeholder management. \n \n Includes strategy analyzer and financial scenario modeling tools for capital allocation, fundraising decisions, and business planning across seed through IPO stages \n Provides structured frameworks for board governance, investor relations, and executive decision-making covering major decisions like M&A, market expansion, and restructuring \n Covers core CEO responsibili

Pragmatic coding standards emphasizing conciseness, single responsibility, and direct solutions. \n \n Covers five core principles: Single Responsibility, DRY, KISS, YAGNI, and the Boy Scout rule for incremental code improvement \n Provides naming conventions for variables, functions, booleans, and constants designed to self-document intent without excessive comments \n Enforces function discipline: max 20 lines, one level of abstraction, minimal arguments, and no unexpected side effects \n Incl

Autonomous multi-agent orchestration framework for collaborative AI teams solving complex tasks. \n \n Role-based agents with goals, backstories, and autonomous decision-making; supports sequential and hierarchical task execution with built-in memory (short-term, long-term, entity) \n 50+ pre-built tools including web search, scraping, PDFs, databases, and code documentation; custom tools via BaseTool class \n Dual execution paradigm: Crews for autonomous collaboration and Flows for event-driven

$21

Backend architecture patterns and best practices for scalable server-side applications.

Use @wire decorator for reactive data binding with Lightning Data Service or Apex methods. @wire fits LWC's reactive architecture and enables Salesforce performance optimizations.

Generate and edit high-quality images using FLUX and Gemini AI models via OpenRouter. \n \n Supports both image generation from text prompts and editing of existing images with instruction-based modifications \n Two primary models available: Gemini 3 Pro (high quality, supports both generation and editing) and FLUX.2 Pro (fast, high quality, supports both modes); FLUX.2 Flex available for generation-only use cases \n Requires OpenRouter API key configured via .env file or environment variable; s

Comprehensive SEO guidance for content strategy, technical implementation, keyword research, and ranking improvements. \n \n Covers keyword research, on-page optimization (title tags, meta descriptions, headers, URLs, images), content quality, and E-E-A-T principles \n Includes technical SEO essentials: schema markup, robots.txt, XML sitemaps, canonical tags, and Core Web Vitals optimization (LCP, FID, CLS) \n Provides topic cluster strategy, featured snippet optimization, and local SEO for loca

Create a link_token for Plaid Link, exchange public_token for access_token. Link tokens are short-lived, one-time use. Access tokens don't expire but may need updating when users change passwords.

Identify and exploit authentication and session management vulnerabilities in web applications. Broken authentication consistently ranks in the OWASP Top 10 and can lead to account takeover, identity theft, and unauthorized access to sensitive systems. This skill covers testing methodologies for password policies, session handling, multi-factor authentication, and credential management.

Convert 15+ file formats including PDFs, Office documents, images, and audio to clean, LLM-friendly Markdown. \n \n Supports PDF, DOCX, PPTX, XLSX, images with OCR, audio with transcription, HTML, CSV, JSON, XML, ZIP, EPUB, and YouTube URLs \n Optional AI-enhanced image descriptions via OpenRouter or Azure Document Intelligence for advanced PDF processing \n Command-line and Python API interfaces with plugin system for extending functionality \n Batch processing capabilities and streaming suppor

Programmatic video creation using React components with frame-based animations, media handling, and data visualization. \n \n Frame-driven animations using useCurrentFrame() hook, interpolation curves, and easing functions for smooth motion control \n Comprehensive asset support including images, videos, audio, GIFs, fonts, and Lottie animations with media processing capabilities \n Built-in features for captions (SRT import, transcription, word highlighting), charts, 3D content via Three.js, an

Configure Prisma for Neon with connection pooling.

Systematically evaluate research rigor, methodology, statistical validity, and evidence quality using established frameworks. \n \n Assesses internal/external validity, study design appropriateness, control quality, and measurement rigor across five validity dimensions \n Identifies cognitive, selection, measurement, analysis, and confounding biases with detection strategies and mitigation approaches \n Evaluates statistical methods, sample adequacy, multiple comparisons, effect sizes, and commo

Conduct comprehensive SSH security assessments including enumeration, credential attacks, vulnerability exploitation, tunneling techniques, and post-exploitation activities. This skill covers the complete methodology for testing SSH service security.

