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. 79 354 files from 1 739 authors, of which 61 713 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.
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Read tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
Write and add new blog posts for this Next.js site by matching the existing BlogPost structure in `src/lib/blog-data.ts`. Use when asked to draft a new blog article, update blog content, or produce SEO metadata/slug/image details for a new post.
Use when the user says "use the DevTools skill" or when they need help debugging a web app with Chrome DevTools MCP (UI bugs, incorrect behavior, console errors, network/API failures, or performance/lag), especially if the user seems inexperienced and needs guided, step-by-step diagnosis.
NixOS module patterns. Use when creating or editing NixOS/home-manager modules, adding packages, or configuring programs.
Work management system replacing built-in todos with tracked tasks and stacked changes
Diagnoses and debugs A2A agent communication issues including agent status, message routing, transport connectivity, and log analysis. Use when agents aren't responding, messages aren't being delivered, routing is incorrect, or when debugging orchestrator, coder-agent, tester-agent communication problems.
Creates new Agent Skills for Claude Code following best practices and documentation. Use when the user wants to create a new skill, extend Claude's capabilities, or package domain expertise into a reusable skill.
Use when the user explicitly asks for a SKILL to create a worktree. If the user does not mention "skill" or explicitly request skill invocation, do NOT trigger this. Only use when user says things like "use a skill to create a worktree" or "invoke the worktree skill". Creates isolated git worktrees with parallel-running configuration.
Master receipt scanning operations including parsing, debugging, enhancing accuracy, and database integration. Use when working with receipts, images, OCR issues, expense categorization, or troubleshooting receipt uploads.
This skill helps you work with the receipt scanning tools in the nonprofit_finance_db project. It includes manual entry tools, automated OCR scanning, and database integration for tracking receipts...
Process video files with audio extraction, format conversion (mp4, webm), and Whisper transcription. Use when user mentions video conversion, audio extraction, transcription, mp4, webm, ffmpeg, or whisper transcription.
This skill is a practical, 'use-it-while-debugging' reference for getting a LiveKit + Letta voice agent working reliably.
Comprehensive git worktree management. Use when the user wants to create, remove, list, or manage worktrees. Handles all worktree operations including creation, deletion, and status checking.
Control Eight Sleep pods (status, temperature, alarms, schedules).
Design and implement RESTful API endpoints following REST principles, HTTP standards, and resource-based URL conventions. Use this skill when creating or modifying API endpoints, routes, controllers, request handlers, or API documentation. Apply when working with REST API design, API versioning, HTTP methods (GET, POST, PUT, PATCH, DELETE), URL structure, query parameters, response formatting, status codes, rate limiting, or API middleware. Use when building web services, microservices, or any backend code that exposes HTTP endpoints for client consumption.
Create and manage database schema migrations with reversibility, zero-downtime deployment support, and proper version control. Use this skill when creating database migration files, modifying schema, adding or removing tables/columns, creating indexes, managing migration rollbacks, or planning database changes. Apply when working with migration files, schema changes, database versioning, or any task involving evolving database structure over time while maintaining backwards compatibility and data integrity.
Define database models and ORM entities with proper naming, relationships, validation, and data integrity constraints. Use this skill when creating or modifying model classes, database table definitions, model relationships (one-to-many, many-to-many), data validation rules, database constraints, or model methods. Apply when working with ORM model files, ActiveRecord, SQLAlchemy, Sequelize, Prisma schemas, or any database model definitions that map objects to database tables and enforce data structure and relationships.
Write secure, optimized database queries using parameterized statements, eager loading, proper indexing, and transaction management. Use this skill when writing database queries, implementing data fetching logic, optimizing query performance, preventing SQL injection, handling N+1 query problems, using ORMs or query builders, implementing caching strategies, or managing database transactions. Apply when working with SQL queries, ORM query methods, database repository patterns, or any code that retrieves or manipulates data from databases.
Build accessible user interfaces using semantic HTML, ARIA attributes, keyboard navigation, color contrast, and screen reader compatibility. Use this skill when creating or modifying HTML templates, React/Vue components, forms, interactive elements, navigation menus, modals, or any UI code. Apply when implementing keyboard navigation, focus management, alt text for images, form labels, heading structure, color contrast, or testing with screen readers. Use for all frontend development to ensure interfaces are usable by people with disabilities and meet WCAG accessibility standards.
Design and build reusable, composable UI components following single responsibility principle with clear props, proper encapsulation, and minimal state management. Use this skill when creating or modifying React, Vue, Svelte, or web components, defining component props or interfaces, managing component state, building component libraries, or refactoring UI code. Apply when working with .jsx, .tsx, .vue, .svelte files, component directories, or any code that defines reusable UI building blocks with configurable interfaces and composable architectures.
