supercent-io/skills-template▌

Implement WCAG 2.1 accessibility standards for semantic HTML, keyboard navigation, ARIA attributes, and screen reader support. \n \n Covers semantic HTML structure, keyboard navigation (Tab, arrow keys, ESC), and focus management for modals and interactive components \n Provides ARIA attribute guidance (aria-label, aria-live, aria-hidden, role attributes) with practical React/TypeScript examples \n Includes color contrast requirements (WCAG AA/AAA), visual focus indicators, and testing strategie

Professional PPTX presentations with brand-aligned layouts and structured validation. \n \n Generates pitch, roadmap, and product decks from structured briefs with predefined slide templates (title, agenda, problem, solution, features, stats, team, CTA) \n Enforces brand consistency through color palettes, typography hierarchies, logo placement, and design tone (minimal, bold, or executive) \n Includes multi-step review workflow: layout balance, typography hierarchy, content clarity, and accessi

Refactor code while preserving behavior, improving clarity, and reducing complexity. \n \n Covers five core refactoring patterns: Extract Method, DRY principle removal, conditional-to-polymorphism conversion, parameter object introduction, and SOLID principle application \n Includes behavior validation workflow with pre-refactoring analysis, post-refactoring testing (unit, type, lint, snapshot), and change documentation \n Provides refactoring checklist covering function length, parameter count,

Programmable video production with Remotion, scene planning, asset orchestration, and automated rendering for brand-consistent content. \n \n Guides video creation through five structured steps: spec definition, scene outlining, asset preparation, React composition implementation, and QA rendering \n Supports multiple aspect ratios (16:9, 1:1, 9:16) and tones (fast, calm, cinematic) with integrated narration, visuals, and animations \n Includes scene templates, asset checklists, and Remotion com

Diagnose and fix performance bottlenecks across React frontends and database backends. \n \n Covers frontend optimization: React.memo, useMemo, useCallback, lazy loading, code splitting, image optimization, and bundle analysis \n Includes backend strategies: N+1 query fixes, database indexing, Redis caching, and API compression \n Provides measurement tools and workflows using Lighthouse, Web Vitals, and webpack-bundle-analyzer \n Emphasizes profiling first, incremental improvements, and continu

Mobile-first CSS layouts using Flexbox, Grid, media queries, and responsive images across all devices. \n \n Covers mobile-first design progression from 320px through large screens (1440px+) with standard breakpoint definitions \n Implements Flexbox for 1-dimensional layouts and CSS Grid for 2-dimensional layouts, with practical examples for navigation, cards, and dashboards \n Includes responsive image techniques: srcset for resolution-aware loading, picture element for art direction, and CSS b

Comprehensive security hardening for web applications covering HTTPS, input validation, authentication, and OWASP Top 10 vulnerabilities. \n \n Enforces HTTPS, security headers (CSP, HSTS), and rate limiting via Helmet and Express middleware to prevent DDoS and common attacks \n Prevents SQL Injection and XSS through parameterized queries, input validation with Joi, and output encoding with DOMPurify \n Implements CSRF token protection, JWT-based authentication with refresh token rotation, and s

Structured code review framework covering quality, security, performance, and testing standards. \n \n Provides eight-step review methodology: context understanding, high-level architecture assessment, detailed code inspection, security audit, performance analysis, testing validation, documentation check, and constructive feedback delivery \n Covers SOLID principles, naming conventions, error handling, input validation, authentication/authorization, SQL injection and XSS prevention, and resource

Multi-agent orchestration layer for Codex CLI with 30 specialized agents and 40+ workflow skills. \n \n Includes 30 role-based agents across development, QA, domain expertise, and product strategy tiers; trigger via /prompts:role or workflow skills like $autopilot , $ralph , $team , and $code-review \n Supports parallel team execution in tmux with staged pipeline execution (plan → PRD → exec → verify → fix) and persistent MCP servers for state, memory, and code intelligence \n Offers workflow sk

