AI Skills Hub - Browse 180,000+ Agent Skills

Create isolated git worktrees with smart directory selection and safety verification

Google Ad Manager report generation module for Python. Covers 5 report types (delivery, inventory, sales, reach, programmatic), report dimensions and metrics, report creation and execution, filtering and date ranges, report data manipulation, and MCP report tools (gam_quick_report, gam_create_report, gam_run_report, gam_list_reports).

Comprehensive guide for building MCP servers with FastMCP 2.0. Use when creating MCP tools, resources, prompts, implementing authentication (JWT, OAuth, RemoteAuthProvider, JWTVerifier), deploying to Cloud Run, working with MCP context, server composition, or building AI assistant integrations. Covers @mcp.tool decorators, type annotations, async patterns, error handling, HTTP transport, and production deployment.

Instantly connect VS Code Remote SSH to any RunPod pod with SSH configured

Query the CDM DuckDB database using natural language. Use this skill when the user wants to query the linkml-coral CDM database with questions in plain English instead of writing SQL. The skill translates natural language to SQL using Claude API and returns formatted results.

This skill should be used when reading files (Markdown, Text, PDF) and creating or updating a knowledge base with semantic indexing using LanceDB for vector search capabilities. Supports hybrid storage with markdown files for human readability and LanceDB for efficient semantic queries.

OCR and markdown conversion skill using Gemini. Supports parallel processing and hash-based caching.

Upload files to Slack channels or threads. Supports auto-detection of channel/thread from environment.

基于 LangGraph 构建生产级 Agent，涵盖 State/Node/Router/HITL 模式

Routes domain expert for code review and validation. Use this skill when reviewing pull requests that touch src/routes/, when analyzing route definitions, loaders, beforeLoad guards, or API handlers, when detecting routes domain violations (redundant auth checks, improper data loading, dead code), or when a senior AI agent needs to validate code against Routes domain best practices. Provides automated violation detection and actionable PR comments.

Create Chrome/Chromium browser extensions for users without coding experience. Use when someone wants to add keyboard shortcuts to a website or web app, automate clicking buttons or focusing inputs on web pages, or create simple browser extensions. Primary use case is adding keyboard shortcuts to web applications like Salesforce, HubSpot, and other CRMs.

Debug getServerSideProps and getStaticProps errors in Next.js. Use when: (1) Page shows generic error but browser console is empty, (2) API routes return 500 with no details, (3) Server-side code fails silently, (4) Error only occurs on refresh not client navigation. Check terminal/server logs instead of browser for actual error messages.

Authoritative context for AppDistillery Platform - a modular monolith SaaS with AI-powered consultancy tools. Use when installing packages, creating modules, adding integrations, or making architecture decisions to prevent duplicates and ensure consistency.

Systematic debugging skill optimized for agentic coding. Use when encountering runtime errors, build failures, test failures, type errors, database issues, performance problems, or unexpected behavior. Provides structured workflows that maintain AI context focus while diagnosing issues efficiently. Essential for production debugging, RLS policy errors, hydration mismatches, or any code requiring systematic analysis.

Generate Umbraco CMS installation scripts using the Package Script Writer CLI

Browser validation checks for testing Umbraco backoffice extensions manually

Umbraco backoffice extension customisation - complete working examples showing how extension types combine

Validate links and references in SKILL.md files using deterministic scripts

Analyze code examples in SKILL.md files for correctness using static analysis and TypeScript compilation

Use when authoring new documentation or fixing style/formatting violations in Auth0 docs-v2 repository - enforces Auth0 Docs Style Guide for terminology, voice/tone, admonitions, placeholders, capitalization, and translation readiness (not for reading/understanding docs)

Updates existing README.md files after code changes. Use for requests to update, check, fix, or add to an existing README. Trigger phrases include "update readme", "check readme", "is the readme current", "add to readme", "fix readme", "readme out of date". Also use after adding dependencies, environment variables, or configuration. For creating new READMEs from scratch, use writing-documentation instead.

Normalize Pencil/MCP-generated UI code to Cloakling’s design system (tokens, primitives, shadows, z-index, spacing).

