AI Skills Hub - Browse 180,000+ Agent Skills

Designs, tests, and ships production prompts using prompt-as-code workflows, templates, evaluation guidance, and optional scripts/assets. Returns a full copy/paste prompt block. Use when building AI features, improving agent performance, or standardizing system prompts.

Build and maintain Tailwind CSS systems fast without framework lock-in: tokens (CSS variables), theme + dark mode, content globs/safelist, component variant patterns, accessibility/responsive conventions, and migration hygiene.

Produces a local, best-effort dependency audit summary and remediation plan for repos with dependency manifests.

Master Git workflows for teams: clean PRs, rebasing/merging, conflict resolution, cherry-picks, safe force-push, bisect, worktrees, and recovery via reflog. Includes playbooks + safe scripts for diagnosing and fixing common Git problems.

Operate the AnyMail email CLI in E:\work\AnyMail to manage Gmail IMAP/SMTP profiles, auth (App Passwords via keyring), inbox listing/searching/reading, flags (seen/star/archive/trash), replying, sending email (with attachments), and auditing via invocation logs. Use when you need deterministic, scriptable email operations from the host (Windows) via the `anymail` CLI, including JSON/pipe workflows and troubleshooting with `anymail doctor`.

Transcribe local audio files to SRT subtitles and TXT transcripts with timestamps using faster-whisper. Use when Claude needs to convert local audio files (MP3, M4A, WAV, etc.) into text transcripts with or without timestamps, generate subtitle files from audio, or perform speech-to-text transcription. Supports multiple Whisper model sizes for accuracy/speed tradeoffs, language specification, VAD filtering, and custom output directories.

You are an expert on Clawdbot documentation. Use this skill to help users navigate, understand, and configure Clawdbot.

Query and monitor Unraid servers via the GraphQL API. Use when the user asks to 'check Unraid', 'monitor Unraid', 'Unraid API', 'get Unraid status', 'check disk temperatures', 'read Unraid logs', 'list Unraid shares', 'Unraid array status', 'Unraid containers', 'Unraid VMs', or mentions Unraid system monitoring, disk health, parity checks, or server status.

Manage documents in Paperless-ngx - search, upload, tag, and retrieve.

用于 Monarch Money 预算管理的 TypeScript 库和 CLI 工具。按日期/商家/金额搜索交易、更新分类、列出账户和预算、管理身份认证。当用户询问 Monarch Money 交易、想要分类支出、查找特定交易或想要自动化预算任务时使用。

为AI智能体设计的API优先电子邮件平台。创建和管理专用电子邮件收件箱、以编程方式发送和接收电子邮件，并通过webhook和实时事件处理基于电子邮件的工作流程。当您需要设置智能体电子邮件身份、从智能体发送电子邮件、处理传入电子邮件工作流程，或用智能体友好的基础设施替换传统的电子邮件提供商（如Gmail）时使用。

Find and search for academic papers using the paper-finder service. Use when conducting literature review, searching for related work, finding baseline papers, or looking for methodology references.

Guide for implementing Apple App Store Connect API integrations. Use when: (1) Building API clients to manage certificates, provisioning profiles, bundle IDs, or devices, (2) Implementing JWT authentication for App Store Connect, (3) Understanding API request/response patterns and error handling, (4) Working with TestFlight builds, beta groups, or app submissions, (5) Discovering available endpoints, schemas, or capabilities via the OpenAPI spec. Includes scripts for fetching and analyzing Apple's official OpenAPI specification.

Create, validate, and publish Agent Skills following the official open standard from agentskills.io. Use when (1) creating new skills for AI agents, (2) validating skill structure and metadata, (3) understanding the Agent Skills specification, (4) converting existing documentation into portable skills, or (5) ensuring cross-platform compatibility with Claude Code, Cursor, GitHub Copilot, and other tools.

Git operations with conventional commits. Use for staging, committing, pushing, PRs, merges. Auto-splits commits by type/scope. Security scans for secrets.

Perform evidence-based mobile app security reviews using OWASP MASVS. Use this skill when asked to map findings to MASVS control IDs, prioritize by MAS domains and risk, or produce practical remediation guidance tied to MASVS controls.

Comprehensive diagnostic, error-fixing, and skill recommendation tool for OpenClaw

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

Find and search for academic papers using the paper-finder service. Use when conducting literature review, searching for related work, finding baseline papers, or looking for methodology references.