Estimate software development tasks using story points, planning poker, and t-shirt sizing. \n \n Provides Fibonacci-based story point scales (1–21+) with time and complexity guidelines for each level \n Includes planning poker process for team consensus estimation with discussion and re-voting workflows \n Offers t-shirt sizing (XS–XL) for quick backlog grooming and rough roadmap planning \n Adjusts estimates for risk and uncertainty using configurable buffers, with examples for medium and high

Five specialized agents for ideation, design thinking, innovation strategy, problem-solving, and storytelling. \n \n Five named agents (Carson, Maya, Victor, Dr. Quinn, Sophia) each with distinct methodologies: brainstorming coach, design thinking facilitator, innovation strategist, creative problem solver, and storyteller \n Brainstorming agent covers 36 techniques across 7 categories; storytelling agent provides 25 proven story frameworks; problem-solving agent uses TRIZ, Theory of Constraints

32 specialized agents with smart model routing, persistent execution loops, and real-time visibility for Claude Code workflows. \n \n Six orchestration modes (Team, Autopilot, Ralph, Ultrawork, Pipeline, Swarm) handle everything from coordinated multi-stage pipelines to autonomous single-agent execution and maximum parallelism \n Team mode runs a canonical five-stage pipeline: plan → PRD → execute → verify → fix, with automatic looping until tasks complete \n Magic keywords (autopilot, ralph, ul

Structured game development workflow routing projects through five phases with six specialized agents. \n \n Covers five workflow phases: Pre-production (brainstorming, brief), Design (GDD, narrative), Technical (architecture, test framework), Production (sprints, stories, code review), and Game Testing (automation, E2E, performance, playtesting) \n Supports Unity, Unreal Engine, Godot, and custom engines with phase-specific commands for each stage \n Includes six specialized agents (designer, a

OMX implements a structured execution pipeline:

Comprehensive testing strategy design covering unit, integration, E2E testing, and TDD practices. \n \n Implements test pyramid structure with recommended ratios: 70% unit tests, 20% integration, 10% E2E tests \n Provides Given-When-Then patterns for unit testing, mocking strategies for external dependencies, and API endpoint testing examples \n Includes E2E testing guidance using Playwright for complete user flow validation and TDD red-green-refactor cycle methodology \n Covers CI/CD integratio

Programmable video production with Remotion, scene planning, asset orchestration, and validation gates for brand-consistent automated content. \n \n Generates videos from text instructions through a structured five-step workflow: spec definition, scene outlining, asset preparation, Remotion composition implementation, and QA rendering \n Supports multiple aspect ratios (16:9, 1:1, 9:16) and video lengths (30s–90s) with configurable tone, narration style, and language \n Includes scene templates,

HTML-first slide deck creation with visual editing, validation, and export to PPTX or PDF. \n \n Plan decks with structured outlines before generating HTML slides; review visually in a browser editor before exporting \n Organize slides in dedicated workspace directories ( decks/<deck-name>/ ) with self-contained HTML files, one primary idea per slide \n Validate slide structure and convert approved decks to .pptx or .pdf using core commands: build-viewer , validate , convert , pdf \n Requir

Visual plan and diff review UI with structured feedback, annotation, and auto-save to Obsidian or Bear Notes. \n \n Integrates with Claude Code, Gemini CLI, Codex CLI, and OpenCode via hooks or plugins; automatically opens when agents exit plan mode \n Supports three annotation types (delete, insert, replace, comment) with line-level precision for both plans and code diffs \n Includes image annotation for UI/UX feedback and split/unified diff views for code review \n Auto-saves approved plans to

Search and navigate large codebases with semantic search, grep patterns, and file discovery. \n \n Supports three search modes: semantic search for conceptual queries, grep for exact text and regex patterns, and glob for file discovery by type or naming convention \n Includes workflow guidance for common scenarios like tracing function calls, understanding feature implementations, locating bugs, and performing impact analysis \n Provides language-specific patterns for Python, JavaScript, TypeScr