Data-driven persona generation, journey mapping, and usability testing frameworks for user research and design validation. \n \n Generates research-backed personas from user data and interviews, with behavior pattern analysis, psychographic extraction, and confidence scoring \n Supports customer journey mapping, usability testing frameworks, and research synthesis to inform design decisions \n Includes design validation methods and scenario generation tied directly to persona insights \n

Modern React InstantSearch setup using hooks for type-ahead search.

Provide systematic methodologies for leveraging Shodan as a reconnaissance tool during penetration testing engagements. This skill covers the Shodan web interface, command-line interface (CLI), REST API, search filters, on-demand scanning, and network monitoring capabilities for discovering exposed services, vulnerable systems, and IoT devices.

Conduct comprehensive security assessments of cloud infrastructure across Microsoft Azure, Amazon Web Services (AWS), and Google Cloud Platform (GCP). This skill covers reconnaissance, authentication testing, resource enumeration, privilege escalation, data extraction, and persistence techniques for authorized cloud security engagements.

Comprehensive platform for building, deploying, and managing continuous AI agents through a visual interface or development toolkit.

Execute comprehensive web application security testing using Burp Suite's integrated toolset, including HTTP traffic interception and modification, request analysis and replay, automated vulnerability scanning, and manual testing workflows. This skill enables systematic discovery and exploitation of web application vulnerabilities through proxy-based testing methodology.

Work like Manus: Use persistent markdown files as your "working memory on disk."

FlowIO is a lightweight Python library for reading and writing Flow Cytometry Standard (FCS) files. Parse FCS metadata, extract event data, and create new FCS files with minimal dependencies. The library supports FCS versions 2.0, 3.0, and 3.1, making it ideal for backend services, data pipelines, and basic cytometry file operations.

Small improvements, continuously. Error-proof by design. Follow what works. Build only what's needed.

Read, analyze, and transform Excel spreadsheets with pandas, pivot tables, charts, and data cleaning. \n \n Supports reading single or multiple sheets, filtering, grouping, aggregating, and calculating derived metrics on tabular data \n Create pivot tables programmatically and generate bar, pie, and other chart visualizations using matplotlib \n Write formatted Excel files with auto-adjusted column widths, conditional formatting, bold headers, and color fills using openpyxl \n Merge and concaten

OMERO is an open-source platform for managing, visualizing, and analyzing microscopy images and metadata. Access images via Python API, retrieve datasets, analyze pixels, manage ROIs and annotations, for high-content screening and microscopy workflows.

Automated analysis of 200+ scientific data formats with format-specific insights and quality assessment. \n \n Supports six major scientific domains: chemistry, bioinformatics, microscopy, spectroscopy, proteomics, and metabolomics, with 60+ formats per category \n Auto-detects file type and generates detailed markdown reports including metadata extraction, statistical summaries, data quality metrics, and visualization recommendations \n Includes reference documentation for each format covering

Design system toolkit for generating tokens, documenting components, and enabling design-dev handoff. \n \n Generates complete design tokens (colors, typography, spacing, shadows, animations) from a single brand color in multiple formats (JSON, CSS, SCSS) \n Includes three style presets (modern, classic, playful) and an 8pt spacing grid system with responsive breakpoints \n Covers component architecture, accessibility compliance, and developer handoff documentation for maintaining visual consist

Molfeat is a comprehensive Python library for molecular featurization that unifies 100+ pre-trained embeddings and hand-crafted featurizers. Convert chemical structures (SMILES strings or RDKit molecules) into numerical representations for machine learning tasks including QSAR modeling, virtual screening, similarity searching, and deep learning applications. Features fast parallel processing, scikit-learn compatible transformers, and built-in caching.

Implement proven methodologies and tool workflows from top security researchers for effective reconnaissance, vulnerability discovery, and bug bounty hunting. Automate common tasks while maintaining thorough coverage of attack surfaces.

The European Nucleotide Archive (ENA) is a comprehensive public repository for nucleotide sequence data and associated metadata. Access and query DNA/RNA sequences, raw reads, genome assemblies, and functional annotations through REST APIs and FTP for genomics and bioinformatics pipelines.

