AI Skills Hub - Browse 180,000+ Agent Skills

Convert Office documents (Word, Excel, PowerPoint, PDF) to Markdown format. ONLY use this skill when the user explicitly requests to CONVERT, TRANSFORM or PARSE a specific office file into Markdown. Do NOT trigger for general questions, documentation reading, or discussions about files.

Look up assessment boundaries and common misconceptions for ELA standards. Use when you need curriculum context before generating questions.

Deploy a local project to a Linux server over SSH using connection details from a .env file, with upload, server load checks, and README-based deployment steps. Use when Codex needs to publish or deploy a project to a remote Linux host via SSH/SFTP and must follow README deployment instructions.

`${error.message}\n\nStack: ${error.stack}\n\nComponent Stack: ${errorInfo.componentStack}`,

Manage task lifecycle with automatic ID generation, CHANGELOG updates, and git commits following project conventions.

Add a new skill to an existing Claude Code plugin

Creates a multi-hook workflow chain with state management. Use when: building automated sequences, validation pipelines, or complex hook orchestrations.

Package a Claude Code plugin for distribution

Creates an individual hook script with proper shell structure. Use when: adding validation guards, workflow automation, or event-driven triggers.

Add a hook configuration to an existing Claude Code plugin

Set up Rei Qwen3 Coder as a model provider. Use when configuring coder.reilabs.org, adding Rei to Clawdbot, or troubleshooting 403 errors from Rei endpoints.

Analyze completed tool-usage workflows from chat history and package them into reusable Agent Skills. Rejects development tasks and guides users through skill creation with interactive refinement.

Access Polymarket user trading data and portfolio analytics. Get trader positions, P&L, trading history, portfolio value, leaderboards, and top holders. Use for user analytics, NOT market discovery. Base URL: https://data-api.polymarket.com

Use when user wants to browse recipe inspirations from Bring! shopping app. For discovering recipes, viewing recipe details (name, author, type, images), or filtering by tags. Note - cannot import ingredients (API limitation).

Use when you need to start a local development server, view the site locally, provide a localhost URL, or when the user wants to preview their work. Handles port conflicts automatically.

使用Playwright与本地Web应用程序进行交互和测试的工具包。支持验证前端功能、调试UI行为、捕获浏览器截图和查看浏览器日志。

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.

End-to-end testing with Playwright. Integrated into APEX EXAMINE phase. A feature CANNOT pass unless E2E test succeeds. Required for Ralph loop completion.

Generate Azure DevOps YAML pipelines for Newman test execution. Use when you need to create ADO pipelines, configure Newman in CI/CD, publish test results to Azure DevOps, set up variable groups for secrets, configure scheduled test runs, or support QA MVP Step 7. Covers smoke and regression pipeline patterns with JUnit and HTML reporting.

Recovers interrupted webnovel tasks with precise workflow state tracking. Detects interruption point and provides safe recovery options. Activates when user wants to resume or /webnovel-resume.

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.

Web content fetching using the Fetch MCP server. Use when Claude needs to access web content, documentation, API references, or public data from URLs. Triggers on requests to fetch, retrieve, or access content from websites, documentation sites, or public APIs.

Garmin Connect integration for Clawdbot: sync fitness data (steps, HR, calories, workouts, sleep) every 5 minutes using OAuth.

Spec-Driven Development using spec-kit with colocated module documentation. Use when (1) planning new features with spec-kit workflow (specify → plan → tasks → implement), (2) creating or updating module SPEC.md files, (3) bootstrapping specs for existing codebases, (4) graduating completed specs to permanent documentation. Integrates with Obsidian for knowledge graph visualization.

Development of AWS Lambda functions using Vertical Slice Architecture with Node.js + TypeScript. Use when the user asks to create Lambda functions, API endpoints, or backend features following the vertical slice pattern. Triggers: "lambda", "vertical slice", "crear feature", "aws function", "scaffold lambda", "nuevo endpoint", "api endpoint", "serverless", "express lambda", "crear slice", "agregar feature"

Use when setting up or operating igrep in Claude Code: bootstrap, indexing, two-stage search, dependency/usage queries, Z.AI/OpenAI-compatible API configuration, background LLM enrichment, and noise filtering for token-efficient codebase understanding.

Reduces verbose WebVTT transcript files into clean, consolidated Markdown format for use in agentic workflows. Use when working with VTT meeting transcripts that need to be processed, summarized, or used as context for document creation.

Create or modify evaluations for MCP Server(s). Use whenever you are tasked with changed MCP evals.