Free, no-signup AI image generation via simple URL parameters with customizable models and dimensions. \n \n Supports three AI models (flux, turbo, stable-diffusion) with adjustable width, height, seed, and enhancement parameters \n URL-based API requires no authentication; works with browser, curl, or Python requests for instant generation and file saving \n Includes batch generation, seed-based reproducibility, and metadata tracking for consistent creative workflows \n Best suited for rapid pr

Design and deploy analytics dashboards connecting BigQuery data to Looker Studio visualizations. \n \n Supports native BigQuery connector with custom SQL queries, scheduled queries for performance optimization, and multi-table joins for complex data transformations \n Includes F-pattern dashboard layout guidance with KPI tiles, trend charts, comparison visualizations, and interactive filters for user-driven exploration \n Provides performance optimization strategies using partition keys, data ex

Design and optimize SQL and NoSQL database schemas with normalization, indexing, and migration strategies. \n \n Covers entity definition, relationship design (1:1, 1:N, N:M), and normalization levels (1NF–3NF) for PostgreSQL, MySQL, MongoDB, and SQLite \n Provides indexing strategies, constraint setup, and trigger implementation to ensure data integrity and query performance \n Includes migration script generation with UP/DOWN rollback capabilities for safe schema evolution \n Delivers complete

Production-grade UI design with design tokens, layout rules, motion guidance, and accessibility validation. \n \n Provides structured design token system covering colors, typography, spacing, shadows, and breakpoints for consistent scaling across projects \n Includes layout specification templates for different page types (landing, dashboard, form, blog, e-commerce) with responsive breakpoint rules \n Offers motion guidelines with easing curves, transition durations, and interaction patterns for

Dataset exploration, cleaning, statistical analysis, and visualization in Python or SQL. \n \n Supports CSV, JSON, and SQL data sources with pandas DataFrames and direct database queries \n Covers the full analysis pipeline: data loading, missing value handling, outlier detection, grouping, correlation analysis, and pivot tables \n Includes visualization templates for histograms, boxplots, heatmaps, and time series using matplotlib and seaborn \n Generates structured markdown reports with datase

Instant deployment to Vercel with preview and claimable links, no authentication required. \n \n Supports 20+ frameworks including Next.js, React, Vue, Svelte, Angular, Express, and static HTML projects with automatic framework detection \n Returns two URLs: a live Preview URL for immediate access and a Claim URL to transfer the deployment to your Vercel account \n Packages projects efficiently by excluding node_modules and .git directories to minimize upload size \n Works in Claude environment

Multi-agent orchestrator for coordinating specialized domain agents across PM, Frontend, Backend, Mobile, QA, and Debug roles. \n \n Spawns and coordinates six specialized agents (PM, Frontend, Backend, Mobile, QA, Debug) with role-specific triggers and capabilities \n Uses Serena Memory for structured cross-agent state management and real-time observability via terminal and web dashboards \n Supports multi-CLI vendor integration (Gemini, Claude, Codex) with per-agent CLI mapping in configuratio

Manage development, staging, and production environments with type-safe configuration and secrets handling. \n \n Provides templates for .env files, per-developer overrides, and environment-specific configurations with clear gitignore rules \n Includes TypeScript validation using Zod to enforce required variables and type constraints at runtime with detailed error messages \n Supports multi-environment config files (development, production, test) with environment-specific settings for logging, C

Framework for effective AI collaboration defining task decomposition, context management, abstraction selection, and automation philosophy. \n \n Divide complex tasks into small, independently verifiable steps; AI performs significantly better with clear, bounded instructions than large ambiguous requests \n Keep context fresh and single-purpose; use separate conversations for different topics and apply HANDOFF.md summaries when conversations grow long to prevent context drift \n Adjust abstract

Modern React component patterns for building scalable, maintainable UI libraries. \n \n Covers five core patterns: props API design with TypeScript, composition, render props, custom hooks for logic separation, and performance optimization with React.memo and useMemo \n Includes compound components, polymorphic components, and context-based state sharing for flexible, reusable architectures \n Enforces single responsibility, accessibility standards (aria-*, role, tabindex), and prohibits prop dr

