affaan-m/everything-claude-code▌

AI-assisted editing for real footage. Not generation from prompts. Editing existing video fast.

Analyze a draft prompt, critique it, match it to ECC ecosystem components, and output a complete optimized prompt the user can paste and run.

Coding standards for readable, maintainable Java 17+ in Spring Boot services. \n \n Covers naming conventions (PascalCase for classes, camelCase for methods, UPPER_SNAKE_CASE for constants), immutability patterns with records and final fields, and Optional usage with map/flatMap \n Establishes best practices for streams, exception handling with domain-specific exceptions, and type-safe generics \n Includes project structure guidance (Maven/Gradle layout), formatting rules, and code smells to avo

$22

Research-backed market intelligence with source attribution and decision-oriented analysis. \n \n Covers investor diligence, competitive analysis, market sizing, and technology vendor research with structured output including findings, implications, risks, and recommendations \n Enforces sourcing standards: every claim requires attribution, stale data is flagged, and contrarian evidence is included alongside supporting data \n Separates fact, inference, and recommendation clearly to support deci

Comprehensive, library-agnostic checklist for reviewing Flutter/Dart applications. These principles apply regardless of which state management solution, routing library, or DI framework is used.

Create zero-dependency, animation-rich HTML presentations with visual style discovery. \n \n Supports three workflows: building new decks from scratch, converting PowerPoint files to HTML, and enhancing existing presentations with improved layout and motion \n Enforces viewport-fit constraint: every slide must fit in one viewport with no internal scrolling, using clamp() for responsive scaling and Intersection Observer for reveal animations \n Defaults to visual exploration over abstract questio

Produce thorough, cited research reports from multiple web sources using firecrawl and exa MCP tools.

Use when building or debugging Nuxt 4 apps with SSR, hybrid rendering, route rules, or page-level data fetching.

Production-grade Django architecture patterns for scalable, maintainable applications. \n \n Covers project structure with split settings (base, development, production, test), custom managers and QuerySets, and service layer separation for business logic \n Includes Django REST Framework patterns: serializers with validation, ViewSets with custom actions, filtering, searching, and pagination \n Demonstrates ORM best practices: select_related and prefetch_related for N+1 prevention, bulk operati

$23

Strategic context compaction at logical task boundaries instead of arbitrary auto-triggers. \n \n Suggests /compact at configurable thresholds (default: 50 tool calls) via PreToolUse hooks on Edit and Write operations \n Provides a decision guide for when to compact across common phase transitions (research to planning, debugging to next feature, etc.) \n Clarifies what persists through compaction (CLAUDE.md, TodoWrite, memory files, git state) versus what's lost (intermediate reasoning, file co

Craft distinctive long-form content that matches a specific voice or brand style, not generic AI output. \n \n Captures and applies existing voice patterns from articles, newsletters, or style guides to maintain consistency across blog posts, guides, tutorials, and launch announcements \n Enforces concrete-first writing: leads with examples, screenshots, code, or data before explanation, avoiding generic openings and filler transitions \n Bans hype language and unsourced claims; requires factual

Idiomatic PyTorch patterns and best practices for building robust, efficient, and reproducible deep learning applications.

Comprehensive Ktor patterns for building robust, maintainable HTTP servers with Kotlin coroutines.

JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, and performance tuning in Spring Boot. \n \n Covers entity mapping with auditing, soft deletes, indexing, and enumerated types; includes transaction management with read-only optimization and propagation strategies \n Provides N+1 prevention techniques using lazy loading, JOIN FETCH queries, and DTO projections for lightweight reads \n Demonstrates pagination with Pageable, custom repository methods, and c

Draft personalized, low-friction investor communications for cold outreach, warm intros, follow-ups, and updates. \n \n Structures cold emails with specific personalization hooks (portfolio companies, public thesis, mutual connections) and a single concrete ask \n Provides templates for warm intro requests with forwardable blurbs under 100 words, follow-up cadence (day 4–5 and day 10–12), and post-meeting updates \n Enforces core rules: proof over adjectives, no generic copy, explicit asks, and

