AI Skills Hub - Browse 180,000+ Agent Skills

Use when attempting to create strategic work beads (PMF, architecture, multi-epic). Routes to proposal workflow for Supervisor approval instead of direct bead creation.

Helps choose the right battery type and charging solution for Arduino/ESP32/RP2040 projects. Use when user asks about battery options, charging circuits, power source selection, or says "what battery should I use". Covers chemistry selection, safety, voltage regulation, and charging circuits.

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.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

Audit SonarCloud security issues (vulnerabilities and hotspots) for NASA PDS repositories and export to CSV for triage. Use when the user requests SonarCloud security scans, vulnerability reports, or security audits for PDS projects.

Executes Test-Driven Development red-green-refactor workflow for the todo web application. This skill should be used when implementing features using TDD cycle, ensuring tests fail first, then pass, then refactor with 70% minimum coverage. Handles both frontend (Jest) and backend (pytest).

PPT 템플릿/에셋 추출 서비스. Use when: (1) 슬라이드에서 콘텐츠/오브젝트 추출, (2) PPTX에서 문서 양식/슬라이드 마스터 추출, (3) 이미지에서 테마/스타일 추출, (4) 온라인 슬라이드 크롤링

Guide for creating Claude Code slash commands. Use when the user wants to create a new slash command, update an existing slash command, or asks about slash command syntax, frontmatter options, or best practices.

Guide for reading data from Notion using the REST API. Use this skill when Claude needs to (1) Query databases and retrieve entries, (2) Search for pages or databases, (3) Read page properties and content, (4) Get block children and page structure, (5) List users or retrieve user info, (6) Read comments from pages, or (7) Understand how to filter, sort, and paginate data from Notion.

This skill should be used when managing Git worktrees for isolated parallel development. Triggers on "create worktree", "git worktree", "review PR in isolation", "parallel development", "work on multiple branches", "isolated code review", or requests to work on multiple features simultaneously without switching branches.

This skill should be used when creating a new skill or updating an existing skill. Triggers on "create a skill", "new skill", "write a skill", "update skill", "skill template", "SKILL.md", or requests to extend Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Tests OrchardCore CMS features through browser automation. Use when the user needs to build, run, setup, or test OrchardCore functionality including admin features, content management, media library, and module testing.

EpisodicRAG 健全性診断と階層推奨

EpisodicRAG初期セットアップ（対話的）

EpisodicRAG設定変更（対話的）

Summarize YouTube videos by extracting and analyzing their transcripts. Use when a user shares a YouTube URL and asks to summarize, explain, analyze, or extract information from the video. Triggers on YouTube links (youtube.com, youtu.be) with requests like "summarize this video", "what's this video about", "give me the key points", or "explain this video".

Manage blog post translations. Creates new translations for posts that don't have them, and syncs existing translations when English sources change.

YouTube 영상에서 쇼츠 클립 3개를 자동 제작합니다. yt-dlp, whisper, ffmpeg 파이프라인을 사용합니다. "쇼츠 만들어줘", "영상 클립 추출해줘" 요청 시 사용합니다.

This skill should be used when the user asks to "set up documentation", "create docs for Python package", "configure Sphinx", "set up MkDocs", "write docstrings", "use NumPy-style docstrings", "set up Read the Docs", "integrate Jupyter notebooks in docs", "organize documentation with Diataxis", "create API reference docs", "build documentation with nox", "fix documentation build errors", "documentation build fails", "sphinx warning", "autodoc error", "fix sphinx errors", "make documentation accessible", "accessibility guidelines for docs", "accessible images", "alt text for figures", "colorblind-friendly plots", "color contrast in docs", or needs guidance on scientific Python documentation best practices, Sphinx extensions, documentation themes (pydata-sphinx-theme, furo, material), documentation hosting, accessibility standards, or troubleshooting documentation issues.

Search past reasoning for relevant decisions and approaches

Convert Markdown files or HackMD URLs to PDF or DOCX with full support for Traditional Chinese characters, embedded images, Mermaid diagrams, code blocks, and intelligent page breaks. Use this skill when users need to export Markdown documents to PDF or Word format, especially for Chinese content, technical documentation with diagrams, or online HackMD documents.

Generate or edit images using Google Gemini API through the nanobanana tool.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

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.