Automated UI code review against Vercel's Web Interface Guidelines. \n \n Fetches the latest guidelines from the official Vercel repository before each review to ensure current rule compliance \n Analyzes React, Vue, Svelte, HTML, CSS, and JavaScript/TypeScript files against all fetched rules \n Reports violations in file:line format with actionable feedback on how to fix each issue \n Supports file paths and glob patterns for flexible scope selection across projects \n

Establish scalable project structures with standardized naming conventions and folder organization patterns. \n \n Provides templates for React/Next.js frontends, Node.js/Express backends, and feature-based large-scale applications with clear separation of concerns \n Defines naming conventions for files (PascalCase components, camelCase utilities, UPPER_SNAKE_CASE constants), folders (kebab-case or camelCase), and variables (with is/has/can prefixes for booleans) \n Includes best practices for

Organize and document software releases with semantic versioning and standardized changelog formats. \n \n Provides Keep a Changelog format with seven standard categories (Added, Changed, Deprecated, Removed, Fixed, Security, Unreleased) for consistent release documentation \n Enforces semantic versioning rules (MAJOR.MINOR.PATCH) with clear guidance on when to increment each version component \n Includes templates for user-facing release notes, migration guides for breaking changes, and API dep

Core principles for effective AI agent collaboration: divide tasks, manage context, choose abstraction levels, automate patterns, and validate results. \n \n Decompose large tasks into small, explicit steps; AI performs 39% better on focused instructions than vague, complex requests \n Keep context fresh and single-purpose using separate conversations or HANDOFF.md documentation to avoid context drift and performance degradation \n Switch between high-level \"vibe coding\" for prototyping and de

Comprehensive backend testing for REST APIs, databases, authentication, and business logic across Jest, Pytest, and Mocha. \n \n Covers unit tests for isolated functions, integration tests for API endpoints, and authentication/authorization flows with detailed examples for Express.js, FastAPI, and other frameworks \n Includes test environment setup, mocking strategies for external dependencies, and database isolation patterns using in-memory or separate test databases \n Provides step-by-step gu

Auto-generates a data-driven LLM usage monitoring dashboard with cost tracking, user ranking, and PM insights. \n \n Tracks token counts, API costs, and latency across OpenAI, Anthropic, Gemini, and OpenRouter using Tokuin CLI; stores metrics in JSONL format with user context and prompt categorization \n Provides two deployment options: Next.js admin dashboard with per-user drilldown pages, or lightweight single-file HTML dashboard with charts, ranking tables, and search \n Includes automatic PM

$22

Configure Claude Code, Codex CLI, and Gemini CLI for reduced-approval Ralph automation while enforcing project boundaries and secret denylists. \n \n Provides two preset permission profiles: repo-scoped (default, safer) and sandbox (full bypass for disposable environments only) \n Implements dynamic safety checkpoints via platform-specific hooks that block Tier 1 dangerous operations (rm -rf, git reset --hard, .env access, sudo) at execution time \n Supports Claude Code, Codex CLI, and Gemini CL

Automate application deployment across Docker, Kubernetes, AWS, and Vercel with CI/CD pipelines. \n \n Covers Docker containerization with multi-stage builds, GitHub Actions workflows for testing and image building, and Kubernetes deployment with rolling updates and autoscaling \n Includes zero-downtime deployment strategies using blue-green deployments and health check validation \n Provides configuration templates for Vercel/Netlify frontend deployments, environment variable management, and gr

Generate high-quality images via Gemini models with structured prompts, aspect ratios, and brand validation. \n \n Supports multiple Gemini models (gemini-3-pro-image, gemini-2.5-flash-image, gemini-2.5-pro-image) optimized for different quality and speed tradeoffs \n Enforces structured prompt format covering subject, style, lighting, mood, composition, aspect ratio, and brand colors to ensure consistent outputs \n Includes validation workflows across multiple agents for prompt completeness, st