高德地图服务工具包，支持地址解析、逆地址解析、路径规划、POI搜索和IP定位。当Claude需要处理以下任务时使用： (1) 将地址转换为经纬度（地址转经纬度/地理编码），(2) 将经纬度转换为地址（经纬度转地址/逆地理编码），(3) 规划路线和导航（路径规划/导航/驾车路线/步行路线/骑行路线/公交路线），(4) 搜索兴趣点如餐厅、酒店、加油站（POI搜索/查找附近的餐厅/酒店/加油站/兴趣点），(5) 通过IP地址获取位置（IP定位），(6) 计算位置之间的距离（距离计算），或任何涉及中国地图、位置服务或高德地图API的任务。当用户提到："地址"、"经纬度"、"坐标"、"导航"、"路线"、"附近"、"定位"、"高德地图"、"amap"、"查询"、"北京"、"上海"或任何中文位置/地理相关查询时触发

Automate creation of multiple audio overviews in Google NotebookLM using Playwright. Use when the user needs to generate multiple audio podcasts from web sources with different prompts or focus areas, or when batch-creating NotebookLM audio content.

Send notes and memos to flomo (浮墨笔记) via URL Scheme with automatic webhook fallback. Use when user wants to save thoughts, links, ideas, or content to their flomo inbox. Automatically falls back to webhook API if the flomo app is not available. Supports hashtags and quick capture workflows on macOS. IMPORTANT: After installing this skill, run `./scripts/configure.sh` to set up your flomo PRO webhook for the best experience.

Validate, fix, and check YAML files against schemas.

Google 캘린더 일정 조회/생성/수정/삭제. "오늘 일정", "이번 주 일정", "미팅 추가해줘" 요청에 사용. 여러 계정(work, personal) 통합 조회 지원.

{2-3 sentence overview of what this skill does and why it exists in the AMCS workflow.}

This skill should be used when users want to sync content from text.md files to gallery project index.html files. Trigger phrases include "sync markdown", "sync text.md", "update gallery content", or when users provide a gallery index.html path for content refresh.

Download paper PDFs by single or multiple DOIs using auto_paper_download with ready-to-run scripts and clear usage.

Create Claude Code hooks for automated validation, permission control, and workflow automation. Use when building event-driven scripts, enforcing code quality, or automating Claude Code interactions.

Scrape webpage content, extract metadata, download images, and prepare for Edge Delivery Services migration. Returns analysis JSON with paths, metadata, cleaned HTML, and local images.

PR 创建与版本控制流程技能。智能分析提交、生成 PR、管理版本号。支持多语言模板、自动检测版本策略。

Twitter/X tweet and comment extraction and content production guide. Use this skill when users mention "Twitter videos", "tweet opinions", "X comment videos", "netizen opinion videos", or explicitly specify this skill. Covers material collection, opinion organization, and narration script generation workflow.

Automating Zabbix monitoring operations including API interactions, metric sending, and agent data retrieval. Use when managing Zabbix hosts, users, items, templates, sending metrics to Zabbix servers, or querying Zabbix agents for monitoring data.

Extract text, tables, and form fields from PDF documents. Use when user mentions PDFs, forms, or document extraction.

Reads, creates, edits, and analyzes Excel spreadsheets with full formula support, formatting, charts, and data validation. Triggers when working with .xlsx, .xlsm, .xls, .csv, or .tsv files for data analysis, spreadsheet creation, formula-based models, or modifying existing workbooks.

Scrape webpage content, extract metadata, download images, and prepare for import/migration to AEM Edge Delivery Services. Returns analysis JSON with paths, metadata, cleaned HTML, and local images.

Reference documentation for the initramfs-architect agent. Contains kernel boot contracts, design patterns, systemd handoff requirements, and advanced feature guides. NOT for direct use - always use the initramfs-architect agent instead.

Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.

抓取Steam游戏评论，按优先级和问题类型智能分类，生成分析报告，并导入飞书多维表格。当用户需要收集、分析或管理Steam游戏评论进行团队协作时使用此技能。

A skill for performing web searches, research, and reasoning using the Perplexity API. Handles real-time web information retrieval, deep research analysis, and advanced reasoning tasks. Use when the user asks for web searches, research, or says things like "look up", "search for", "latest information", "research", or "analyze".