Modern C++ standards enforcing type safety, resource management, and clarity through the C++ Core Guidelines. \n \n Covers six foundational principles: RAII for resource lifetime, immutability by default, compile-time type safety, intent-driven naming, minimal complexity, and value semantics over pointers \n Provides detailed rules across 15+ domains including functions, classes, resource management, error handling, concurrency, templates, and standard library usage with code examples for each \

Playwright E2E testing patterns with Page Object Model, configuration, CI/CD setup, and flaky test strategies. \n \n Provides Page Object Model structure for maintainable test organization, with reusable page classes that encapsulate locators and navigation logic \n Covers multi-browser testing across Chromium, Firefox, WebKit, and mobile devices with configurable retries, parallelization, and artifact capture (screenshots, videos, traces) \n Includes flaky test identification and remediation pa

Neural search for web content, code, companies, and people via the Exa MCP server.

Systematically analyze an unfamiliar codebase and produce a structured onboarding guide. Designed for developers joining a new project or setting up Claude Code in an existing repo for the first time.

Distribute content across platforms without turning it into the same fake post in four costumes.

Modern C++ testing workflow using GoogleTest/GoogleMock with CMake/CTest integration. \n \n Covers unit and integration test design with TDD red-green-refactor loop, fixtures, mocks, and fakes for dependency isolation \n Includes CMake/CTest configuration with automatic test discovery via gtest_discover_tests() and filtering strategies \n Provides coverage setup for GCC (gcov/lcov) and Clang (llvm-cov), plus sanitizer configuration (ASan, UBSan, TSan) for memory and race detection \n Documents f

$22

Idiomatic Go patterns, best practices, and conventions for building robust applications. \n \n Covers core principles including simplicity over cleverness, useful zero values, and accepting interfaces while returning concrete types \n Includes error handling patterns with wrapping, custom error types, and proper error checking using errors.Is and errors.As \n Provides concurrency patterns for worker pools, context-based cancellation, graceful shutdown, and goroutine leak prevention \n Addresses

Comprehensive Spring Security guidance for authentication, authorization, input validation, secrets, and dependency scanning in Java Spring Boot. \n \n Covers authentication patterns (JWT, OAuth2, sessions with secure cookies), authorization via method security annotations, and token validation with filters \n Includes input validation with Bean Validation constraints, SQL injection prevention through parameterized queries, and password hashing with BCrypt or Argon2 \n Provides CSRF, CORS, and s

You are a senior trade compliance specialist with 15+ years managing customs operations across US, EU, UK, and Asia-Pacific jurisdictions. You sit at the intersection of importers, exporters, customs brokers, freight forwarders, government agencies, and legal counsel. Your systems include ACE (Automated Commercial Environment), CHIEF/CDS (UK), ATLAS (DE), customs broker portals, denied party screening platforms, and ERP trade management modules. Your job is to ensure lawful, cost-optimized movem

Patterns for structured concurrency, Flow-based reactive streams, and coroutine testing in Android and Kotlin Multiplatform projects.

Next.js 16+ uses Turbopack by default for local development: an incremental bundler written in Rust that significantly speeds up dev startup and hot updates.

Multi-agent DAG execution framework for decomposing large features into independently verifiable work units with quality gates. \n \n Structures complex features as directed acyclic graphs with explicit dependencies, complexity tiers (isolated edits to schema/security changes), and per-unit acceptance criteria \n Enforces a seven-stage pipeline: RFC intake, DAG decomposition, unit assignment, implementation, validation, merge queue processing, and final system verification \n Implements merge qu

You are a senior freight exceptions analyst with 15+ years managing shipment exceptions across all modes — LTL, FTL, parcel, intermodal, ocean, and air. You sit at the intersection of shippers, carriers, consignees, insurance providers, and internal stakeholders. Your systems include TMS (transportation management), WMS (warehouse management), carrier portals, claims management platforms, and ERP order management. Your job is to resolve exceptions quickly while protecting financial interests, pr

Turn a one-line objective into a step-by-step construction plan that any coding agent can execute cold.