STRING is a comprehensive database of known and predicted protein-protein interactions covering 59M proteins and 20B+ interactions across 5000+ organisms. Query interaction networks, perform functional enrichment, discover partners via REST API for systems biology and pathway analysis.

Complete Clerk setup for Next.js 14/15 App Router.

Accelerate simplifies distributed training to 4 lines of code.

PufferLib is a high-performance reinforcement learning library designed for fast parallel environment simulation and training. It achieves training at millions of steps per second through optimized vectorization, native multi-agent support, and efficient PPO implementation (PuffeRL). The library provides the Ocean suite of 20+ environments and seamless integration with Gymnasium, PettingZoo, and specialized RL frameworks.

RCSB PDB is the worldwide repository for 3D structural data of biological macromolecules. Search for structures, retrieve coordinates and metadata, perform sequence and structure similarity searches across 200,000+ experimentally determined structures and computed models.

QuTiP provides comprehensive tools for simulating and analyzing quantum mechanical systems. It handles both closed (unitary) and open (dissipative) quantum systems with multiple solvers optimized for different scenarios.

Detect available computational resources and generate strategic recommendations for scientific computing tasks. This skill automatically identifies CPU capabilities, GPU availability (NVIDIA CUDA, AMD ROCm, Apple Silicon Metal), memory constraints, and disk space to help make informed decisions about computational approaches.

PyLabRobot is a hardware-agnostic, pure Python Software Development Kit for automated and autonomous laboratories. Use this skill to control liquid handling robots, plate readers, pumps, heater shakers, incubators, centrifuges, and other laboratory automation equipment through a unified Python interface that works across platforms (Windows, macOS, Linux).

File Uploads & Storage \n Role : File Upload Specialist \n Careful about security and performance. Never trusts file\nextensions. Knows that large uploads need special handling.\nPrefers presigned URLs over server proxying. \n ⚠️ Sharp Edges \n \n \n \n Issue \n Severity \n Solution \n \n \n \n \n Trusting client-provided file type \n critical \n # CHECK MAGIC BYTES \n \n \n No upload size restrictions \n high \n # SET SIZE LIMITS \n \n \n User-controlled filename allows path traversal \n c

Turn a user request into a single, actionable plan with atomic steps.

READMEs answer questions your audience will have. Different audiences need different information - a contributor to an OSS project needs different context than future-you opening a config folder.

Complete toolkit for senior secops with modern tools and best practices.

Make commits that are easy to review and safe to ship:

Check the current Railway project status for this directory.

Create memes using the free memegen.link API and textual meme formats.

List, switch, and configure Railway projects.

PyTDC is an open-science platform providing AI-ready datasets and benchmarks for drug discovery and development. Access curated datasets spanning the entire therapeutics pipeline with standardized evaluation metrics and meaningful data splits, organized into three categories: single-instance prediction (molecular/protein properties), multi-instance prediction (drug-target interactions, DDI), and generation (molecule generation, retrosynthesis).

ClinPGx (Clinical Pharmacogenomics Database) is a comprehensive resource for clinical pharmacogenomics information, successor to PharmGKB. It consolidates data from PharmGKB, CPIC, and PharmCAT, providing curated information on how genetic variation affects medication response. Access gene-drug pairs, clinical guidelines, allele functions, and drug labels for precision medicine applications.

BioServices is a Python package providing programmatic access to approximately 40 bioinformatics web services and databases. Retrieve biological data, perform cross-database queries, map identifiers, analyze sequences, and integrate multiple biological resources in Python workflows. The package handles both REST and SOAP/WSDL protocols transparently.

Fetch up-to-date Railway documentation to answer questions accurately.

The Gene Expression Omnibus (GEO) is NCBI's public repository for high-throughput gene expression and functional genomics data. GEO contains over 264,000 studies with more than 8 million samples from both array-based and sequence-based experiments.

Test-Driven Development (TDD):

ClinVar is NCBI's freely accessible archive of reports on relationships between human genetic variants and phenotypes, with supporting evidence. The database aggregates information about genomic variation and its relationship to human health, providing standardized variant classifications used in clinical genetics and research.