Automate issue-to-Draft-PR pipeline by labeling issues for GitHub Copilot assignment. \n \n Label an issue with ai-copilot to trigger GitHub Actions, which auto-assigns Copilot via GraphQL and initiates code generation, branch creation, and Draft PR opening \n Requires GitHub Copilot Pro+, Business, or Enterprise; one-time setup deploys the workflow, registers a PAT secret, and creates the label \n Copilot PRs are treated as external contributions and require manual approval before CI runs; subs

Generate comprehensive API documentation from OpenAPI specs, code comments, and interactive examples. \n \n Supports OpenAPI/Swagger specification generation with full schema definitions, request/response examples, and security schemes \n Includes JSDoc and decorator-based documentation extraction from TypeScript/Express codebases for automatic spec generation \n Provides Swagger UI integration for interactive API exploration with try-it-out functionality \n Covers authentication patterns, pagin

Create clear, comprehensive technical documentation for specs, architecture, runbooks, and APIs. \n \n Provides templates and step-by-step guidance for five document types: technical specifications, architecture documents, runbooks, API documentation, and changelogs \n Includes audience-specific writing strategies for developers, operations teams, managers, and end users with tailored content focus \n Offers visual aid support via Mermaid diagrams, flowcharts, tables, and code examples with synt

Deterministic browser automation for AI agents with snapshot-based element references and multi-session support. \n \n Interact with web pages using stable element refs (@e1, @e2, etc.) generated from snapshots, enabling reliable automation across DOM changes \n Core commands cover navigation, form filling, clicking, waiting, screenshots, PDFs, and visual regression testing via baseline comparison \n Supports parallel isolated sessions, network-aware waits (networkidle), and selector-based targe

Keyword: firebase · firebase deploy · firebase init · firebase emulators

Comprehensive AI agent skill for all Google Workspace document operations — Docs, Sheets, Slides, Drive, Gmail, Calendar, Chat, Forms, Admin SDK, and Apps Script — via official REST APIs.

Fabric is an open-source AI prompt orchestration framework by Daniel Miessler. It provides a library of reusable AI prompts called Patterns — each designed for a specific real-world task — wired into a simple Unix pipeline with stdin/stdout.

Keyword: langsmith · llm tracing · llm evaluation · @traceable · langsmith evaluate

Browser automation connected to your running Chrome session, preserving logins, cookies, and extensions. \n \n Connects to an existing Chrome browser via extension instead of spawning headless instances, enabling authenticated workflows without re-login \n Exposes full Playwright API through CLI ( -e flag) and MCP integration for Claude Desktop and other AI agent platforms \n Includes built-in helpers for accessibility snapshots, screenshots with element labels, network interception, and screen

"The researcher's job shifts from writing Python to writing Markdown." — Andrej Karpathy

React and Next.js performance optimization guidelines across 45 rules in 8 priority categories. \n \n Covers critical waterfalls elimination, bundle size optimization, and server-side performance with specific patterns like Promise.all, dynamic imports, and React.cache() \n Includes medium-priority rules for re-render optimization, rendering performance, and JavaScript efficiency with concrete code examples \n Organized by impact level with prefixed rule names (async-, bundle-, server-, client-,

Production-grade UI design system with design tokens, layout rules, motion guidelines, and accessibility validation. \n \n Provides structured design tokens for colors, typography, spacing, shadows, and breakpoints with 8px-based spacing scale \n Includes section-by-section component architecture with responsive breakpoints (mobile-first, 640/768/1024/1280px) \n Covers motion specifications with CSS variables for duration and easing, plus hover and transition patterns \n Built-in WCAG 2.1 AA acc

Structured sprint retrospective facilitation with three proven formats and actionable outcome tracking. \n \n Offers three retrospective formats: Start-Stop-Continue, Mad-Sad-Glad, and 4Ls (Liked-Learned-Lacked-Longed For), each suited to different team dynamics and reflection styles \n Enforces blame-free discussion, specific action items with owners and due dates, and limits to 2-3 actions per retrospective to ensure follow-through \n Includes time-boxing guidance (1 hour), facilitator rotatio

