Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 404 files from 1 741 authors, of which 61 763 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Designs REST and GraphQL APIs including endpoints, error handling, versioning, and documentation. Use when creating new APIs, designing endpoints, reviewing API contracts, or when asked about REST, GraphQL, or API patterns.
Designs software architecture and selects appropriate patterns for projects. Use when designing systems, choosing architecture patterns, structuring projects, making technical decisions, or when asked about microservices, monoliths, or architectural approaches.
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
Manages Git workflows including branching, commits, and pull requests. Use when working with Git, creating commits, opening PRs, managing branches, resolving conflicts, or when asked about version control best practices.
Analyzes and optimizes application performance across frontend, backend, and database layers. Use when diagnosing slowness, improving load times, optimizing queries, reducing bundle size, or when asked about performance issues.
Patterns for parallel subagent execution using Task tool with run_in_background. Use when coordinating multiple independent tasks, spawning dynamic subagents, or implementing features that can be parallelized.
Multi-agent development workflow system. Load when orchestrating development tasks, spawning subagents, or managing workflow phases.
Pattern for effectively interacting with users to gather information or get decisions. Use when you need user input.
Robust workflow checkpoint and resume. Handles session interruption, state recovery, and safe resume across all workflow phases.
Contract lifecycle management - creation, consumption, modification, and resolution.
Load coding conventions and style guidelines when writing or reviewing code. Ensures consistency with project standards.
Pattern for aggregating insights across multiple tasks to enable data-driven evolution.
Load past architectural decisions. Use when making new decisions to ensure consistency.
Strategies for handling subagent failures with retry logic and escalation patterns.
Pattern for efficiently exploring codebases using parallel subagents. Use when you need to understand code structure, find patterns, or gather context.
Pattern for respecting file ownership boundaries during implementation. Prevents conflicts in parallel work.
How to lint and typecheck in this project. Load when implementing or verifying code.
Load common code patterns and abstractions used in this project. Use when implementing features to maintain consistency.
Load project architecture and structure knowledge. Use when you need to understand how this project is organized.
Pattern for producing quality reflections after completing work. Required for all agent outputs.
How to run tests in this project. Load when implementing or verifying code.
Pattern for testing your own code during implementation. Ensures quality before declaring complete.
Pattern for spawning parallel subagents efficiently. Use when you need multiple independent tasks done concurrently.
Pattern for verifying your output matches required schema before completing. Use before writing final output to ensure validity.
Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices.
Create professional, dark-themed architecture diagrams as standalone HTML files with SVG graphics. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology diagrams, or any technical diagram showing system components and their relationships.
Create well-formatted git commits with conventional commit messages and emoji. Use when user asks to commit changes, save work, or after completing a task that should be committed.
Create a new version release with git tag and GitHub Release. Use when user asks to release, publish, create a new version, or ship a release. (project)
Auto-fix CodeRabbit review comments - get CodeRabbit review comments from GitHub and fix them interactively or in batch
AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security).
Collaborative design exploration that refines ideas into validated specs through iterative questioning. Use before any creative work including creating features, building components, adding functionality, or modifying behavior.
Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files, subsystems, bugs) with no shared state or ordering dependencies.
Disciplined plan execution for implementation tasks. Use when executing a saved implementation plan, following step-by-step instructions from a plan document.
Git branch completion workflow. Use when implementation is complete, tests pass, and a feature branch needs to be integrated via merge, pull request, or cleanup.
Assesses and responds to incoming code review feedback on PRs (reviewer comments, requested changes), especially when suggestions are unclear, technically questionable, or scope-expanding. Use before implementing review suggestions to align on intent and keep changes minimal.
Use when you need to request a code review for a PR/MR and want a consistent review brief (context, scope, risk areas, test instructions, acceptance criteria) before merge.
Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid pollution, when formal review cycles (spec compliance then code quality) are required between tasks, or when you need diff-based validation of each task before proceeding.
Root cause analysis for debugging. Use when bugs, test failures, or unexpected behavior have non-obvious causes, or after multiple fix attempts have failed.