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.

OnlyWorlds schema reference for field lookups and validation. Use when checking if a field exists, validating element structure, disambiguating element types, or answering schema questions. AI reference tool.

데이터 분석 쿼리 에이전트 사용 시점: 유저가 데이터 조회/분석을 요청할 때 (거래액, UV, 전환율 등) 기능: 테이블 탐색 → 쿼리 작성 → Trino 실행 → 결과 정리

Execute Elasticsearch queries against production(prod) or stage environments.

Agit Bot API v2를 사용하여 그룹, 게시글(wall_messages), 댓글을 조회합니다.

Use when work is complete and you want to commit it, push it to GitHub, and optionally create a PR.

Run integration tests for the Loyalty Points Program using the containerized test suite. All tests are defined in specs/testing.md.

AI image generation with OpenAI, Google and DashScope APIs. Supports text-to-image, reference images, aspect ratios, and parallel generation (recommended 4 concurrent subagents). Use when user asks to generate, create, or draw images.

Create OpenGraph and Twitter share images for Next.js applications using next/og ImageResponse. Generates dynamic social preview cards with gradients, SVG icons, and proper dimensions. Use when building OG images, Twitter cards, social previews, meta images, or share images for webapps.

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.

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 CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

This skill should be used when syncing agents, commands, and skills from a central Claude Code repository. It guides users through selecting what to pull (all items, specific categories, or individual items) and handles cloning, backups, and safe overwriting.

本地 CI 执行器。在提交代码前强制运行架构检查、风格检查和针对性单元测试，确保本地质量门禁通过后才允许推送云端。

Trade perpetual futures on WOOFi Pro (Orderly Network). Use when user wants to place orders, manage positions, set stop-loss/take-profit, or run systematic trading strategies. This skill is an EXECUTION layer — it runs strategy.json configs. If user has no strategy, direct them to iamstarchild.com to create one first.

Complete workflow to process lesson videos - converts MP4 to MP3, transcribes audio to text, and generates email summary. Automatically chains convert-to-mp3, transcribe-audio, and send-email skills.

Convert audio files to text using faster-whisper. Supports MP3, MP4, WAV, M4A and other formats. Optimized for speed with multiple model options.

Guidelines for creating and managing Pull Requests in this repo

初始化 Spec Mode 框架（元技能），一键创建 .comate/ 目录结构和核心文件。 **触发词**：初始化specmode、init specmode、创建.comate目录、初始化spec mode框架、新项目接入、从零搭建、bootstrap specmode **使用场景**：新项目接入 Spec Mode 框架、从零搭建 AI 协作规范

SNES Assembly (65816) patch manager. Curates ASM snippets, verifies patches with Asar/Z3DK, and manages the code library for Oracle of Secrets.

Autonomous navigation agent for Oracle of Secrets. Uses static map data and dynamic RAM state to localize Link and route him to destinations.

Performance profiler for Oracle of Secrets. Samples the CPU Program Counter (PC) to identify code hotspots and laggy routines using statistical analysis.

Regression testing tool for Oracle of Secrets. Records gameplay scenarios and replays them on new builds to detect logic bugs or desyncs.

Autonomous crash analysis for Mesen2. Captures execution traces upon crash/pause, resolves symbols using z3ed, and generates annotated reports for debugging.

Dynamic RAM analyzer for SNES debugging. Monitors memory ranges in real-time via Mesen2 to identify unknown variables, detect changes, and map memory usage.

Background watchdog for Oracle of Secrets. Monitors Mesen2 for crashes (pauses) and softlocks (stuck state/input), automatically triggering a crash dump investigation when detected.

Automated fuzzer for Oracle of Secrets. Injects random inputs to stress-test the game engine and detect crashes or softlocks.

Use when: (1) Testing async/await functions and coroutines, (2) Creating async fixtures, (3) Mocking async code with AsyncMock, (4) Testing aiohttp clients or async database ops, (5) Debugging event loop errors, (6) Testing Django async views/ORM/Channels.

Use when: (1) Writing unit tests for single functions/classes in isolation, (2) Testing without external dependencies (no DB/network/filesystem), (3) Implementing TDD workflows, (4) Debugging flaky tests, (5) Questions about test design or best practices.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Test the running application using Playwright headless browser or Chrome MCP. Takes screenshots, clicks elements, reads console errors, verifies UI renders correctly. Invoke this after implementing a feature.