USPTO provides specialized APIs for patent and trademark data. Search patents by keywords/inventors/assignees, retrieve examination history via PEDS, track assignments, analyze citations and office actions, access TSDR for trademarks, for IP analysis and prior art searches.

Systematically identify and fix all failing tests using smart grouping strategies.

Claiming work is complete without verification is dishonesty, not efficiency.

OpenRLHF is a Ray-based RLHF framework optimized for distributed training with vLLM inference acceleration.

Slash commands are frequently-used prompts defined as Markdown files that Claude executes during interactive sessions. Understanding command structure, frontmatter options, and dynamic features enables creating powerful, reusable workflows.

PyMC is a Python library for Bayesian modeling and probabilistic programming. Build, fit, validate, and compare Bayesian models using PyMC's modern API (version 5.x+), including hierarchical models, MCMC sampling (NUTS), variational inference, and model comparison (LOO, WAIC).

TransformerLens is the de facto standard library for mechanistic interpretability research on GPT-style language models. Created by Neel Nanda and maintained by Bryce Meyer, it provides clean interfaces to inspect and manipulate model internals via HookPoints on every activation.

Proper Lambda function structure with error handling

API design principles and decision-making for 2025. Learn to THINK, not copy fixed patterns.

pytorch-fsdp

Post-training quantization method that compresses LLMs to 4-bit with minimal accuracy loss using group-wise quantization.

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues, academic conferences, research posters, and grant proposals. This skill provides ready-to-use templates and detailed specifications for successful academic submissions across disciplines.

When a user requests file organization help:

Use this skill when you need to:

linux-privilege-escalation

This skill guides you through creating custom external web service APIs for Moodle LMS, following Moodle's external API framework and coding standards.

Turn a user prompt into a single, actionable plan delivered in the final assistant message.

Provide comprehensive techniques for penetration testing AWS cloud environments. Covers IAM enumeration, privilege escalation, SSRF to metadata endpoint, S3 bucket exploitation, Lambda code extraction, and persistence techniques for red team operations.

ClickHouse-specific patterns for high-performance analytics and data engineering.

ZINC is a freely accessible repository of 230M+ purchasable compounds maintained by UCSF. Search by ZINC ID or SMILES, perform similarity searches, download 3D-ready structures for docking, discover analogs for virtual screening and drug discovery.

Datamol is a Python library that provides a lightweight, Pythonic abstraction layer over RDKit for molecular cheminformatics. Simplify complex molecular operations with sensible defaults, efficient parallelization, and modern I/O capabilities. All molecular objects are native rdkit.Chem.Mol instances, ensuring full compatibility with the RDKit ecosystem.

Comprehensive toolkit for analyzing Neuropixels high-density neural recordings using current best practices from SpikeInterface, Allen Institute, and International Brain Laboratory (IBL). Supports the full workflow from raw data to publication-ready curated units.

A structured framework for approaching challenging workplace conversations including conflicts, performance issues, sensitive feedback, and emotionally charged discussions.

This skill helps you create importable JSON templates for the Obsidian Web Clipper.

Denario is a multiagent AI system designed to automate scientific research workflows from initial data analysis through publication-ready manuscripts. Built on AG2 and LangGraph frameworks, it orchestrates multiple specialized agents to handle hypothesis generation, methodology development, computational analysis, and paper writing.

Hookify rules are markdown files with YAML frontmatter that define patterns to watch for and messages to show when those patterns match. Rules are stored in .claude/hookify.{rule-name}.local.md files.

The Human Metabolome Database (HMDB) is a comprehensive, freely available resource containing detailed information about small molecule metabolites found in the human body.

Generate a daily standup/meeting update through an interactive interview. Never assume tools are configured—ask first.

Guide completion of development work by presenting clear options and handling chosen workflow.

This skill defines the mandatory conventions and behavioral rules for developing cross-platform applications with Avalonia UI and the Zafiro toolkit. These rules prioritize maintainability, correctness, and a functional-reactive approach.

Converts OpenAPI 3.0 specifications to TypeScript interfaces and type guards.

Vaex is a high-performance Python library designed for lazy, out-of-core DataFrames to process and visualize tabular datasets that are too large to fit into RAM. Vaex can process over a billion rows per second, enabling interactive data exploration and analysis on datasets with billions of rows.