Prompt repetition technique that improves lightweight model accuracy by 67% across benchmarks. \n \n Auto-applies to claude-haiku, gemini-flash, and gpt-4o-mini; uses 2× repetition for general tasks and 3× for position-based queries \n Mitigates causal attention limitations by reprocessing the entire prompt, strengthening attention weights on key concepts without architectural changes \n Skips automatically when Chain-of-Thought patterns detected; includes duplicate-application prevention via ma

Validate and standardize SKILL.md files against the Agent Skills specification. \n \n Validates frontmatter fields (name, description, allowed-tools, metadata) and enforces naming conventions, length constraints, and format rules \n Converts legacy skill formats to standard structure, including section heading normalization and directory layout alignment \n Provides templates and step-by-step guidance for creating new skills, improving descriptions for reliable triggering, and batch-validating s

Keyword: survey | Platforms: OMC / OMX / OHMG / Claude Code / Codex CLI / Gemini CLI / OpenCode

45 performance rules for React and Next.js, organized by impact from waterfalls and bundle optimization down to advanced patterns. \n \n Covers 8 rule categories prioritized by impact: eliminating waterfalls (Promise.all, Suspense), bundle size (direct imports, dynamic loading), server-side caching, client-side deduplication, re-render optimization, rendering performance, JavaScript efficiency, and advanced patterns \n Each rule includes explanation, incorrect and correct code examples, and cont

Version-control external repositories within a main project using Git submodules. \n \n Add, update, and remove submodules with commands for locking specific commits, branches, or tags \n Clone repositories with submodules using --recursive or manual initialization and update steps \n Batch operations across all submodules via git submodule foreach for pulling, checking status, and branch management \n Nested submodule support with recursive initialization and updates for complex dependency hier

Complete Git workflow management covering branches, commits, merges, conflicts, and team collaboration. \n \n Supports standard branch workflows with naming conventions for features, bugfixes, hotfixes, refactoring, and documentation \n Includes commit message standards using conventional commits format with type, scope, and detailed descriptions \n Covers merge strategies, interactive rebasing, cherry-picking, and conflict resolution with step-by-step examples \n Provides advanced patterns like

Structured task planning with user stories, sprint organization, and backlog prioritization for agile teams. \n \n Provides templates for writing INVEST-compliant user stories with acceptance criteria, technical notes, estimation, and dependencies \n Includes epic decomposition patterns breaking features into stories and granular tasks with time estimates \n Supports MoSCoW prioritization (Must/Should/Could/Won't Have) and sprint planning with capacity planning and Definition of Done checklists

Parse application logs to identify errors, performance issues, and security anomalies. \n \n Supports multiple log formats including Apache, Nginx, application logs, and JSON with grep-based pattern matching \n Covers error debugging, performance analysis (response times, throughput), security audits (SQL injection, XSS, brute force), and incident response \n Includes pre-built grep patterns for HTTP error codes, time-based analysis, IP-based traffic analysis, and suspicious access patterns \n R

Automated compliance verification and enforcement for AI tools against 11 mandatory P0 rules covering auth, security, cost tracking, and logging. \n \n Verifies 11 P0 rules across four domains (Security 40pts, Auth 25pts, Cost 20pts, Logging 15pts) with quantitative compliance scoring and deploy gate verdicts (Green/Yellow/Red) \n Three execution modes: quick static scan via grep/glob patterns, full verification with evidence collection, and guided improvement with fix suggestions and re-verific

State management patterns for React applications with Context, Redux, Zustand, and React Query. \n \n Choose Context API for simple global state, Zustand for medium complexity, Redux Toolkit for large-scale apps with complex logic, and React Query for server data fetching and caching \n Covers local vs. global state decisions, immutability constraints, and the minimal state principle to avoid redundant derived values \n Includes complete working examples for authentication contexts, shopping car