Review skills against skill-creator's Progressive Disclosure philosophy. Analyze SKILL.md size, duplication, unused resources, and suggest refactorings. Use --holistic for cross-plugin analysis (pattern propagation, boundary issues, missing connections). Triggers: "/refactor-skill"

Advanced Telegram automation assistant using telegram-mcp and local Telethon client. Use when users want to: (1) Get a digest of unread Telegram messages (2) Analyze their writing style from channel posts (3) Draft and publish posts to Telegram channels (4) Search and reply to messages across chats (5) Deep search across all chats with keywords (6) Scrape "Saved Messages" by specific date Triggers: "telegram digest", "unread messages", "summary", "post to channel", "draft telegram post", "analyze writing style", "extract style from channel", "search telegram", "find in telegram", "scrape saved messages", "telegram search", "telegram workflow"

This skill should be used when registering or syncing safe terminal commands to Claude Code settings. Use when the user wants to configure which bash commands Claude Code can execute without requiring approval, or when they need to register/update their safe commands list from the reference file.

This skill should be used when the user wants to list all projects, switch projects, rename a project, enable/disable PR deploys, make a project public/private, or modify project settings.

Build production RAG (Retrieval-Augmented Generation) pipelines with LangChain and Qdrant. Use when users ask to implement semantic search, document Q&A, build RAG systems, create vector search, implement HyDE, CRAG, or Agentic RAG patterns.

// ❌ BAD: Separate tests for each property test('should have id', () { expect(model.id, equals('1')); }); test('should have name', () { expect(model.name, equals('Test')); }); ```

Generate git commit messages from staged changes using the smart-commit style (emoji-first, imperative, issue key from branch). Trigger when a user invokes /smart-commit or asks for a commit message from a git diff.

Query and manipulate Forest Admin data through MCP tools. Use when the user wants to search, filter, explore, create, update, delete data from their Forest Admin database. Triggers on questions like "find all users", "create a new order", "update user 42", "delete inactive products", "show me customers from Paris", or any data operation request involving Forest Admin collections.

Expert on HuskarUI components. Queries metadata for documentation and examples. Works with or without Python.

Harbor framework for agent evaluation. Use when: (1) Running harbor commands (harbor run, harbor tasks check), (2) Creating/validating SkillsBench tasks, (3) Understanding task format or debugging failures.

Deterministic math operations using SymPy - arithmetic, algebra, calculus, linear algebra, number theory, and statistics

Search Yelp for local businesses, get contact info, ratings, and hours. Use when finding services (cleaners, groomers, restaurants, etc.), looking up business phone numbers to text, or checking ratings before booking. Triggers on queries about finding businesses, restaurants, services, or "look up on Yelp".

Extracts hidden or encoded text from GCODE files by analyzing toolpath geometry and coordinate data. This skill should be used when tasks involve decoding text from 3D printing files, recovering embossed or engraved text from GCODE, or CTF-style challenges involving GCODE analysis. Applies to any task requiring geometric reconstruction of text from CNC or 3D printer movement commands.

Guidance for converting COBOL programs to modern languages (Python, Java, etc.) while preserving exact behavior and data format compatibility. This skill should be used when modernizing legacy COBOL applications, converting COBOL business logic to modern languages, or ensuring byte-for-byte output compatibility between COBOL and its replacement.

Guidance for data resharding tasks that involve reorganizing files across directory structures with constraints on file sizes and directory contents. This skill applies when redistributing datasets, splitting large files, or reorganizing data into shards while maintaining constraints like maximum files per directory or maximum file sizes. Use when tasks involve resharding, data partitioning, or directory-constrained file reorganization.

Guidance for developing CoreWars warriors that achieve target win rates against specific opponents. This skill should be used when tasks involve writing, optimizing, or debugging Redcode assembly warriors for the CoreWars programming game, particularly when win rate thresholds must be met against multiple opponents.

Send Telegram notifications when tasks complete, fail, or need user input. Use after completing significant work, encountering errors, or when blocked waiting for user decisions.

Use this skill when the user asks to "create corner plots", "visualize posteriors", "plot chains", "analyze nested sampling output", "plot marginal distributions", "compare prior and posterior", "make triangle plots", or work with posterior samples from PolyChord, MultiNest, UltraNest, Cobaya, or other Bayesian inference tools. Provides complete guidance for creating publication-quality posterior visualizations from nested sampling or MCMC chains.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

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.

Use when work is complete and ready to commit. Triggers after code review passes, when asked to "commit", "save this", or "wrap up". Runs quality checks, updates changelog, creates commit.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis.

Create animated SVG demos for CLI tools to embed in README files. Supports two styling approaches - picocolors for lightweight output or @clack/prompts for polished interactive UIs. Use when building CLI demos, recording terminal output for documentation, or adding visual demos to READMEs.