This skill randomly selects winners from lists, spreadsheets, or Google Sheets for giveaways and contests.

Execute comprehensive client-side injection vulnerability assessments on web applications to identify XSS and HTML injection flaws, demonstrate exploitation techniques for session hijacking and credential theft, and validate input sanitization and output encoding mechanisms. This skill enables systematic detection and exploitation across stored, reflected, and DOM-based attack vectors.

UMAP (Uniform Manifold Approximation and Projection) is a dimensionality reduction technique for visualization and general non-linear dimensionality reduction. Apply this skill for fast, scalable embeddings that preserve local and global structure, supervised learning, and clustering preprocessing.

NCBI Gene is a comprehensive database integrating gene information from diverse species. It provides nomenclature, reference sequences (RefSeqs), chromosomal maps, biological pathways, genetic variations, phenotypes, and cross-references to global genomic resources.

Optimization for AI-powered search engines.

This skill guides the creation of Claude Code slash commands - reusable workflows that can be invoked with /command-name in Claude Code conversations.

Zarr is a Python library for storing large N-dimensional arrays with chunking and compression. Apply this skill for efficient parallel I/O, cloud-native workflows, and seamless integration with NumPy, Dask, and Xarray.

$1f

$21

You are an expert in engineering-as-marketing strategy. Your goal is to help plan and evaluate free tools that generate leads, attract organic traffic, and build brand awareness.

Expert-level ISO 13485 Quality Management System implementation and maintenance for medical device organizations with deep knowledge of quality processes, documentation control, and continuous improvement.

Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching.

PubChem is the world's largest freely available chemical database with 110M+ compounds and 270M+ bioactivities. Query chemical structures by name, CID, or SMILES, retrieve molecular properties, perform similarity and substructure searches, access bioactivity data using PUG-REST API and PubChemPy.

SimPO is a reference-free preference optimization method that outperforms DPO without needing a reference model.

Adversary simulation principles based on MITRE ATT&CK framework.

Query resource usage metrics for Railway services.

4-bit quantization that preserves salient weights based on activation patterns, achieving 3x speedup with minimal accuracy loss.

Expert-level Information Security Management System (ISMS) auditing with comprehensive knowledge of ISO 27001, security audit methodologies, security control assessment, and cybersecurity compliance verification.

Comprehensive guide to running ML workloads on Lambda Labs GPU cloud with on-demand instances and 1-Click Clusters.

Open-source AI observability and evaluation platform for LLM applications with tracing, evaluation, datasets, experiments, and real-time monitoring.

Expert-level guidance for implementing Group Relative Policy Optimization (GRPO) using the Transformer Reinforcement Learning (TRL) library. This skill provides battle-tested patterns, critical insights, and production-ready workflows for fine-tuning language models with custom reward functions.

scikit-survival is a Python library for survival analysis built on top of scikit-learn. It provides specialized tools for time-to-event analysis, handling the unique challenge of censored data where some observations are only partially known.

This skill takes your images and screenshots and makes them look better—sharper, clearer, and more professional.

Production-ready patterns for building LLM applications, inspired by Dify and industry best practices.

pyvene is Stanford NLP's library for performing causal interventions on PyTorch models. It provides a declarative, dict-based framework for activation patching, causal tracing, and interchange intervention training - making intervention experiments reproducible and shareable.

You are an email systems engineer who has maintained 99.9% deliverability across millions of emails. You've debugged SPF/DKIM/DMARC, dealt with blacklists, and optimized for inbox placement. You know that email is the highest ROI channel when done right, and a spam folder nightmare when done wrong. You treat deliverability as infrastructure, not an afterthought.

This skill provides personalized feedback on your recent coding work by analyzing your Claude Code chat interactions and identifying patterns that reveal strengths and areas for growth.

Convert web pages to clean Markdown by driving a locally installed browser (via web2md).

A CLI tool for AI agents to debug and triage using Datadog logs and metrics.

You are an expert Move language code reviewer with deep knowledge of the Move Book Code Quality Checklist. Your role is to analyze Move packages and provide specific, actionable feedback based on modern Move 2024 Edition best practices.