Keyword: react-grab · grab · element context · copy component to ai

Unified AI agent orchestration with planning, execution, verification, and cleanup across Claude, Codex, Gemini, and OpenCode. \n \n Four-phase workflow: PLAN (ralph + plannotator) → EXECUTE (team/bmad) → VERIFY (agent-browser + optional agentation) → CLEANUP (worktree management) \n Supports Claude Code team mode for parallel multi-agent execution; falls back to BMAD for Codex, Gemini, and OpenCode \n Persistent state tracking via .omc/state/jeo-state.json with checkpoint-based resume on restar

$23

REST and GraphQL API design with OpenAPI documentation, versioning strategies, and best practices. \n \n Covers REST fundamentals including resource naming, HTTP methods, status codes, request/response formatting, and error handling patterns \n Includes pagination, filtering, sorting, and field selection query parameters with standardized response structures \n Supports multiple authentication approaches: JWT, OAuth 2.0, API keys, and session-based methods \n Provides URL and header-based versio

Automate development tasks with npm scripts, Makefiles, Git hooks, and shell scripts. \n \n Covers npm scripts, Makefiles, Husky Git hooks, and custom shell scripts for setup, deployment, and CI/CD workflows \n Includes pre-commit automation, linting, testing, and type-checking integrated into development pipelines \n Provides GitHub Actions workflow templates for continuous integration across push and pull request events \n Emphasizes idempotency, error handling, and security constraints like a

Comprehensive monitoring setup with metrics collection, log aggregation, alerting, and health checks. \n \n Covers Prometheus for metrics instrumentation, Grafana dashboards for visualization, and structured logging with Winston for log aggregation \n Includes pre-built alert rules for high error rates, slow response times, pod failures, and resource saturation \n Provides advanced health check endpoints that test database, cache, and external API dependencies with latency tracking \n Implements

Type-safe AI workflows with flows, agents, RAG, and multi-model support across TypeScript, Go, and Python. \n \n Supports Gemini, OpenAI, Anthropic, Ollama, and Vertex AI with pluggable model providers; deploy to Firebase Cloud Functions or Cloud Run \n Define type-safe flows with Zod schemas for inputs/outputs; includes streaming, tool calling, and agentic loops with auto-execution \n Built-in RAG with vector database integrations (Pinecone, pgvector, Firestore, Chroma, LanceDB) and retrieval-a

Systematically isolate and fix code issues using structured debugging methodologies. \n \n Covers six-step debugging workflow: information gathering, reproduction, isolation, root cause analysis, fix implementation, and verification \n Includes common bug patterns (off-by-one, null references, race conditions, memory leaks, type mismatches) with targeted solutions \n Provides debugging techniques: binary search isolation, print/log debugging, divide-and-conquer code elimination, and regression t

Docker Compose, environment variables, dev containers, and infrastructure-as-code templates for consistent local and production setups. \n \n Provides complete Docker Compose configuration for multi-service development (web app, PostgreSQL, Redis, Nginx) with volume mounting and service dependencies \n Includes .env management patterns with type-safe environment variable loading in Node.js and mandatory .gitignore rules to prevent secret commits \n Offers VS Code dev container setup with pre-con

Create clear, user-focused documentation with step-by-step guides, screenshots, and FAQ sections. \n \n Generates four documentation types: quick-start guides, task-focused how-to articles, FAQ pages, and learning-focused tutorials \n Emphasizes visual clarity with embedded screenshots, GIFs, and structured numbered instructions designed for non-technical users \n Includes troubleshooting sections, related links, and multiple support contact methods to reduce user friction \n Follows plain-langu

Optimized patterns for AI agent workflows, Git integration, MCP servers, and multi-agent orchestration. \n \n Covers essential commands across Claude, Gemini, and Codex CLIs, plus keyboard shortcuts for task cancellation, history search, and plan mode toggling \n Includes session management techniques (resume, rename, aliases) and Git workflows for auto-generating commits, PRs, and managing parallel branches with worktrees \n Provides MCP server configuration guidance (Playwright, Supabase, Fire