Creates presentation slide decks from provided content. Use when user wants slides, a deck, or a presentation. Expects research/content to be provided - does not conduct research.

Validate skills and plugins with deterministic evidence bundles and strict schema gates. Use when auditing changes or enforcing compliance. Trigger with 'run validation' or 'audit validators'.

Produces verified datasets, verified evaluation results, and a deployable contract bundle for a workflow. Use when you need provable correctness at data and evaluation boundaries. Trigger with 'verify workflow', 'validate contract', or 'run verification pipeline'.

SkillsMP技能商城搜索和管理工具。提供在 https://skillsmp.com/ 网站上搜索、查看详情、安装和更新技能的完整功能。支持关键词搜索和AI语义搜索两种模式。当用户需要：(1) 搜索特定主题的技能（如"SEO"、"视频制作"），(2) 通过自然语言描述查找相关技能（如"如何创建网络爬虫"），(3) 查看技能详细信息（版本、作者、评分、示例），(4) 一键安装发现的技能，(5) 检查已安装技能的更新，(6) 管理本地技能库时使用此技能。

Validate Nixtla skills and plugins with deterministic evidence bundles and strict schema gates. Use when auditing changes or enforcing compliance. Trigger with 'run validation' or 'audit validators'.

Vet ClawHub skills for security and utility before installation. Use when considering installing a ClawHub skill, evaluating third-party code, or assessing whether a skill adds value over existing tools.

Comprehensive diagnostic, error-fixing, and skill recommendation tool for OpenClaw

내게 할당된 Jira 이슈 조회, 마감일 알림, 대화형 코멘트 작성. 현재 사용자를 자동 감지하여 할당된 이슈 대시보드를 출력하고, 선택한 이슈에 작업 코멘트를 게시한다.

기간 기반 주간업무보고서 생성. 프로젝트 키와 기간을 입력하면 Jira에서 이슈와 코멘트를 가져와 팀별 카테고리 설정으로 마크다운 보고서를 자동 생성한다.

Guides creation of 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). Covers tool design, authentication, Docker deployment, and evaluation creation. NOT when consuming existing MCP servers (use the server directly).

Systematic methodology for debugging bugs, test failures, and unexpected behavior. Use when encountering any technical issue before proposing fixes. Covers root cause investigation, pattern analysis, hypothesis testing, and fix implementation. Use ESPECIALLY when under time pressure, "just one quick fix" seems obvious, or you've already tried multiple fixes. NOT for exploratory code reading.

A phased builder with three validation gates - smoke, contract, and integration - that generates skills using structured output templates.

Sync git worktrees with remote and main branch changes. Use to keep long-running feature branches up-to-date.

Build Mojo packages (.mojopkg files) for distribution. Use when creating distributable libraries or during packaging phase.

Fetch and inspect XiaoHongShu/小红书 favorites: saved notes (收藏) + saved boards (收藏专辑/收藏夹), and extract note details (title/desc) for summarization using Playwright + your logged-in cookies (CookieCloud supported). Use when the user asks to 查看小红书收藏/收藏专辑、最近收藏了哪些笔记、或“这条笔记讲了啥”(need text).

Fetch and inspect Zhihu collections (收藏夹) and saved items, and extract full text for saved answers/articles via Zhihu web APIs (CookieCloud supported). Use when the user asks to查看知乎收藏夹、我收藏了哪些回答/文章、或"这篇回答/文章讲了什么"(need text).

Fetch and inspect Bilibili favorites (收藏夹/收藏内容) and video transcripts (字幕/逐字稿) using your own logged-in cookies (CookieCloud supported). Use when the user asks to查看/导出 B站收藏夹、最近收藏了哪些视频、或"这个 BV/视频讲了什么"(needs transcript).

Codemagic CI/CD build monitoring and build control via the Codemagic REST API (status dashboards by environment and platform, in-progress build summaries, failure/error summaries, starting builds, and canceling builds). Use when a request mentions Codemagic builds, workflows, apps, build failures, build logs, or downloading/updating the Codemagic API v3 OpenAPI schema from the Codemagic Swagger UI.

Analyze VMR codeflow PR status for dotnet repositories. Use when investigating stale codeflow PRs, checking if fixes have flowed through the VMR pipeline, or debugging dependency update issues in PRs authored by dotnet-maestro[bot].