SHAP is a unified approach to explain machine learning model outputs using Shapley values from cooperative game theory. This skill provides comprehensive guidance for:

Role: Browser Extension Architect

Source: obra/superpowers

Measure, analyze, optimize - in that order.

33+ essential JavaScript concepts every developer should know, inspired by 33-js-concepts.

NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs. Use this skill when working with network or graph data structures, including social networks, biological networks, transportation systems, citation networks, knowledge graphs, or any system involving relationships between entities.

Use Outlines when you need to:

Statistical modeling, experimentation, causal inference, and production ML systems for data-driven decision-making. \n \n Covers experiment design, A/B testing, feature engineering, model evaluation, and causal analysis with Python, R, SQL, and Scala \n Includes production patterns for scalable data processing, ML model deployment, and real-time inference with monitoring and drift detection \n Supports MLOps best practices: automated retraining, feature stores, model serving, canary deployments,

Provide a comprehensive, structured reference for the 100 most critical web application vulnerabilities organized by category. This skill enables systematic vulnerability identification, impact assessment, and remediation guidance across the full spectrum of web security threats. Content organized into 15 major vulnerability categories aligned with industry standards and real-world attack patterns.

To access Anthropic's official brand identity and style resources, use this skill.

$22

$23

Identify and exploit HTML injection vulnerabilities that allow attackers to inject malicious HTML content into web applications. This vulnerability enables attackers to modify page appearance, create phishing pages, and steal user credentials through injected forms.

Expert guidance for designing, testing, and optimizing prompts that reliably guide LLM behavior. \n \n Covers six core capabilities: prompt design and optimization, system prompt architecture, context window management, output format specification, few-shot example design, and prompt testing and evaluation \n Provides structured patterns for system prompts, few-shot examples, and chain-of-thought reasoning with explicit anti-patterns and sharp edges to avoid \n Emphasizes systematic evaluation a

Comprehensive assistance with llama-factory development, generated from official documentation.

This skill provides efficient Python-based tools for searching and retrieving preprints from the bioRxiv database. It enables comprehensive searches by keywords, authors, date ranges, and categories, returning structured JSON metadata that includes titles, abstracts, DOIs, and citation information. The skill also supports PDF downloads for full-text analysis.

LaminDB is an open-source data framework for biology designed to make data queryable, traceable, reproducible, and FAIR (Findable, Accessible, Interoperable, Reusable). It provides a unified platform that combines lakehouse architecture, lineage tracking, feature stores, biological ontologies, LIMS (Laboratory Information Management System), and ELN (Electronic Lab Notebook) capabilities through a single Python API.

You are a voice AI architect who has shipped production voice agents handling millions of calls. You understand the physics of latency - every component adds milliseconds, and the sum determines whether conversations feel natural or awkward.

PyDESeq2 is a Python implementation of DESeq2 for differential expression analysis with bulk RNA-seq data. Design and execute complete workflows from data loading through result interpretation, including single-factor and multi-factor designs, Wald tests with multiple testing correction, optional apeGLM shrinkage, and integration with pandas and AnnData.

Create pull requests following Sentry's engineering practices.

The Bolt framework is Slack's recommended approach for building apps. It handles authentication, event routing, request verification, and HTTP request processing so you can focus on app logic.

Role: Voice AI Architect

Autonomously analyze the entire codebase to understand its architecture, patterns, and purpose, then systematically transform it into production-grade, corporate-level professional code. This skill performs deep line-by-line scanning, identifies all issues across security, performance, architecture, and quality, then provides comprehensive fixes to meet enterprise standards.

DrugBank is a comprehensive bioinformatics and cheminformatics database containing detailed information on drugs and drug targets. This skill enables programmatic access to DrugBank data including ~9,591 drug entries (2,037 FDA-approved small molecules, 241 biotech drugs, 96 nutraceuticals, and 6,000+ experimental compounds) with 200+ data fields per entry.

template-skill

Pydicom is a pure Python package for working with DICOM files, the standard format for medical imaging data. This skill provides guidance on reading, writing, and manipulating DICOM files, including working with pixel data, metadata, and various compression formats.

The vector database for production AI applications.