AI Skills Hub - Browse 180,000+ Agent Skills

Look up contacts from macOS Contacts.app. Use when resolving phone numbers to names, finding contact info, or searching the address book.

AI-powered web application QA automation using accessibility-tree based testing. Smoke tests, test suites, and PDF reports.

LinkedIn inbox management with scheduled scanning, auto-draft responses following user's communication style, and approval workflows. Use when monitoring LinkedIn messages, drafting replies, managing inbox during off-hours, or setting up morning ping summaries of LinkedIn activity.

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

Create professional PowerPoint presentations from outlines, data sources, or AI-generated content. Supports custom templates, style presets, charts/tables from data, and AI-generated images. Use when asked to create slides, pitch decks, reports, or presentations.

Transcribe YouTube videos and local audio/video files with speaker diarization. Use when user asks to transcribe a YouTube URL, podcast, video, or audio file. Outputs clean speaker-labeled transcripts ready for LLM analysis.

Manage Tailscale tailnet via CLI and API. Use when the user asks to "check tailscale status", "list tailscale devices", "ping a device", "send file via tailscale", "tailscale funnel", "create auth key", "check who's online", or mentions Tailscale network management.

Create and manage Product Requirements Documents (PRDs) for feature planning.

High-quality voice synthesis with 18 personas, 32 languages, sound effects, batch processing, and voice design using ElevenLabs API.

Professional stock price tracking, fundamental analysis, and financial reporting tool. Supports global markets (US, KR, etc.), Crypto, and Forex with real-time data. (1) Real-time quotes, (2) Valuation metrics (PE, EPS, ROE), (3) Earnings calendar and consensus, (4) High-quality Candlestick & Line charts with technical indicators (MA5/20/60).

Automate common Word/WPS document operations on Windows via COM (read text, replace, insert, headings, headers/footers, page breaks, merge, split, export to PDF/TXT, add/replace images). Use for single-document actions (no batch).

Google Calendar integration for viewing, creating, and managing calendar events. Use when the user asks about their schedule, wants to add/edit/delete events, check availability, or needs a morning brief. Supports natural language like "What's on my calendar tomorrow?" or "Schedule lunch with Alex at noon Friday." Free tier provides read access; Pro tier ($12) adds create/edit/delete and morning briefs.

Search the web or X/Twitter using xAI Grok server-side tools (web_search, x_search) via the xAI Responses API. Use when you need tweets/threads/users from X, want Grok as an alternative to Brave, or you need structured JSON + citations.

Access and manage NocoDB databases, tables, and records via REST API. Use when the user wants to view bases, list tables, inspect column schemas, query or filter row data, or insert new records into a self-hosted NocoDB instance. Also use for spreadsheet-style database lookups and data entry.

This skill should be used when the user asks to "design REST APIs", "optimize database queries", "implement authentication", "build microservices", "review backend code", "set up GraphQL", "handle database migrations", or "load test APIs". Use for Node.js/Express/Fastify development, PostgreSQL optimization, API security, and backend architecture patterns.

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.

Cloudflare CLI - manage DNS records, purge cache, and control Workers routes.

Swap tokens on Solana via Jupiter aggregator and check wallet balances. Use when user wants to swap tokens, check SOL/token balance, or get swap quotes.

Manage your YouTube account from the command line. Complete CLI for YouTube Data API v3 - list/search videos, upload, manage playlists, and more.

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.

Complete guide for setting up worktree development environment and testing Odoo addons

Linear issues, comments, and webhooks. Use Linear webhooks to trigger the agent on every comment, issue assignment, and other events; use the Linear API or MCP for queries and updates.

End-to-end testing skill for web applications using agent-browser CLI. Trigger terms: e2e, end-to-end, playwright, test, testing, UI testing, functional testing, integration testing, responsive, mobile testing.

When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," or "CTA copy." Trigger terms: copywriting, marketing copy, landing page copy, headline, CTA, write copy, rewrite copy, page copy.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks. Trigger terms: docx, word document, create document, edit document, tracked changes, document formatting.

Use Proton Bridge's local IMAP/SMTP interface to read, organize, and send Proton Mail from scripts or email clients. Trigger terms: proton bridge, proton mail bridge, IMAP, SMTP, local email management, archive, spam, reply, inbox, mailbox details.

Deep-dive into specific candidates or search candidates by criteria.

Parse Tally.so CSV export and download/extract PDF resumes into candidate JSON files.