Start or restart the Godot editor MCP server and debugger/DAP ports for this project. Use when MCP tools are missing, handshake fails, or the debug port is absent; includes a single-editor restart workflow and command checks.

Autonomous MCP and Godot recovery procedures. Use when MCP tools are unresponsive, port 9080 is not listening, or multiple Godot instances are causing conflicts.

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.

Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you’re designing a CLI spec (before implementation) or refactoring an existing CLI’s surface area for consistency, composability, and discoverability.

Generate mermaid diagram for a workflow.

Analyze open-source technologies in the project directory to extract core technical principles and architecture. Generate comprehensive technical documentation summarizing the latest technologies, their core principles, implementation details, and architectural patterns. Use when the user wants to understand the technical essence of projects in the project/ directory, extract core principles, or generate technical summaries in the sumup/ directory.

Three.js scene-graph parsing and export workflows: mesh baking, InstancedMesh expansion, part partitioning, per-link OBJ export, and URDF articulation.

Use when creating Python projects, managing dependencies with uv, configuring pyproject.toml, building packages, or publishing to PyPI - covers project initialization, dependency management, and distribution; NOT for testing or performance (plugin:python@dot-claude)

Linux VM bootstrap verification skill. MUST BE USED when setting up new VMs or verifying environment. Supports modes: check (warn-only), install (operator-confirmed), strict (CI-ready). Enforces Linux-only + mise as canonical; honors preference brew→npm (with apt fallback). Verifies required tools: mise, node, pnpm, python, poetry, gh, railway, bd, tmux, jq, rg. Handles optional tools as warnings: tailscale, playwright, docker, bv. Never prints/seeds secrets; never stores tokens in repo/YAML; Railway vars only for app runtime env. Safe on dirty repos (refuses and points to dirty-repo-bootstrap skill, or snapshots WIP branch). Keywords: vm, bootstrap, setup, mise, toolchain, linux, environment, provision, verify, new vm

Safely delete files and directories by moving them to trash/recycle bin instead of permanent deletion. Works across macOS, Linux, and Windows with automatic fallback mechanisms.

Generate professional YouTube thumbnails with AI-powered expression cutouts and Remotion rendering. Perfect for content creators who want consistent, high-quality thumbnails at scale.

Professional resume builder with PDF export, ATS optimization, and analysis capabilities. Use when users need to (1) Create new resumes from scratch, (2) Customize/tailor existing resumes for specific roles, (3) Analyze resumes and provide improvement recommendations, (4) Convert resumes to ATS-friendly PDF format. Supports chronological, functional, and combination resume formats.

Removes a feature harness created by the create-harness skill. Use when you need to clean up harnesses that are no longer needed.

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries.

AI-powered image editing using Qwen-Image-Edit-2511 via RunPod serverless. Use for photo editing, reframing, clothing changes, style transfers, and character transformations while preserving identity.

This skill should be used when analyzing chess positions. Automatically triggers when users provide FEN positions for analysis or ask about specific chess positions. Provides engine-powered analysis with natural language explanations of best moves, key variations, and strategic/tactical themes.

Compiles LaTeX source code to PDF using pdflatex. Use this skill whenever the user asks to create and compile LaTeX documents, generate PDFs from LaTeX, or compile existing LaTeX code in artifacts.

Video editing with ffmpeg including cutting, trimming, concatenating segments, and re-encoding. Use when working with video files (.mp4, .mkv, .avi) for: removing segments, joining clips, extracting portions, or any video manipulation task.

Generate beautiful HTML timeline reports from Claude Code session history files (.jsonl). Use when the user wants to view session history, create a session report, or export conversation history in a readable format. Automatically filters out system messages, tool results, and empty content to show only meaningful user instructions and assistant responses.

Creates isolated git worktree development environments with tmux sessions. Use when starting new features, bug fixes, or experiments that need isolated git context. Automatically manages branch naming, creates dedicated tmux windows.

Connect a Feishu (Lark) bot to Clawdbot via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a messaging channel, troubleshooting the Feishu bridge, or managing the bridge service (start/stop/logs). Covers bot creation on Feishu Open Platform, credential setup, bridge startup, macOS launchd auto-restart, and group chat behavior tuning.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Comprehensive toolset for interacting with LeadGenius Pro Agent APIs. Use for managing ABM campaigns, lead lifecycle, AI enrichment, target accounts, outreach sequences, and system integrations. Supports listing, creating, and updating resources via the LeadGenius RESTful API.