Validate and publish Pine Script using browser automation with Fly log correlation for debugging TradingView automation issues.

Use when: (1) testing boundaries (database, APIs, queues), (2) writing acceptance tests for user workflows, (3) setting up test fixtures with real infrastructure, (4) questions about transaction rollback or HTTP test clients. For pure unit tests, use typescript-unit-testing skill instead.

Creates 06-backlog.md as a solo-friendly build plan (30–90 min tasks) derived from 00-* docs + PRD + UI/UX + Architecture. Includes phases, epics, dependencies, acceptance criteria, and verification commands. Use after docfactory-arch or when the user asks for a backlog, task breakdown, or build plan. Do not generate code.

Creates 03-ui-ux-spec.md (IA, Expo Router route map, screen list, states, design tokens, component inventory, micro-interactions, accessibility) from 00-* docs and 02-prd.md. Use after docfactory-prd or when the user asks for a UI spec, UX design, screens, or a design system. Do not generate code.

Creates 04-tech-architecture.md (stack decisions, data layer, Supabase schema + RLS approach, integrations, folder tree, deployment, performance, security) from 00-* docs + PRD + UI/UX spec. Use after docfactory-uiux or when the user asks for technical architecture, a tech stack, or a data model. Do not generate code.

Creates the Source-of-Truth docs for a new mobile app idea (00-project-brief.md, 00-decisions.md, 00-glossary.md) from a short Idea Capsule. Use at the start of every new idea, before PRD/UX/architecture, or when the user asks for initial docs, a project brief, or to start a new idea. Do not do market research, TAM/SAM/SOM, or generate code.

Creates 02-prd.md (vision, personas, JTBD, MVP scope, user stories, core loop, monetization, metrics, ASO) from 00-* docs and 01-market-research.md. Use after docfactory-init + docfactory-market or when the user asks for a PRD, product requirements, or user stories. Do not do coding.

Drafts 01-market-research.md (competitors, user complaints, gap analysis, wedge hypothesis) for a new app idea using credible sources and citations. Use after docfactory-init or when the user asks for market research, competitor analysis, or gap analysis. Do not invent TAM/SAM/SOM or download estimates.

Generate images using this repo’s image generation CLI (located under `skills/public/image-gen/scripts/image-gen/generate.mjs`). Use when asked to create/iterate on images (PNG/JPG/WEBP/GIF), choose aspect ratios, and troubleshoot `.env` / `GEMINI_API_KEY` / CLI usage.

Generate pixel art sprites, animations, and tilesets using the PixelLab v2 API (Pro endpoints). This skill wraps all endpoints via a helper script that handles authentication, image encoding, and file I/O.

Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.

Testing guide using Vitest. Use when writing tests (.test.ts, .test.tsx), fixing failing tests, improving test coverage, or debugging test issues. Triggers on test creation, test debugging, mock setup, or test-related questions.

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.

Analyze images using OpenAI's Vision API. Use bash command to execute the vision script like 'bash <base_dir>/scripts/vision.sh <image> <question>'. Can understand image content, objects, text, colors, and answer questions about images.

Call LinkAI applications and workflows. Use bash command to execute like 'bash <base_dir>/scripts/call.sh <app_code> <question>'.

Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.

Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation.

Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.

Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

List, switch, and configure Railway projects. Use when user wants to list all projects, switch projects, rename a project, enable/disable PR deploys, make a project public/private, or modify project settings.

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.

Claude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets), and refactor existing Skills for clarity, activation reliability, and quality gates.

Async operations and background tasks in GPUI. Use when working with async, spawn, background tasks, or concurrent operations. Essential for handling async I/O, long-running computations, and coordinating between foreground UI updates and background work.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

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.

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers environment. Requires CDP_SECRET env var and cdpUrl configured in browser.profiles.

Interactive Archon integration for knowledge base and project management via REST API. On first use, asks for Archon host URL. Use when searching documentation, managing projects/tasks, or querying indexed knowledge. Provides RAG-powered semantic search, website crawling, document upload, hierarchical project/task management, and document versioning. Always try Archon first for external documentation and knowledge retrieval before using other sources.

This skill should be used when developing, debugging, or maintaining Positron Notebooks - the React-based feature-flagged notebook editor. Load this skill when tasks involve notebook cells, execution, selection state, context keys, or notebook editor features.