Write and maintain CSS using consistent methodology (Tailwind, BEM, CSS Modules), design tokens, framework patterns, and optimized production builds. Use this skill when writing or modifying CSS files, applying utility classes, styling components, creating design systems, defining color/spacing tokens, or working with CSS frameworks. Apply when working with .css, .scss, .sass files, Tailwind config, styled-components, CSS-in-JS, or any styling code that controls visual presentation, layout, typography, and design consistency across the application.
Build mobile-first responsive layouts with fluid containers, relative units, standard breakpoints, and touch-friendly design that adapts seamlessly across devices. Use this skill when creating or modifying layouts, implementing media queries, defining breakpoints, choosing sizing units, optimizing for mobile devices, or testing UI across screen sizes. Apply when working with responsive design, mobile layouts, tablet views, desktop views, viewport configuration, or any styling that needs to adapt to different screen sizes and device capabilities.
Write clean, consistent code following naming conventions, DRY principles, small focused functions, automated formatting, and meaningful variable names. Use this skill when writing or refactoring any code in any language, naming variables/functions/classes/files, structuring code logic, removing dead code, or ensuring code readability and maintainability. Apply to all programming tasks including Python, JavaScript, TypeScript, Ruby, Java, Go, or any other language files (.py, .js, .ts, .rb, .java, .go) to maintain consistent style, improve code quality, and enhance team collaboration across the entire codebase.
Write self-documenting code with minimal, evergreen comments that explain complex logic without describing recent changes or temporary fixes. Use this skill when writing code comments, documentation strings, explaining complex algorithms, clarifying business logic, or deciding whether code needs comments. Apply when working with any source code files where comments or documentation might be added, ensuring comments remain relevant, helpful, and focused on explaining why rather than what the code does, while preferring clear code structure and naming over excessive commenting.
Follow project-wide development conventions including project structure, version control practices, environment configuration, documentation, dependency management, and code review processes. Use this skill when organizing files/directories, writing commit messages, managing branches, configuring environments, handling secrets, maintaining documentation, or establishing team workflows. Apply when working with project structure, README files, .gitignore, environment variables, dependency files (package.json, requirements.txt), feature flags, changelogs, or any aspect of project organization and team collaboration that requires consistency across the development lifecycle.
Implement robust error handling with user-friendly messages, specific exception types, fail-fast validation, centralized error boundaries, graceful degradation, and proper resource cleanup. Use this skill when writing try-catch blocks, raising exceptions, handling API errors, validating input, implementing error boundaries, managing external service failures, or ensuring resource cleanup. Apply when working with error handling code in any language, exception classes, error middleware, API error responses, retry logic, or any code that needs to handle failures gracefully while maintaining system stability and providing clear feedback to users.
Understand and apply project-specific technology choices including frameworks, languages, databases, testing tools, and third-party services to maintain consistency across the stack. Use this skill when making technology decisions, adding new dependencies, choosing libraries/frameworks, configuring build tools, setting up databases, implementing authentication, or integrating third-party services. Apply when working with framework-specific code, package managers, ORM configurations, testing setups, deployment configurations, or any task that requires knowledge of the project's chosen technologies to ensure architectural consistency and avoid introducing conflicting tools or patterns.
Implement comprehensive server-side validation with allowlists, type checking, input sanitization, and consistent error messages, while using client-side validation for user experience. Use this skill when validating user input, form data, API requests, implementing security checks, preventing injection attacks, checking data types/formats/ranges, or providing validation feedback. Apply when working with form validation, API endpoint validation, input sanitization, business rule enforcement, or any code that accepts and validates external data to ensure security, data integrity, and proper user feedback across all entry points.
Write minimal, focused tests for core user flows and critical paths during development, testing behavior rather than implementation with clear test names and mocked dependencies. Use this skill when writing unit tests, integration tests, test files, test cases for critical workflows, or mocking external dependencies. Apply when working with test files (.test.js, .spec.ts, _test.py), test frameworks (Jest, RSpec, pytest), testing user journeys, or implementing fast-executing tests that validate business-critical functionality without over-testing implementation details or edge cases during feature development.
Reproduces the full prefill sensitivity analysis pipeline for reward hacking indicators. Use when evaluating how susceptible model checkpoints are to exploit-eliciting prefills, computing token-based trajectories, or comparing logprob vs token-count as predictors of exploitability.