Decision framework for autonomous agent loops with quality gates, evals, and recovery patterns. \n \n Four loop modes available: continuous-pr for CI/PR workflows, rfc-dag for RFC decomposition, infinite for exploratory parallel generation, and sequential as default \n Recommended production stack combines RFC decomposition, code quality gates, eval harness, and session persistence for robust autonomous execution \n Built-in failure mode detection covers loop churn, repeated retries, merge queue

Architectural patterns, API design, and database optimization for Node.js, Express, and Next.js backends. \n \n Covers repository, service, and middleware layers for clean separation of concerns; includes REST API structure with resource-based URLs and query parameters \n Database patterns include N+1 prevention, query optimization, transactions, and caching strategies (Redis, cache-aside) \n Error handling with centralized handlers, retry logic with exponential backoff, and structured logging f

Engineering operating model for teams shipping code with AI-assisted generation. \n \n Emphasizes planning quality, evaluation coverage, and behavior-focused code review over traditional syntax checking and typing speed \n Requires agent-friendly architectures with explicit boundaries, stable contracts, typed interfaces, and deterministic tests to minimize implicit behavior \n Shifts review priorities to behavior regressions, security assumptions, data integrity, failure handling, and rollout sa

$23

Transform one idea into platform-native content across X, LinkedIn, TikTok, YouTube, and newsletters without cross-posting. \n \n Adapts source assets (articles, videos, demos, docs) into distinct platform variants with native hooks, pacing, and CTAs \n Covers five platforms with specific guidance: X (fast opens, one idea per post), LinkedIn (strong first lines, explicit lessons), short video (attention-grabbing first 3 seconds), YouTube (early results, visual refresh every 20-30 seconds), and n

ClickHouse table design, query optimization, and analytics patterns for high-performance OLAP workloads. \n \n Covers three primary MergeTree engine variants: standard MergeTree for time-series data, ReplacingMergeTree for deduplication, and AggregatingMergeTree for pre-aggregated metrics \n Includes query optimization patterns for efficient filtering, aggregations, window functions, and percentile calculations with ClickHouse-specific functions \n Demonstrates data insertion strategies (bulk in

Cache expensive file processing results using SHA-256 content hashes instead of file paths. \n \n Content-hash keys survive file moves and auto-invalidate when content changes, eliminating path-based cache brittleness \n Store cache entries as individual {hash}.json files for O(1) lookup without requiring a separate index \n Implement caching as a service layer wrapper around pure processing functions, keeping extraction logic separate from cache concerns \n Handle cache corruption gracefully by

Multi-agent adversarial verification framework. Make a list, check it twice. If it's naughty, fix it until it's nice.

Measures whether coding agents actually follow skills, rules, or agent definitions by:

Scan installed skills, extract cross-cutting principles that appear in multiple skills, and distill them into rules — appending to existing rule files, revising outdated content, or creating new rule files.

Find bugs that static code reading misses: state interaction side effects, race conditions between sequential calls, and handlers that silently undo each other.

Analyze token overhead across every loaded component in a Claude Code session and surface actionable optimizations to reclaim context space.

A lightweight CLI tool for comparing coding agents head-to-head on reproducible tasks. Every "which coding agent is best?" comparison runs on vibes — this tool systematizes it.

Generated from affaan-m/everything-claude-code on 2026-03-20

Capture architectural decisions as they happen during coding sessions. Instead of decisions living only in Slack threads, PR comments, or someone's memory, this skill produces structured ADR documents that live alongside the code.

Build a production-ready, AI-powered data collection agent for any public data source. Runs on a schedule, enriches results with a free LLM, stores to a database, and improves over time.

Comprehensive security guidance for Laravel applications to protect against common vulnerabilities.

Production-grade Laravel architecture patterns for scalable, maintainable applications.

Test-driven development for Laravel applications using PHPUnit and Pest with 80%+ coverage (unit + feature).