Generate complete, production-ready Claude skills directly to the filesystem. Claude should use this skill when creating new skills, extending Claude's capabilities, or helping users build custom skill packages.

Generate OpenAPI specifications from Chrome DevTools network requests. Use this skill when users need to reverse-engineer or document an undocumented API by analyzing network traffic, create API specifications from web application requests, or build efficient client interfaces for websites without public APIs.

Toolkit for interacting with and testing local web applications using Chrome DevTools Protocol. Supports modern tools (pnpm, turborepo, Next.js/React), verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Download images from websites to local directory with intelligent renaming and metadata insertion. Supports authenticated downloads using cookies and session tokens from Chrome DevTools. Use when users need to save images from URLs (including login-protected sites), rename downloaded files systematically, or embed metadata (title, author, copyright, source URL) into image files. Supports JPEG, PNG, TIFF, WebP with EXIF/PNG metadata standards.

Use when working with Qdrant vector database for semantic search and RAG. Covers collection setup, embedding generation, vector upsert/search, HNSW indexing, filtering, and integration with OpenAI embeddings for textbook content retrieval.

Use when working with Neon serverless PostgreSQL database. Covers database setup, CLI commands, Drizzle ORM integration, schema migrations, connection pooling, and user data storage patterns for authentication and chat history.

Interact with Plane project management (self-hosted) via REST API for issue tracking, project planning, sprint management, time tracking, and documentation. This skill should be used when: (1) working in a project directory that needs task tracking, (2) creating implementation plans with trackable issues, (3) managing sprints/cycles and modules, (4) updating issue status as work progresses, (5) logging time spent on tasks, (6) creating project documentation pages. Secrets stored in Phase (claude-code app).

Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Search code semantically using natural language. Automatically checks if index exists - only indexes if needed. Use when you need to find code by meaning rather than exact text matching.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Compress Excel files into LLM-friendly format and perform AI-based cell range recognition. Use this when users need to process, analyze, or extract data from spreadsheet files.

Use when creating Claude Code hooks for code quality, static analysis, or workflow automation. Use when user says "add hook", "enforce linting", "add pre-commit check", "block bad code".

Create or update an Action in app/Actions following JournalOS conventions (validation, logging, queues, tests).

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Enforces DevOps best practices for commits, merges, and PRs. Use when user requests a commit, merge, or pull request. Analyzes changes, validates quality, composes conventional commit messages, and ensures user approval before any git operations.

Add a new language model to the Giselle codebase. Use when the user wants to add, register, or integrate a new LLM model (OpenAI, Anthropic, Google) into the system.

Comprehensive ImageMagick operations for image manipulation in Moltbot.

Remote-control zellij sessions for interactive CLIs by sending keystrokes and scraping pane output.

Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.

Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.

Daily morning rollup of important emails and calendar events at 8am with AI-generated summaries

Subskill zur Marker Engine für strikt markerbasierte JSON-Annotationen mit Farbhervorhebung; enthält Overlapping-Span-Merging, Dark-Mode-Farben und eine In-Page-SIT-UI (ohne Popup). Erzwingt ZIP-Entpacken, Supabase-Nutzung und Anti-Halluzination (Only-Original-Marker + 3×-Schwelle).

Compare cursor-agent help outputs between different versions to identify new or changed features, options, and commands. Use when the user asks about cursor-agent version differences, what's new, changelog, or comparing cursor-agent versions.

Convert JSON ABI files to TypeScript const exports with proper typing. Use when working with smart contract ABIs, converting JSON to TypeScript, generating typed contract interfaces, or adding new contract ABIs to the SDK.

Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.

Transforms discovery findings into formal specifications with user stories, use cases, business rules, and acceptance criteria. REQUIRES USER APPROVAL before continuing.

Test Ash Reactor workflows including unit tests for individual steps, integration tests for complete reactors, mocking with Mimic, and compensation/undo testing. Use when writing tests for reactors, testing reactor steps, mocking external services in reactor workflows, testing error handling and rollback behavior, or setting up test data for reactor inputs.