This skill should be used when updating the project CHANGELOG, tracking requirement changes, recording design decisions, or documenting version history. Uses git-diff to detect and categorize changes to both code and requirements. Trigger on "changelog", "version history", "what changed", or after significant commits.
| Posts a progress checkpoint to the currently active GitHub Issue thread. Saves work state including completed tasks, in-progress items, files changed, commits, and blockers without changing workflow phases. Requires an already-claimed in-progress thread. Use when user wants to save progress, record milestones, document blockers, or preserve state before ending a session.
| CLAIM a specific GitHub issue to START working on it. Requires an issue number. Performs validation, atomic claim, posts claim comment, and sets up worktree. Use when user wants to begin work on a specific issue number (e.g., "claim #201", "start working on issue #N").
Reference material for Athena when writing requirements. NOT a template - Athena writes requirements freely based on the domain. This skill provides guidance patterns that may be useful, not constraints to follow.
| Generate detailed workflow reports with metrics, health assessments, and epic-specific analysis for GitHub Elements. Covers throughput, cycle times, compliance status, and thread history.
This skill should be used when creating, updating, linking, or versioning requirements for GitHub Elements threads. Use when user mentions requirements, specs, REQ files, or when starting feature development. Provides the requirements folder structure, versioning system, and SERENA backup protocols.
| READ-ONLY quick overview of GitHub Elements workflow state. Shows active threads, phase distribution, and workflow health at a glance.
| This skill interprets natural language - users should NOT memorize commands.
Change phases in the GitHub Elements workflow by closing current thread and opening the next. Use for DEV→TEST, TEST→REVIEW, REVIEW→merge transitions, or demotions. Do not use for saving progress.
This skill should be used when the user asks to "track work across sessions", "create an epic", "manage issue waves", "post a checkpoint", "claim an issue", "recover from compaction", "coordinate multiple agents", "update memory bank", "store large documents", or mentions GitHub Issues as persistent memory, multi-session work, context survival, agent collaboration, SERENA MCP memory, or project-level context. Provides complete protocols for using GitHub Issues as permanent memory that survives context exhaustion, with integrated SERENA MCP memory bank for project-level context and large document storage.
Use when generating or updating Table of Contents in markdown files. Supports multiple files, glob patterns, configurable header levels, and various insertion modes. Triggered by "generate toc", "update toc", "table of contents", "add toc to markdown".
Use when creating releases for Claude Code plugin marketplaces. Supports independent plugin versioning - each plugin can be released separately. Triggered by "release", "bump version", "create release", "publish plugin".
Guides users on modern async patterns including native async fn in traits, async closures, and avoiding async-trait when possible. Activates when users work with async code.
Guides users on choosing between async and sync patterns for Lambda functions, including when to use tokio, rayon, and spawn_blocking. Activates when users write Lambda handlers with mixed workloads.
Enterprise-grade browser automation using WebDriver protocol. Use when the user needs to automate web browsers, perform web scraping, test web applications, fill forms, take screenshots, monitor performance, or execute multi-step browser workflows. Supports Chrome, Firefox, and Edge with connection pooling and health management.
Provides guidance on reducing Lambda cold start times through binary optimization, lazy initialization, and deployment strategies. Activates when users discuss cold starts or deployment configuration.
Provides architectural guidance for data lake design including partitioning strategies, storage layout, schema design, and lakehouse patterns. Activates when users discuss data lake architecture, partitioning, or large-scale data organization.
Reviews SQL queries and DataFrame operations for optimization opportunities including predicate pushdown, partition pruning, column projection, and join ordering. Activates when users write DataFusion queries or experience slow query performance.
Guides users in creating rich domain models with behavior, value objects, and domain logic. Activates when users define domain entities, business rules, or validation logic.
Guides users on error conversion patterns, From trait implementations, and the ? operator. Activates when users need to convert between error types or handle multiple error types in a function.
Proactively reviews error handling patterns and suggests improvements using Result types, proper error propagation, and idiomatic patterns. Activates when users write error handling code or use unwrap/expect.
Reviews code architecture for hexagonal patterns, checks dependency directions, and suggests improvements for ports and adapters separation. Activates when users work with services, repositories, or architectural patterns.
Reviews AWS Lambda functions for performance, memory configuration, and cost optimization. Activates when users write Lambda handlers or discuss Lambda performance.
Identifies deeply nested if-let expressions and suggests let chains for cleaner control flow. Activates when users write nested conditionals with pattern matching.
Production-ready patterns and best practices for MCP servers - architecture, security, performance, and maintenance
Claude Skills — questions
Answers built from the skills we actually parsed.