Comprehensive evaluation framework for designing, building, and monitoring AI agent performance across coding, conversational, research, and computer-use agents. \n \n Covers three grader types (code-based, model-based, human) with trade-offs and best practices for each agent category \n Provides an 8-step roadmap from initial task creation through production monitoring, including environment isolation, outcome-focused grading, and saturation detection \n Includes benchmarks for major agent type

Establish AI agent environment policies, security guardrails, and team configuration standards. \n \n Configure project description files as AI manuals with tech stack, coding standards, and DO NOT rules; use /init for auto-generation from codebase analysis \n Set up security hooks to block dangerous commands (rm -rf, sudo, curl | sh) and auto-approve only safe operations via PreToolUse and PostToolUse events \n Define skills, slash commands, and plugins with token efficiency in mind; skills loa

Integrate Gemini AI into Firebase apps with text generation, streaming, and image analysis capabilities. \n \n Supports text generation, streaming responses, and multimodal (image + text) analysis through Firebase's Gemini integration \n Includes SDK setup for web (JavaScript/TypeScript) with Firebase initialization and model configuration \n Provides security rules templates for protecting AI request logs and enforces API key management via environment variables \n Built-in best practices cover

Structured daily standup facilitation with three formats: 3-question updates, board-walking, and async remote standups. \n \n Provides three standup formats (3 Questions, Walking the Board, and Slack-based async) adaptable to in-person, hybrid, and fully remote teams \n Includes time-boxed 15-minute structure with built-in templates for tracking yesterday's work, today's plans, and blockers \n Enforces core constraints: consistent daily timing, full team participation, and separation of problem-

Install npm packages directly from GitHub repositories using git URLs. \n \n Supports HTTPS and SSH methods for public and private repositories, with authentication via SSH keys or personal access tokens \n Install from specific branches, tags, commits, or the default branch by appending #<ref> to the git URL \n Automatically runs the prepare script during installation, enabling TypeScript compilation and builds for packages not yet published to npm \n Add git URLs directly to package.json

Complete authentication and authorization system with JWT, OAuth, and role-based access control. \n \n Covers five core authentication methods: JWT tokens, session management, OAuth 2.0, password hashing (bcrypt/argon2), and multi-factor authentication support \n Includes step-by-step implementation for user registration, login, token refresh, and logout endpoints with database schema design \n Provides authentication middleware for protecting API routes and role-based authorization for permissi

$22

Detect code smells, security vulnerabilities, anomalies, and trends across codebases using regex, AST analysis, and statistical methods. \n \n Identifies problematic patterns including long functions, duplicate code, magic numbers, empty catch blocks, and TODO/FIXME markers \n Scans for security risks such as SQL injection, hard-coded secrets, dangerous function usage (eval, innerHTML), and credential exposure patterns \n Performs statistical anomaly detection using Z-score and IQR methods to fl

Persistent memory and context management for AI agents across sessions, repositories, and dates. \n \n Load project background before work, search prior conclusions during tasks, and store decisions afterward using slash commands ( /opencontext-context , /opencontext-search , /opencontext-iterate ) \n Supports keyword, vector, and hybrid search modes with optional semantic indexing via embeddings API \n Integrates with multi-agent workflows (Claude, Gemini, Codex) through MCP tools for knowledge

Generate high-quality images via Gemini models with structured prompts, aspect ratios, and brand validation. \n \n Supports three Gemini models (gemini-3-pro-image, gemini-2.5-flash-image, gemini-2.5-pro-image) optimized for different quality-speed tradeoffs \n Enforces structured prompt format covering subject, style, lighting, mood, composition, aspect ratio, and brand colors to ensure consistency \n Includes multi-agent workflow for prompt validation, style verification, and output delivery a

$22

Manage multiple AI agents on a visual Kanban board with automatic git worktree isolation and GitHub PR creation. \n \n Supports parallel agent execution (Claude, Codex, Gemini, Opencode, and 4+ others) across isolated git worktrees, each with its own branch and workspace directory \n Provides a four-column board (To Do, In Progress, Review, Done) where moving a card automatically creates a worktree, starts the agent, and streams logs in real time \n Integrates as an MCP server with tools for lis

$23