Interactive menu for browsing and composing agent teams on demand. Works with flat or domain-subdirectory agent collections.

claude-devfleet

When the user asks about libraries, frameworks, or APIs, fetch current documentation via the Context7 MCP (tools resolve-library-id and query-docs) instead of relying on training data.

Idiomatic Rust patterns and best practices for building safe, performant, and maintainable applications.

fal-ai-media

Testing patterns specifically designed for AI-assisted development, where the same model writes code and reviews it — creating systematic blind spots that only automated tests can catch.

Comprehensive patterns for database access with JetBrains Exposed ORM, including DSL queries, DAO, transactions, and production-ready configuration.

Comprehensive Kotlin testing patterns for writing reliable, maintainable tests following TDD methodology with Kotest and MockK.

Comprehensive testing strategies for Perl applications using Test2::V0, Test::More, prove, and TDD methodology.

Programmatic interaction with X (Twitter) for posting, reading, searching, and analytics.

Comprehensive security guidelines for Perl applications covering input validation, injection prevention, and secure coding practices.

You are a senior returns operations manager with 15+ years handling the full returns lifecycle across retail, e-commerce, and omnichannel environments. Your responsibilities span return merchandise authorization (RMA), receiving and inspection, condition grading, disposition routing, refund and credit processing, fraud detection, vendor recovery (RTV), and warranty claims management. Your systems include OMS (order management), WMS (warehouse management), RMS (returns management), CRM, fraud det

Build applications with the Anthropic Claude API and SDKs.

Perception + memory + actions for video, live streams, and desktop sessions.

Idiomatic Perl 5.36+ patterns and best practices for building robust, maintainable applications.

You are a senior energy procurement manager at a large commercial and industrial (C&I) consumer with multiple facilities across regulated and deregulated electricity markets. You manage an annual energy spend of $15M–$80M across 10–50+ sites — manufacturing plants, distribution centers, corporate offices, and cold storage. You own the full procurement lifecycle: tariff analysis, supplier RFPs, contract negotiation, demand charge management, renewable energy sourcing, budget forecasting, and

You are a senior transportation manager with 15+ years managing carrier portfolios ranging from 40 to 200+ active carriers across truckload, LTL, intermodal, and brokerage. You own the full lifecycle: sourcing new carriers, negotiating rates, running RFPs, building routing guides, tracking performance via scorecards, managing contract renewals, and making allocation decisions. Your systems include TMS (transportation management), rate management platforms, carrier onboarding portals, DAT/Greensc

You are a senior demand planner at a multi-location retailer operating 40–200 stores with regional distribution centers. You manage 300–800 active SKUs across categories including grocery, general merchandise, seasonal, and promotional assortments. Your systems include a demand planning suite (Blue Yonder, Oracle Demantra, or Kinaxis), an ERP (SAP, Oracle), a WMS for DC-level inventory, POS data feeds at the store level, and vendor portals for purchase order management. You sit between merchandi

You are a senior production scheduler at a discrete and batch manufacturing facility operating 3–8 production lines with 50–300 direct-labor headcount per shift. You manage job sequencing, line balancing, changeover optimization, and disruption response across work centers that include machining, assembly, finishing, and packaging. Your systems include an ERP (SAP PP, Oracle Manufacturing, or Epicor), a finite-capacity scheduling tool (Preactor, PlanetTogether, or Opcenter APS), an MES for shop

You are a senior quality engineer with 15+ years in regulated manufacturing environments — FDA 21 CFR 820 (medical devices), IATF 16949 (automotive), AS9100 (aerospace), and ISO 13485 (medical devices). You manage the full non-conformance lifecycle from incoming inspection through final disposition. Your systems include QMS (eQMS platforms like MasterControl, ETQ, Veeva), SPC software (Minitab, InfinityQS), ERP (SAP QM, Oracle Quality), CMM and metrology equipment, and supplier portals. You sit

Patterns for building shared UI across Android, iOS, Desktop, and Web using Compose Multiplatform and Jetpack Compose. Covers state management, navigation, theming, and performance.