Create, validate, and optimize Mermaid diagrams for software documentation. Use when Claude needs to: (1) Create flowcharts, sequence diagrams, state diagrams, class diagrams, ER diagrams, or architecture diagrams, (2) Validate Mermaid syntax, (3) Review and improve diagram aesthetics, (4) Fix broken Mermaid code, or (5) Choose the right diagram type for a use case.

Generate XML sitemap and configure sitemap generation for frameworks. Handles static sitemaps, dynamic generation, and robots.txt integration.

Run full SEO validation with Lighthouse. Returns scores for Performance, Accessibility, Best Practices, SEO. Use for auditing, verifying implementation, or checking Lighthouse scores.

Optimize Core Web Vitals for Lighthouse 100 score. Handles images, fonts, preloading, and render-blocking resources. Auto-validates via PostToolUse hook. Use when optimizing performance, fixing CLS, or improving LCP/FID.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Design and scaffold Python FastAPI backends with multi-agent LangGraph workflows, FAISS vector stores, and component-based architecture. Use when: (1) Creating new FastAPI backend projects with async patterns (2) Designing LangGraph multi-agent orchestration workflows (3) Building component-based agent architectures (tools + nodes + services) (4) Implementing FAISS vector similarity search systems (5) Setting up SSE streaming endpoints for real-time updates (6) Structuring Pydantic models for API contracts (7) Creating configuration systems with environment variables and YAML

Configure Opik SDK for LLM observability. Use when setting up a new project, connecting to Opik Cloud, or configuring self-hosted Opik.

Create and run evaluations on your LLM outputs. Use when testing prompts, measuring quality, comparing models, or creating evaluation datasets.

批量翻译系统完全指南。包含架构、添加翻译源、进度追踪、语言检测、报告生成。(project)

Connect a Feishu (Lark) bot to Clawdbot via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a messaging channel, troubleshooting the Feishu bridge, or managing the bridge service (start/stop/logs). Covers bot creation on Feishu Open Platform, credential setup, bridge startup, macOS launchd auto-restart, and group chat behavior tuning.

Manipulate Markdown files surgically by section without loading entire content. Use when editing large .md files, updating specific sections, using Markdown as a lightweight database, or when asked to work with sections in a Markdown file. Commands include outline, read, write, append, empty, remove, search, concat, meta, create.

Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you’re designing a CLI spec (before implementation) or refactoring an existing CLI’s surface area for consistency, composability, and discoverability.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

fal.aiスキルに新しいモデルを追加するためのスキル

Automate interactive CLI programs with persistent sessions using pexpect-cli and pueue. Use when needing to automate programs that require interactive input/output (SSH sessions, database CLIs, vim/editors, interactive shells, or any program with prompts). Provides session management, real-time monitoring, and persistent state across multiple commands.

Enfocus PitStop Library SDK (v25.11) for PDF preflight, processing, and quality control automation. 🔹 Native SDK: "EPL_", "EPM_", "preflight", "Action List", "Preflight Profile", "Certified PDF" 🔹 Web Integration: "PitStop Library Container", "PLC", "Docker", "REST API", "cloud preflight" 🔹 Processing: "PDF 품질검사", "인쇄용 PDF", "색상 관리", "PDF 렌더링", "썸네일 생성" 🔹 Reports: "preflight report", "JSON report", "XML report", "에러/경고/수정" Use when: (1) Processing PDF with preflight profiles, (2) Creating preflight reports, (3) Web/cloud PDF processing architecture, (4) PLC Docker deployment, (5) MES integration

인쇄 산업 공통 기술 지식 베이스. 조판 계산, CTP 판수, 접지 배열, 책등/오시, 크립 보정 등 인쇄 기초 지식 제공. 🔹 조판 계산: "UP수 계산", "판걸이", "조판 효율", "자투리 배치" 🔹 CTP 계산: "CTP 몇 판?", "판수 계산", "Work&Turn" 🔹 접지 배열: "십자접지", "3단접지", "페이지 순서", "대지" 🔹 책등/오시: "책등 두께", "오시 줄 수", "표지 펼침 크기" 🔹 크립 보정: "크립 계산", "중철 보정" 🔹 용지 규격: "국전", "46전", "롤 폭", "인쇄 영역" 사용 시점: 인쇄 견적/생산 시스템 개발, 조판 최적화, 제본 계산 필요 시 확장 스킬: huni-printing-estimator, mycom-printing-estimator에서 참조

Token-Oriented Object Notation (TOON) 포맷 처리 스킬. JSON 대비 30-60% 토큰 절감하는 LLM 최적화 직렬화 포맷.