Red-green-refactor development methodology requiring verified test coverage. Use for feature implementation, bugfixes, refactoring, or any behavior changes where tests must prove correctness.
Git worktree–based workspace isolation for parallel or non-disruptive development. Use when work must occur without modifying or interfering with the current working tree.
Meta-skill enforcing skill discovery and invocation discipline through mandatory workflows. Use when starting any conversation to check for relevant skills before any response, ensuring skill-first workflow before proceeding.
Verification discipline for completion claims. Use when about to assert success, claim a fix is complete, report tests passing, or before commits and PRs. Enforces evidence-first workflow.
Structured implementation planning for multi-step development tasks. Use when you have a spec or requirements and need to break work into executable steps.
Expert guidance for creating and working with marimo notebooks - reactive Python notebooks that can be executed as scripts and deployed as apps. Use when the user asks to create marimo notebooks, convert Jupyter notebooks to marimo, build interactive dashboards or data apps with marimo, work with marimo's reactive programming model, debug marimo notebooks, or needs help with marimo-specific features (cells, UI elements, reactivity, SQL integration, deploying apps, etc.).
Fast, reproducible scientific Python environments with pixi - conda and PyPI unified
Comprehensive Python programming guidelines based on Google's Python Style Guide. Use when Claude needs to write Python code, review Python code for style issues, refactor Python code, or provide Python programming guidance. Covers language rules (imports, exceptions, type annotations), style rules (naming conventions, formatting, docstrings), and best practices for clean, maintainable Python code.
Modern R development practices emphasizing tidyverse patterns (dplyr 1.1 and later, native pipe, join_by, .by grouping), rlang metaprogramming, performance optimization, and package development. Use when Claude needs to write R code, create R packages, optimize R performance, or provide R programming guidance.
Specialized knowledge of Bash and Zsh scripting, shell automation, command-line tools, and scripting best practices. Use when the user needs to write, debug, or optimize shell scripts, work with command-line tools, automate tasks with bash/zsh, or asks for shell script help.
Generic BAML patterns for type-safe LLM prompting. Covers schema design, DTO generation, client wrappers, and cross-language codegen. Framework-agnostic.
Browser automation for documentation discovery. Use when curl fails on JS-rendered sites, when detecting available browser tools, or when configuring browser-based documentation collection.
C4 architectural modeling for documenting software architecture. Use when creating architecture diagrams, planning new systems, communicating with stakeholders, or conducting architecture reviews.
Debug and analyze web applications using Chrome DevTools MCP. Use for console log inspection, network request monitoring, performance analysis, and debugging authenticated sessions. For basic browser automation (screenshots, form filling), use browser-discovery skill instead.
Patterns and techniques for analyzing brownfield codebases. Use when onboarding to unfamiliar code, preparing for refactoring, conducting architecture reviews, or identifying technical debt.
Detect new imports in modified files and auto-install missing dependencies. Works with npm, uv, pip, cargo, go mod, and other package managers. Triggers after code implementation to keep manifests in sync.
Navigate hierarchical ai-docs indexes to find documentation. Check local docs FIRST for speed and curated context before web searching. Covers Claude Code, BAML, MCP, and other tracked libraries.
Retrieve documentation context from local ai-docs. Check here first when implementing features, debugging errors, or needing library information. Fall back to web search if topic not found locally.
Knowledge of documentation platforms and fetching strategies. Use when adding new documentation sources, determining fetch strategy for a docs site, detecting doc frameworks, or configuring the docs registry.
Detect project stack from package manifests (package.json, pyproject.toml, go.mod, Cargo.toml, pubspec.yaml, CMakeLists.txt). Auto-identify frameworks, test tools, and build systems for onboarding.
The MapReduce skill enables parallel task execution across multiple AI providers or agent instances, followed by intelligent consolidation of results. This produces higher-quality outputs by levera...
Fetch current model names from AI providers (Anthropic, OpenAI, Gemini, Ollama), classify them into tiers (fast/default/heavy), and detect new models. Use when needing up-to-date model IDs for API calls or when other skills reference model names.
Claude Skills — questions
Answers built from the skills we actually parsed.