Session-aware REPL for NanoClaw v2 with persistent markdown storage and dynamic skill loading. \n \n Eight core commands: model switching, skill loading, session branching, cross-session search, history compaction, and export to multiple formats (md/json/txt) \n Markdown-backed sessions enable persistent state, version control compatibility, and human-readable session history \n Designed for zero external runtime dependencies and deterministic, local command handling to maintain simplicity and p

Clean Architecture patterns for Android and KMP projects. Covers module boundaries, dependency inversion, UseCase/Repository patterns, and data layer design with Room, SQLDelight, and Ktor.

Operational controls for long-lived agent workloads with observability, security, and lifecycle management. \n \n Covers four operational domains: runtime lifecycle (start, pause, stop, restart), observability (logs, metrics, traces), safety controls (scopes, permissions, kill switches), and change management (rollout, rollback, audit) \n Enforces baseline controls including immutable deployment artifacts, least-privilege credentials, environment-level secret injection, and hard timeouts with re

Write-time code quality enforcement with auto-formatting, linting, and Claude-powered subprocess fixes on every file edit. \n \n Three-phase architecture: silent auto-formatting, violation collection, and tiered model routing (Haiku for style, Sonnet for complexity, Opus for types) to fix unfixable issues \n Supports Python, TypeScript, Shell, YAML, JSON, TOML, Markdown, and Dockerfile with 20+ linters including ruff, biome, shellcheck, and hadolint \n Config protection via PreToolUse and Stop h

AI-driven engineering workflows with eval-first execution, task decomposition, and cost-aware model routing. \n \n Defines an eval-first loop: establish baseline evals before implementation, then re-run post-execution to measure deltas and catch regressions \n Decomposes work into 15-minute units with single dominant risks, independent verifiability, and clear done conditions \n Routes tasks by complexity: Haiku for classification and boilerplate, Sonnet for implementation, Opus for architecture

On-device LLM integration for iOS 18+ using Apple's FoundationModels framework with privacy-first text generation and structured output. \n \n Covers text generation, structured output via @Generable macro, custom tool calling, and snapshot streaming—all running locally without cloud dependency \n Requires availability checks before session creation; supports single-turn and multi-turn conversations with optional system instructions \n Guided generation with @Guide constraints (numeric ranges, a

Single-threaded by default with explicit background offloading via @concurrent and isolated protocol conformances. \n \n Async functions stay on the calling actor by default, eliminating implicit background offloading that caused data-race errors in Swift 6.1 and earlier \n Isolated conformances allow MainActor types to safely conform to non-isolated protocols without unsafe workarounds \n @concurrent attribute explicitly offloads CPU-intensive work to background threads; requires nonisolated ty

Create consistent, credible investor materials aligned to a single source of truth. \n \n Covers pitch decks, one-pagers, investor memos, financial models, accelerator applications, and use-of-funds tables \n Enforces cross-document consistency by establishing canonical facts (traction, pricing, raise size, team, milestones) before drafting \n Includes structured guidance for each asset type, from pitch deck slide order to financial model assumptions and sensitivity analysis \n Flags common red

$22

Thread-safe data persistence in Swift using actors with in-memory cache and file-backed storage. \n \n Implements an actor-based repository pattern that eliminates data races at compile time, replacing manual synchronization with Swift's actor model \n Combines fast O(1) in-memory lookups with atomic file persistence, supporting any Codable & Identifiable model type \n Provides synchronous initialization to avoid async complexity, with automatic await enforcement on all public API calls \n

Protocol-based dependency injection for testable Swift code with focused abstractions and Swift Testing. \n \n Define small, single-responsibility protocols for each external concern (file system, network, APIs) and provide default production implementations \n Create mock implementations with configurable error properties to test failure paths deterministically without real I/O \n Inject dependencies via default parameters so production code uses real implementations automatically while tests o

Automated verification pipeline for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review. \n \n Runs six sequential phases: Maven/Gradle build, static analysis (SpotBugs, PMD, Checkstyle), unit and integration tests with JaCoCo coverage reporting, dependency CVE scanning, optional code formatting, and git diff review \n Supports both Maven and Gradle with parallel build acceleration ( -T 4 flag) and includes example test patterns for unit tests, Test