Direct Farcaster control: check mentions, cast anywhere, post to channels. Independent of webhooks.

Post to Twitter/X without API keys. Cookie-based auth + Puppeteer headless browser automation. Use for trade announcements, alpha signals, or any Farcaster updates you want to cross-post to X.

Design system skill for UI/UX workflow integration with spec-kit. Use when the user asks to "create prototype", "design UI", "generate HTML prototype", "audit design", "check design vs spec", "create Figma mapping", "map Figma pages", "verify design integration", "check design in plan", "check design in tasks", or mentions spec-to-implementation design workflow, UI/UX design process, or Figma integration.

This codebase uses a multi-layered testing strategy with Vitest for unit tests and Playwright for integration, API, and E2E tests.

Find gaps, weaknesses, and areas for improvement. Use to stress-test ideas, plans, or implementations.

Improve code structure without changing behavior. Use to reduce complexity, improve readability, or prepare for new features.

Create product requirements documents. Use when defining features, projects, or product changes.

Pull structured data from unstructured content. Use to extract entities, relationships, or data from text, documents, or logs.

Decompose a task into actionable steps with risks and assumptions. Use when starting any non-trivial work.

Quality check any artifact against criteria. Use to validate code, documents, plans, or any work product.

Review code changes for quality, correctness, and maintainability. Use when reviewing PRs, commits, or code snippets.

Execute TSpec test cases and suites against API endpoints and report results. This skill runs `.tcase` test files and `.tsuite` suite files, validates responses against assertions, and provides detailed pass/fail reporting in text or JSON format. Suites support lifecycle hooks (setup/teardown/before_each/after_each) with proper execution order.

Validate `.tcase` and `.tsuite` files for schema correctness without executing any tests. This skill checks YAML syntax, required fields, protocol block structure, assertion formats, and suite configuration. Use it for pre-commit hooks, CI/CD validation stages, and catching errors before test execution.

Parse and display TSpec test case and suite information without executing any requests. This skill resolves variables, expands templates, and shows the final test configuration. Use it for debugging variable substitution, understanding template inheritance, inspecting request payloads, and exploring suite structure before actual execution.

系统化的数据库设计方法,涵盖建模、范式化、索引优化和查询性能调优。

This pipeline is centered on `edgar-analyzer` and the EDGAR data sources. The core loop is: configure credentials, create a project with examples, analyze patterns, generate code, run extraction, and export reports.

Phoenix operations and deployment: releases, runtime configuration, clustering, libcluster, telemetry/logging, secrets, assets, background jobs, and production hardening on the BEAM.

When multiple unrelated failures occur (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

Datadog is a SaaS observability platform providing unified monitoring across infrastructure, applications, logs, and user experience. It offers AI-powered anomaly detection, 1000+ integrations, and OpenTelemetry compatibility.

Ecto is the data layer for Phoenix applications: schemas, changesets, queries, migrations, and transactions. Good Ecto practice keeps domain logic in contexts, enforces constraints in the database, and uses transactions for multi-step workflows.

Claiming work is complete without verification is dishonesty, not efficiency.

Apify platform operations including builds, runs, storage, and deployment. Use for managing Actor builds, monitoring runs, accessing datasets/key-value stores, and diagnosing errors on the Apify platform.

Locate places using flexible query formats - free-form search or structured address components. Returns coordinates, addresses, and optional street-level photos. Use for geocoding addresses or finding specific named places.

Plan multi-waypoint journeys with route optimization, feasibility analysis, and time budget constraints. Use when you need to plan trips with multiple stops or check if an itinerary is achievable.

Fetch transcripts from YouTube videos. Use when the user shares a YouTube URL, references a video, wants to know what someone said in a video, or needs video content as text.

This skill should be used when the user needs to read, write, extract, or analyze content from Microsoft Word (.docx) files. It provides Python scripts to convert docx files to plain text or Markdown format, and create new Word documents from JSON or Markdown content.

How the Zig-backed instance graph works (GraphView/NodeReference/EdgeReference), the real Python API surface, and the invariants around allocation, attributes, and cleanup.

How the Zig S-expression engine and typed KiCad models work, how they are exposed to Python (pyzig_sexp), and the invariants around parsing, formatting, and freeing.

Design software concepts using Daniel Jackson's methodology. This skill should be used when analyzing existing applications to identify concepts, designing new concepts for features or systems, defining concept structure (purpose, operational principles, state, actions), or composing multiple concepts together. Handles queries like "design a concept for X", "what concepts does this app have", "help me model this feature as a concept".