博客图片自动 WebP 转换。支持文章（Markdown）和 Prompt（TypeScript）两种类型的图片转换。扫描图片引用，转换非 WebP 格式，更新引用并清理旧文件。支持 PNG、JPG、JPEG、BMP、TIFF、TIF、GIF 转 WebP，可控制压缩质量。当用户请求图片格式转换或压缩时调用该 skill。

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

LangGraph 패턴 및 이 Coding Agent 프로젝트의 아키텍처 지식. "LangGraph", "노드", "상태", "워크플로우" 관련 질문 시 자동 로드.

Voice interaction for Claude Code. Use when users mention voice mode, speak, talk, converse, voice status, or voice troubleshooting.

Monitors Azure DevOps pipeline execution status, retrieves logs, parses errors, and determines success/failure. Polls pipeline runs until completion and provides detailed error analysis. Use for automated pipeline monitoring and debugging.

Resets starter-config.json to its default template state with automatic backup. Use when you need to clear all configuration values and start fresh, when the config file becomes corrupted, after testing/cleanup, or to prepare for a new deployment of the Azure AI Foundry Starter template.

Cleans up Azure DevOps resources (repositories, service connections, variable groups, pipelines) and resets configuration files. Use when you need to remove Azure DevOps artifacts after testing or to prepare for a fresh deployment of the Azure AI Foundry Starter template.

Creates UI tests for a GitHub issue and verifies they reproduce the bug. Iterates until tests actually fail (proving they catch the issue). Use when PR lacks tests or tests need to be created for an issue.

Verifies UI tests catch the bug. Auto-detects mode based on git diff - if fix files exist, verifies FAIL without fix and PASS with fix. If only test files, verifies tests FAIL.

Use when the user wants to design Codex agent equivalents (specialized workers/profiles/prompt files), define triggering conditions, or build reusable agent prompts and validation tools.

Use when the user wants to create Codex workflow hooks (pre/post run gates, tool-use validators, stop checks) or needs guidance on hook scripts and hooks.json configuration.

Use before any code changes - hard gate ensuring work never happens on main branch, with proper feature branch creation from correct base

Train deep learning models on Lambda Labs Cloud GPU instances. Use when: (1) User wants to train ML/DL models on cloud GPUs, (2) User mentions Lambda Labs, (3) User needs to launch/manage GPU instances, (4) User wants to run training on A100/H100 GPUs, (5) User needs persistent storage for checkpoints.

YouTube 영상의 자막을 SRT로 추출하는 스킬.

PDF 파일에서 텍스트, 테이블, 이미지를 추출하여 Markdown으로 저장하는 스킬. pdf_to_text.py 사용.

Before modifying shared code (types, APIs, utilities), find all consumers. Prevents partial migrations and broken integrations. Trigger before changing any exported symbol.

Configure Claude Code status line to show notification status

Release workflow using package.json scripts and GitHub Actions monitoring

Creates git worktrees for parallel development with automatic naming and branch management. Use when you need a separate working environment for features, hotfixes, or debugging—especially when juggling multiple branches without stashing changes.

此技能用于下载并分析学术论文（主要支持 arXiv），使用 Moonshot AI (Kimi) 进行深度分析，生成笔记、摘要、代码项目和阅读指南。

Convert Jupyter notebooks (.ipynb) to PDF with proper MathJax formula rendering. Use when: (1) User wants to export a notebook to PDF, (2) PDF needs proper math/LaTeX formula display, (3) User needs a Table of Contents, title page, or clickable navigation, (4) User mentions 'convert notebook', 'export to PDF', or 'notebook PDF'.

Guide for OpenClaw setup, CLI commands, Discord bot integration, configuration, and troubleshooting. Use when helping with OpenClaw agent configuration, channel setup (especially Discord), gateway management, or diagnosing connection issues.

Stacks blockchain development intelligence for Codex.

Use when deploying Node.js, Next.js, or Python/Django apps or static frontends on Ubuntu/Fedora with Nginx, SSL, process managers, Postgres, Docker, or CI/CD guidance.

Comprehensive expert knowledge for NVIDIA DGX Spark workstation. Use when users ask about DGX Spark hardware, software, playbooks, AI Workbench, fine-tuning, inference, troubleshooting, known issues, container workflows, multi-node setup, or any development task on DGX Spark/GB10 Grace Blackwell systems. Triggers on mentions of "DGX Spark", "GB10", "Grace Blackwell desktop", "Spark workstation", or related NVIDIA AI workstation topics.