Hybrid regex-and-LLM framework for parsing structured text, optimizing cost by handling 95–98% with regex and reserving LLM calls for edge cases. \n \n Combines regex extraction with confidence scoring to flag low-confidence items, then validates only those items with an LLM, reducing LLM calls by ~95% versus all-LLM approaches \n Includes production-ready Python patterns for regex parsing, confidence scoring, and hybrid pipeline orchestration with real metrics from a 410-item quiz parsing examp

Project-specific architecture, code patterns, and deployment guidelines for Zenith application. \n \n Next.js 15 frontend with FastAPI backend, Supabase PostgreSQL database, and Claude API integration via structured output \n Includes standardized API response formats, custom React hooks, and Pydantic models for type safety across stack \n Testing requirements: pytest with 80% coverage minimum for backend, React Testing Library for frontend, Playwright for E2E \n Deployment via Google Cloud Run

Test-driven development workflow enforcing 80%+ coverage across unit, integration, and E2E tests. \n \n Write tests first, then implement code to make them pass; covers unit tests (functions, components), integration tests (APIs, databases), and E2E tests (Playwright for critical user flows) \n Includes comprehensive testing patterns with Jest/Vitest for components, API route testing, and Playwright for browser automation workflows \n Provides mocking strategies for external services (Supabase,

Comprehensive verification system running build, type, lint, test, and security checks across Claude Code sessions. \n \n Executes six sequential verification phases: build compilation, type checking, linting, test suite with coverage reporting, security scanning for secrets and debug statements, and git diff review \n Supports both JavaScript/TypeScript (npm/pnpm, tsc, ESLint) and Python (pyright, ruff) projects with language-specific commands \n Produces a structured verification report indica

Document conversion, extraction, OCR, redaction, signing, and form-filling via the Nutrient DWS API. \n \n Converts between 15+ formats including PDF, DOCX, XLSX, PPTX, HTML, and images (JPG, PNG, TIFF, WebP, SVG, and more) \n Extracts plain text and tables from documents; OCR supports 100+ languages for scanned PDFs and images \n Redacts PII using preset patterns (SSN, email, credit card, phone, date, URL, IP, MAC address, ZIP code, VIN) or custom regex \n Adds watermarks, applies digital CMS s

PostgreSQL best practices for indexing, schema design, query optimization, and security. \n \n Covers six index types with specific use cases: B-tree for equality/range queries, composite for multi-column filters, GIN for JSONB and full-text search, and BRIN for time-series data \n Includes data type guidance (bigint for IDs, text over varchar, timestamptz for timestamps, numeric for money) and anti-pattern detection queries for unindexed foreign keys and slow queries \n Provides ready-to-use SQ

React and Next.js patterns for component composition, state management, performance optimization, and accessible UI. \n \n Covers component patterns including composition, compound components, and render props for flexible, reusable UI architecture \n Provides custom hooks for state management, async data fetching, debouncing, and form handling with validation \n Includes performance techniques: memoization, code splitting with lazy loading, and virtualization for large lists \n Demonstrates err

CI/CD pipelines, Docker containerization, deployment strategies, health checks, and production readiness for web applications. \n \n Covers three deployment patterns: rolling (zero-downtime gradual updates), blue-green (atomic traffic switching), and canary (percentage-based rollout with monitoring) \n Includes multi-stage Dockerfile examples for Node.js, Go, and Python with best practices for image size, non-root users, and health checks \n Provides GitHub Actions pipeline templates, environmen

Comprehensive TDD guide for Django with pytest, factory_boy, and DRF API testing. \n \n Covers the red-green-refactor cycle with pytest configuration, test settings, and conftest fixtures for models, views, and API endpoints \n Factory Boy patterns for creating test data, including sequences, relationships, and post-generation hooks \n Model, view, serializer, and API ViewSet testing strategies with real code examples for CRUD operations and filtering \n Mocking and patching techniques for exter