Create and apply OpenAPI Overlay Specification documents. Use when working with OpenAPI/Swagger files and needing to apply repeatable transformations such as adding metadata, filtering endpoints, translating descriptions, or modifying API specifications without editing the source.

> Debug non-functional M365 Copilot declarative agents.

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

This skill should be used when the user asks to "create a Home Assistant add-on", "wrap a Docker image for HA", "create an HA addon", "scaffold an add-on", "convert docker-compose to add-on", "analyze for add-on creation", or mentions Home Assistant add-ons, Supervisor add-ons, or wrapping applications for Home Assistant.

Analyze SPX mean reversion for put-selling decisions. Use when the user wants to check market conditions, run mean reversion analysis, generate trading signals (GREEN_LIGHT/WAIT/RED_FLAG), or analyze SPX/VIX relationship for options trading.

Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) using Python (`openpyxl`, `pandas`), especially when formulas, references, and formatting need to be preserved and verified.

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

Converts plain text files into HTML fragments compatible with WordPress Custom HTML blocks.

Extracts lessons learned from Claude Code session logs into organized markdown and JSONL files

Stage all changes and commit with a descriptive message. Use when the user asks to commit, save changes, or says "/commit".

Create and manage Product Requirements Documents (PRDs) for feature planning.

Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features

Hybrid memory strategy combining OpenClaw's built-in vector memory with Graphiti temporal knowledge graph. Use when you need to recall past context, answer temporal questions ("when did X happen?"), or search memory files. Provides decision framework for when to use memory_search vs Graphiti.

Autonomous block mining for MegaCube. Use when user asks to mine, automate, run the RRS Terminal, or set up autonomous mining.

This skill should be used when the user asks to "validate requirements", "review requirements quality", "check requirements completeness", "verify traceability", "check INVEST compliance", "validate user stories", "requirements health check", "quality gate check", or when running /re:review validation.

Guide for creating MCP (Model Context Protocol) servers to extend Claude's capabilities with external services. Use when building custom integrations for Guitar CRM like Spotify enrichment, calendar sync, or payment processing.

Guide for creating new Claude Code skills to extend capabilities with specialized workflows. Use when creating custom skills for Guitar CRM like lesson-plan-generator, student-report, or practice-schedule.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Search the web or X/Twitter using xAI Grok server-side tools (web_search, x_search) via the xAI Responses API. Use when you need tweets/threads/users from X, want Grok as an alternative to Brave, or you need structured JSON + citations.

Create a structured school essay outline (plan) from a topic and target word count when the user asks for an essay plan/outline or “план сочинения”.

name: "infra-script-gcs-sync"

name: "sanctuary-api-sos"

name: "route-llm-through-vertex-gemini"

name: "rag-ui-source-display"

name: "role-model-table-schema"

name: "admin-table-prompts"

name: "a11y-check"

name: "activity-log-api-reaction"

Read text from images (news screenshots, articles) and broadcast via TTS.

Feishu (Lark) integration for OpenClaw. Create, read, and manage documents, folders, and app permissions. Actions: create_doc, read_doc, write_doc, append_doc, update_block, delete_block, list_blocks, list_folders, get_scopes. Topics: feishu, lark, document, folder, collaboration, team.

Centralized discovery and quality scoring for the exploding MCP (Model Context Protocol) ecosystem.

Align script text to audio with karaoke-style word timestamps using Qwen3-ForcedAligner + jieba

Text-guided audio source separation using SAM-Audio via mlx-audio

Smart video chunking and MLX-accelerated transcription for long-form content.

Download images from URLs (like Pexels, Unsplash), resize them, and convert to WebP format. Use when the user wants to optimize stock images, download and convert images to WebP, or prepare images for web use.

Contribute to and reference Clawpedia, the collaborative knowledge base for AI agents

Create complex directed/undirected graphs with precise layout control. Best for dependency trees, org charts, network topologies, and module relationships. Use when you need fine-grained edge routing or hierarchical layouts with many levels. NOT for simple flowcharts (use mermaid) or data charts (use vega).

A tool to create a Lightning Network wallet using Cashu and expose it via Nostr Wallet Connect (NWC). Use this to receive zaps or pay invoices.

Switch between Ollama models at runtime - GLM for smart text, Qwen3-VL for vision.

> Progressive disclosure hub for AI agents working on this MCP server.

This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation request.