Comprehensive guide for testing Ash Framework resources, actions, policies, validations, relationships, calculations, and aggregates. Use when writing tests for Ash resources, testing code interfaces, validating authorization policies, testing changesets and validations, setting up test data with Ash.Generator, mocking external services, or ensuring test isolation with DataCase. Triggers include test files for Ash resources, mentions of Ash.Test, Ash.Generator, policy testing, assert_has_error, or testing Ash actions.

Analyze budget vs actual variances in Excel with drill-down and root cause analysis. Use when performing variance analysis or explaining budget differences. Trigger with phrases like 'excel variance', 'analyze budget variance', 'actual vs budget'.

Git-backed issue tracker for multi-session work with dependencies and persistent memory across conversation compaction. Use when work spans sessions, has blockers, or needs context recovery after compaction.

Launch and manage interactive terminal canvases (document, calendar, flight) in tmux split panes. Use when the user wants to display markdown documents, calendars, or flight booking interfaces in a side panel. Supports real-time updates via IPC.

Diagnose and verify Parade project setup. Checks all required components and reports issues.

Approve a specification and export it to beads as an epic with tasks. Creates the epic, child tasks, dependencies, and agent assignment labels. Use after reviewing the spec from /start-discovery.

Build leveraged buyout (LBO) models in Excel with debt schedules and IRR analysis. Use when structuring LBO transactions or analyzing PE returns. Trigger with phrases like 'excel lbo', 'build lbo model', 'calculate pe returns'.

Use when you need to generate, validate, or deploy stored procedures for PostgreSQL, MySQL, or SQL Server. Creates database functions, triggers, and procedures with proper error handling and transaction management. Trigger with phrases like "generate stored procedure", "create database function", "write SQL procedure", "add trigger to table", or "create CRUD procedures".

Creates, updates, and merges GitHub pull requests using GitHub CLI. Handles the complete PR lifecycle including validation, creation, labeling, review, squash merge, and automatic semantic versioning with git tags. Use when user wants to create a PR, update existing PR, merge with squash, manage PR workflow, or create releases with version tags. Requires GitHub CLI (gh) installed and authenticated. Works with project-specific conventions for JordiNodeJS/thesimpsonsapi.

Keep Clawdbot/Moltbot gateway running 24/7 with PM2 auto-restart and boot startup. Use when setting up daemon mode, process management, crash recovery, or Windows/Linux/Mac startup persistence for the gateway.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

Automate database backup processes with scheduling, compression, and encryption. Supports PostgreSQL (pg_dump), MySQL (mysqldump), MongoDB (mongodump), and SQLite. Generates production-ready backup scripts with retention policies and restore procedures. Trigger: "automate database backups", "schedule backups", "create backup script", "disaster recovery".

Conda 环境管理。本项目使用 newcamera 环境，所有代码运行前必须先激活环境。

Build discounted cash flow (DCF) valuation models in Excel. Use when creating DCF models, calculating enterprise value, or valuing companies. Trigger with phrases like 'excel dcf', 'build dcf model', 'calculate enterprise value'.

Execute automatic activation for all google cloud agent development kit (adk) Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

进行股票异动，价值投资分析与趋势查询

Create data fetching services using the Crevio SDK. Use this skill when the user asks to fetch data from the Crevio API, create new integration services, or work with Crevio resources like products, orders, customers, or subscriptions.

Control Sonos speakers (discover/status/play/volume/group). Use this skill when the user wants to control audio playback, manage speaker groups, or interact with their Sonos system.

This skill should be used when deploying a Docusaurus site to GitHub Pages. It automates the configuration, building, and deployment process, handling GitHub Pages setup, environment configuration, and CI/CD automation. Includes local validation before GitHub Actions triggering.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Local documentation retrieval, navigation, and synchronization using llms.txt standard. Use when users ask questions about LangChain, Spring, or project-specific documentation, need to search/browse the local knowledge base, or want to sync remote documentation to local.

PRD 기반 코드 완성도 평가 스킬. 사용 시점: (1) '코드 리뷰해줘', '코드 평가해줘' 요청 시, (2) PRD 대비 구현 완성도 확인 시, (3) '코드 분석', '코드 품질 체크' 요청 시. Python과 C# Unity 코드를 우선 지원하며, 문법/로직/구조/효율성/명명규칙을 평가하여 100점 만점 종합점수와 항목별 A/B/C/D 등급을 제공. MD 리포트와 1장 PPTX 요약 생성.