Universal coding standards and best practices for TypeScript, JavaScript, React, and Node.js projects. \n \n Covers core principles (readability, KISS, DRY, YAGNI) with practical code examples for variable naming, function design, immutability, error handling, and type safety \n Includes React-specific guidance on component structure, custom hooks, state management, and conditional rendering patterns \n Provides API design standards with REST conventions, response formats, and input validation u

Audit Claude Code configurations for security vulnerabilities, misconfigurations, and injection risks. \n \n Scans five configuration areas: CLAUDE.md , settings.json , MCP servers, hooks, and agent definitions for hardcoded secrets, prompt injection patterns, overly permissive permissions, and command injection risks \n Provides four output formats (terminal, JSON, Markdown, HTML) and integrates with CI/CD via GitHub Action with configurable severity filtering \n Includes auto-fix mode for safe

Safe, reversible database schema changes for production systems. \n \n Covers PostgreSQL, MySQL, and five major ORMs (Prisma, Drizzle, Django, TypeORM, golang-migrate) with workflow examples and schema patterns for each \n Enforces core principles: immutable deployed migrations, forward-only production rollbacks, and separation of schema (DDL) from data (DML) migrations \n Provides the expand-contract pattern for zero-downtime column renames and large refactors, with concrete timeline examples \

Progressive context refinement loop for multi-agent workflows solving the subagent context problem. \n \n Four-phase cycle (dispatch, evaluate, refine, loop) that iteratively narrows retrieval to high-relevance files, capping at 3 iterations to balance token usage and context quality \n Scores retrieved files on a 0–1 relevance scale and explicitly identifies missing context gaps to drive the next refinement cycle \n Learns codebase terminology and patterns during the first cycle, improving subs

Django security best practices covering authentication, authorization, CSRF, SQL injection, and XSS prevention. \n \n Provides production-ready settings configurations including HTTPS enforcement, secure cookies, HSTS headers, and password validation with minimum 12-character requirements \n Covers authentication patterns: custom user models, Argon2 password hashing, session management, and role-based access control (RBAC) \n Includes authorization strategies: Django permissions, custom permissi

Test-driven development framework for Spring Boot with JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo enforcement. \n \n Covers unit tests (Mockito), web layer tests (MockMvc), integration tests (SpringBootTest), and persistence tests (DataJpaTest) with concrete examples \n Integrates Testcontainers for production-mirroring Postgres/Redis databases and JaCoCo for enforcing 80%+ code coverage \n Emphasizes Arrange-Act-Assert patterns, AssertJ assertions, and test data builders for maintain

Docker and Docker Compose patterns for local development, multi-service orchestration, and container security. \n \n Covers multi-stage Dockerfiles with dev, build, and production targets; Docker Compose configuration for web app stacks with PostgreSQL, Redis, and Mailpit; and override files for environment-specific settings \n Includes service discovery via container networking, custom network isolation, and volume strategies (named volumes, bind mounts, anonymous volumes) for data persistence

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills. \n \n Runs as a Stop hook at session end to evaluate transcripts, detect patterns, and save skills to ~/.claude/skills/learned/ \n Configurable pattern detection across five categories: error resolution, user corrections, workarounds, debugging techniques, and project-specific conventions \n Customizable via config.json with minimum session length, extraction thresholds, and pattern ignore lists \n

The Model Context Protocol (MCP) lets AI assistants call tools, read resources, and use prompts from your server. Use this skill when building or maintaining MCP servers. The SDK API evolves; check Context7 (query-docs for "MCP") or the official MCP documentation for current method names and signatures.

Bun is a fast all-in-one JavaScript runtime and toolkit: runtime, package manager, bundler, and test runner.

Systematize research-before-coding by searching existing tools, libraries, and patterns before writing custom code. \n \n Provides a five-phase workflow: need analysis, parallel search across npm/PyPI/MCP/GitHub, evaluation, decision (adopt/extend/compose/build), and implementation \n Includes a decision matrix to score candidates on functionality, maintenance, community, docs, license, and dependencies \n Offers search shortcuts organized by category (development tooling, AI/LLM integration, da

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust Python applications. \n \n Covers core principles including readability, explicit code, EAFP exception handling, and modern type hints with generics and protocols \n Includes practical patterns for error handling, context managers, comprehensions, generators, dataclasses, and decorators with runnable examples \n Addresses concurrency patterns for I/O-bound (threading, async/await) and CPU-bound (multiprocessing)

Comprehensive Rust testing patterns for writing reliable, maintainable tests following TDD methodology.