A guide for building AI agents with the Claude Agent SDK (Python/TypeScript). Use this skill when you need to create agents that can read files, execute code, search the web, or perform autonomous tasks. It provides a clear workflow, links to official documentation, and references to best practices and common patterns.

Convert Obsidian Canvas (.canvas) JSON files to standalone HTML for viewing on GitHub or in browsers. Use when users want to export, convert, or view canvas files as HTML, share canvas diagrams outside Obsidian, or need a web-viewable version of their .canvas files. Handles edge cases like scrollable content for long text, proper box sizing, markdown rendering, and SVG edge connections.

Claude Code hooks configuration patterns, event types, validation scripts, and decision control for automating workflows and integrating external tools. This skill should be used when creating hooks, validating tool usage, automating workflows, or integrating external tools with Claude Code.

Extract structured data from document images or PDFs using a JSON schema. Calls a KIE extraction API and returns field values as JSON.

Extract structured data from document images or PDFs using a JSON schema. Calls a KIE extraction API and returns field values as JSON.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Generalized C++ project testing skill. Analyze project structure, identify key functions, and write test code based on project intent. Use this skill when users need to add unit tests, verify key functions, perform regression testing, check protocol parsers, or test network modules for C++ projects. Supports GoogleTest and Catch2 frameworks.

Add restaurants to your lists by searching Resy and confirming before adding (project)

HTTP traffic capture and WireMock stub generation for QWIQ integration tests. Use when creating offline test fixtures, recording API responses, or converting HAR files to WireMock stubs.

Integration test environment validation for QWIQ. Use when setting up the qwiq-sandbox Azure DevOps environment, verifying test prerequisites, or troubleshooting integration test failures.

Use this skill when implementing any feature, bug fix, or plan task. Triggers on "write tests", "add a test", "do TDD", "test-driven", "implement with tests", "implement task", or when dispatched as a subagent for plan execution. Write test first, watch it fail, write minimal code to pass.

名刺レイアウト JSON から PNG 画像を生成するスキルです。

Scaffold a low-level ability (script-backed). Keywords: ability, low-level, script, scaffolding.

Scaffold a high-level ability (workflow-backed). Keywords: ability, high-level, workflow, scaffolding.

Generate OpenSpec proposals using Gemini CLI. Gemini explores codebase and creates files directly via WriteFile tool. Cost-efficient with 1M token context.

Complete .NET 10 project setup with Next.js frontend and comprehensive C# testing infrastructure using Playwright, Reqnroll (BDD), and NUnit. Use when creating a new full-stack project that requires (1) .NET backend/testing with Next.js frontend, (2) End-to-end testing with Playwright in C#, (3) BDD testing with Reqnroll/SpecFlow patterns, (4) NUnit test framework setup, or (5) VS Code configuration for .NET testing workflow.

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.

코드 작성 완료 후 CI 검증을 로컬에서 수행합니다. 코드 변경 완료 시, 커밋 요청 시, PR 생성 요청 시 자동으로 적용됩니다.

Git Flow를 사용한 릴리즈 및 버전 관리 가이드입니다. 릴리즈 요청 시, 버전 업 요청 시, hotfix 필요 시 사용합니다.

Use PROACTIVELY when working in a worktree as an autonomous agent. Auto-trigger after completing significant work milestones, when tests pass/fail, when blocked on something, or when todo progress changes significantly. Provides status reporting commands for parallel agent coordination.

Sync Plane.so issues to local cache. Use when user says "sync plane", "update plane cache", or "refresh plane issues".

Link task file to Plane issue. Use when user says "link task to plane", "connect to issue", or "link PROJ-XX".

PowerShell development standards for this project. Use when writing, reviewing, or debugging PowerShell code (.ps1, .psm1, .psd1). Covers naming conventions (Verb-Noun, CmdletBinding), error handling (-ErrorAction Stop), performance (List<T>, .Where()), security (TryParse, Test-SafePath), console UI (brackets not emoji), logging (Write-Log module), and Pester testing.

Generate custom animated light patterns using advanced mathematical functions including Fourier transforms, Perlin noise, parametric curves, and wave superposition. Use when the user wants to create new custom patterns, design unique lighting effects, or experiment with mathematical pattern generation.

Discover Govee smart light devices on the local network via multicast or network scanning. Use when the user needs to find Govee devices, locate device IPs, or determine which Govee lights are available on the network.

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.