Deploy Flask/Python webapps to Google Cloud Run with Firebase Hosting for friendly URLs. Zero-cost for low-traffic internal tools.

Roll real dice using OS randomness (not fabricated), optionally log results to NDJSON for audit, and emit a Markdown-ready summary for Mechanics blocks.

Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate. Teaches the LLM model the patterns, philosophy, and decision-making for effective beads usage.

Use when implementing features via BDD for behaviors and TDD for units, tracking with Bead for persistence and dependencies - minimizes iterations from story to code by enforcing workflows and handling discoveries.

Update the wrangler plugin to the latest version by clearing all caching layers. Use when user says "update yourself", "update wrangler", or after pushing changes to the wrangler repo.

Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

Manage features.yml for tracking requirements and progress; use proactively ONLY when features.yml already exists, or invoke manually to create one; complements TodoWrite for persistent project state.

Guide for writing effective log messages using wide events / canonical log lines. Use when writing logging code, adding instrumentation, improving observability, or reviewing log statements. Teaches high-cardinality, high-dimensionality structured logging that enables debugging.

Enforces strict waterfall development workflow with phase gates. Use when (1) features.yml exists in project root, (2) user asks to implement/develop/build a feature, (3) user explicitly requests waterfall workflow. Creates features.yml if missing when invoked.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Generate AI-ready metadata for design system components to enable intelligent UI generation. Analyzes component structure and generates structured metadata that helps AI understand when and how to use components correctly. Useful for teams building AI-consumable design systems.

Document software architecture using ARCHITECTURE.md and docs/*.md files with Mermaid diagrams. Use proactively when ARCHITECTURE.md exists in project root, or invoke to create initial architecture documentation. Covers system design, data flows, component relationships, and code organization with references to key entry points and abstractions.

Decompose high-level specs into atomic specs

Implement code changes based on approved atomic specs. Executes one atomic spec at a time, gathers evidence, and escalates if implementation reveals spec gaps. Use after spec group approval.

Generates test scaffolding and suggests test cases for Python code. Use when creating tests for new code, adding tests to untested code, generating Hypothesis strategies, or creating test fixtures. Follows pytest naming conventions and modern testing best practices.

Tracks and reports code quality metrics over time. Use when reviewing overall code quality, preparing quality reports, setting quality gates, or tracking technical debt. Calculates complexity, maintainability, and other metrics.

Guides safe, automated refactoring operations across codebases. Use when renaming symbols, extracting functions/classes, moving code between modules, or applying design patterns. Ensures refactoring preserves behavior.

Sets up and maintains CI/CD quality pipelines for GitHub Actions. Use when setting up CI, configuring quality gates, optimizing pipelines, or troubleshooting CI failures. Generates appropriate workflows based on repository tooling.

Autonomous documentation quality enforcement using rumdl, vale, and Diataxis standards. Use when working with markdown files, documentation, README files, guides, or .md files. Validates frontmatter, prose quality, code blocks, and ensures Diataxis compliance.

Analyzes and maintains documentation structure using the Diataxis framework. Use when creating new documentation sections, reorganizing docs, setting up zensical/sphinx, or planning documentation for new projects.

Generates hand-drawn style visuals from video scripts by creating Excalidraw JSON files programmatically, then importing into Excalidraw for visual validation. Use when creating diagrams, flowcharts, infographics, or illustrations for YouTube videos, educational content, or presentations.

Mandatory self-review of generated images before marking complete

Manage Plane.so projects, work items, cycles, and modules. Use when creating/updating issues, managing sprints, organizing work, or querying project status. Supports all Plane API operations without heavy MCP token overhead.

Implements and configures Mintlify documentation sites. Use when setting up new Mintlify sites, troubleshooting configuration errors, configuring OpenAPI/API reference pages, or implementing personalization. Includes guidance on avoiding anti-patterns and applying workarounds.

Implements and configures Mintlify documentation sites. Use when setting up new Mintlify sites, troubleshooting configuration errors, configuring OpenAPI/API reference pages, or implementing personalization. Includes guidance on avoiding anti-patterns and applying workarounds.