$22

Comprehensive pytest testing strategies with TDD, fixtures, mocking, and coverage best practices. \n \n Covers TDD methodology (red-green-refactor cycle), parametrization, fixtures with multiple scopes, and mocking patterns for unit and integration testing \n Includes pytest fundamentals: assertions, markers for test selection, exception testing, and async test support with pytest-asyncio \n Provides practical patterns for testing APIs, databases, file operations, and class methods with real cod

Idiomatic Kotlin patterns and best practices for building robust, efficient, and maintainable applications.

Spring Boot patterns for REST APIs, layered services, data access, caching, and async processing. \n \n Covers controller, service, and repository layers with Spring MVC/WebFlux, Spring Data JPA queries, and transactional boundaries \n Includes DTOs with validation, centralized exception handling via @ControllerAdvice , and RFC 7807 error responses \n Provides caching strategies with @Cacheable and @CacheEvict , async processing with @Async , and structured logging via SLF4J \n Demonstrates requ

Orchestrate parallel AI agent sessions using dmux, a tmux pane manager for agent harnesses.

Comprehensive pre-deployment verification pipeline for Django projects covering migrations, linting, tests, security, and configuration. \n \n Runs 12 sequential phases: environment validation, code quality checks (mypy, ruff, black, isort), migration safety, test coverage analysis, security scanning (pip-audit, bandit, gitleaks), and Django-specific configuration verification \n Includes coverage targets by component (models 90%+, views 80%+, overall 80%+) and pre-deployment checklist covering

Table-driven tests, subtests, benchmarks, fuzzing, and golden files for Go TDD workflows. \n \n Covers the RED-GREEN-REFACTOR cycle with step-by-step examples for writing tests before implementation \n Includes table-driven test patterns for comprehensive coverage, error cases, and parallel execution with t.Run() \n Provides benchmarking techniques for performance analysis, memory allocation tracking, and comparative benchmarks across input sizes \n Supports fuzzing with seed corpus and property

Formal evaluation framework for Claude Code sessions implementing eval-driven development principles. \n \n Defines capability and regression evals with pass/fail criteria before implementation, treating evals as unit tests for AI-assisted workflows \n Supports three grader types: code-based (deterministic checks via bash/grep), model-based (Claude-as-judge), and human review for manual adjudication \n Tracks reliability with pass@k metrics (success within k attempts) and pass^k (all k trials su

Translate visa application documents to English and generate bilingual PDFs automatically. \n \n Handles multiple document types: bank certificates, employment letters, retirement certificates, property documents, IDs, and passports \n Automatically converts HEIC to PNG, detects and corrects image orientation via EXIF data, and extracts text using macOS Vision, EasyOCR, or Tesseract OCR \n Translates extracted text professionally while preserving structure, proper names, dates, and amounts; uses

Intelligent model routing, budget tracking, and retry logic to optimize LLM API costs without sacrificing quality. \n \n Routes requests to cheaper models (Haiku) for simple tasks and expensive models (Sonnet, Opus) only when complexity thresholds are met, reducing spend by 3–19x on routine work \n Tracks cumulative API costs with immutable dataclasses, enforces budget limits, and fails early to prevent overspend \n Implements narrow retry logic that retries only on transient errors (network, ra

Comprehensive security checklist and patterns for authentication, input validation, secrets management, and sensitive operations. \n \n Covers 10 core security domains: secrets management, input validation, SQL injection prevention, authentication/authorization, XSS prevention, CSRF protection, rate limiting, sensitive data exposure, blockchain wallet verification, and dependency security \n Includes code examples for each vulnerability type with clear \"never do this\" and \"always do this\" pa

$22