AI Skills Hub - Browse 180,000+ Agent Skills

Professional static type checking for Python with mypy (v1.19.1). Use when working with Python type hints, type annotations, or integrating mypy into codebases for: (1) Adding type annotations to Python code, (2) Configuring mypy (mypy.ini, pyproject.toml, setup.cfg), (3) Resolving mypy errors and type checking issues, (4) Using advanced type patterns (Generics, Protocols, TypedDict), (5) Running mypy in CI/CD or development workflows, (6) Creating or working with stub files, (7) Migrating existing codebases to typed Python, or (8) Any mypy-related development task.

Use PROACTIVELY when setting up end-to-end testing, debugging UI issues, creating visual regression suites, or automating browser testing. Uses Playwright with LLM-powered visual analysis, screenshot capture, and fix recommendations. Zero-setup for React, Next.js, Vue, Node.js, and static sites. Not for unit testing, API-only testing, or mobile native apps.

Use PROACTIVELY when validating Claude Code skills before sharing or public release. Automated testing framework using multiple isolation environments (git worktree, Docker containers, VMs) to catch environment-specific bugs, hidden dependencies, and cleanup issues. Includes production-ready test templates and risk-based mode auto-detection. Not for functional testing of skill logic or non-skill code.

Use PROACTIVELY when setting up OpenTelemetry monitoring for Claude Code usage tracking, cost analysis, or productivity metrics. Provides local PoC mode (full Docker stack with Grafana) and enterprise mode (centralized infrastructure). Configures telemetry collection, imports dashboards, and verifies data flow. Not for non-Claude telemetry or custom metric definitions.

Use PROACTIVELY when searching past Claude Code conversations, analyzing development patterns, or generating activity reports. Automatically processes conversation history from the project, enables RAG-powered semantic search, and generates insight reports with pattern detection. Provides optional dashboard for visualization. Not for real-time analysis or cross-project searches.

Guide for creating specialized AI agents (subagents). Use when users want to create a new agent, define agent configurations, or need guidance on agent architecture. Triggers: "create an agent", "new agent", "make a subagent", "agent template"

복잡한 작업을 체계적인 단계로 나누어 처리하는 커스텀 워크플로우 스킬을 생성합니다. 워크플로우 생성, 새 워크플로우 만들기, 스킬 만들기, 작업 흐름 설계, 단계별 프로세스 설계, 반복 작업 자동화 워크플로우, 커스텀 워크플로우 개발 시 사용하세요.

Create serverless endpoint templates and endpoints on RunPod.io. Supports Python/Node.js runtimes, GPU selection (3090, A100, etc.), and idempotent configuration. Use this skill when a user wants to set up a new serverless endpoint or template on RunPod.

将 vless+reality 等新协议配置转换为带 ACL4SSR Full NoAuto 规则的配置文件，支持分组+分流，可直接上传 OpenClash 使用。触发词：合并 OpenClash、转换订阅、Clash 配置

Semantic search over workspace files using Telnyx Storage + AI embeddings. Index your memory, knowledge, and skills for natural language retrieval.

生成多语言双语字幕并烧录到视频。支持中英、中日、日英等语言组合。当用户需要制作双语字幕视频时使用。

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

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.

Global Exception Filters and standard error formats.

View plans dashboard with progress tracking and timeline visualization. Use for kanban boards, plan status overview, phase progress, milestone tracking, project visibility.

Fetches aggregated trace metrics (token usage, latency, trace counts, quality evaluations) from MLflow tracking servers. Triggers on requests to show metrics, analyze token usage, view LLM costs, check usage trends, or query trace statistics.

Use when setting up, installing, configuring, deploying, or troubleshooting the content-collection Telegram bot that saves URLs and text to Notion with AI categorization

Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.

Preview and analyze EPUB rendering on Kindle devices using Kindle Previewer 3 and Gemini vision API. Use when the user wants to test Kindle compatibility, check e-reader rendering, or verify the book displays correctly on Kindle devices. Triggers on mentions of Kindle preview, e-reader testing, or Kindle compatibility.

Retrieve Azure DevOps build information for GitHub Pull Requests, including build IDs, stage status, failed jobs, and Helix console logs for any Helix-based test failures.

Create and manage Qdrant collections for textbook RAG pipelines. Use when setting up vector databases, changing embedding models, adding payload indexes, debugging retrieval issues, or managing dev/staging/prod collections. Handles vector configuration, payload schemas, indexes, safe lifecycle operations, and validation.

Store, verify, and manage AI data on the Ethereum blockchain (Base network) using the ERCData standard. Use when an agent needs to store data fingerprints on-chain, verify data integrity, create audit trails, manage access control for private data, or interact with the ERCData smart contract. Supports public and private storage, EIP-712 verification, snapshots, and batch operations.

Read/write public Twitter/X posts via Apify. Do not call a tool named apify-twitter; use exec to run: node tools/apify-twitter/cli.js read|write ...

Operate the /slider repo end-to-end: list/create/update/delete slide styles (styles/*.toml), manage per-style layout tables under [layouts.*], scaffold specs (specs/*.md), and render per-slide prompts (prompts/generated/*) using the bundled slider_ops script and/or the slider CLI. Use when a user asks to create/manage styles or layouts, generate prompts from a Markdown SPEC, or otherwise run the slider workflow so Codex should execute commands/edits instead of the user.

Use when fetching dbt documentation, looking up dbt features, or answering questions about dbt Cloud, dbt Core, or the dbt Semantic Layer

Utility tools for MicroSim management including quality validation, screenshot capture, icon management, and index page generation. Routes to the appropriate utility based on the task needed.

Testing Apex triggers and flows with bulk data operations.

Comprehensive Agentforce testing skill with test execution, coverage analysis, and agentic fix loops. Run agent tests via sf CLI, analyze topic/action coverage, generate test specs, and automatically fix failing agents with 100-point scoring.

Interactive wizard for creating Claude Code skills. Use when scaffolding new skills, validating skill structure, managing dependencies, or editing skill configuration files.

Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.

Generates strategic customer segment definitions with observable filters, segment sizing, and pain intensity scores. Use when defining target customers, building Canvas section 04, translating market research to segments, or when user mentions "segments", "ICP", "target market", or "who to sell to".

Sync root README.md with current skills inventory from skills/ directory

The `count_equations_in_file()` function in `book-metrics.py` was significantly over-counting LaTeX equations. For example, a signal processing textbook showed 2,421 equations when the actual count was much lower.

Create a comprehensive Claude skill that generates or updates README.md files in GitHub repositories, following all GitHub best practices and including 12 specific steps:

Guide for creating effective skills

Replace arbitrary timeouts with condition polling for reliable async tests

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

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.

Analyze large documents (100x larger than LLM context) using recursive language model with Nucleus DSL. Use when searching, filtering, aggregating text logs, reports, or structured text data without loading everything into context.

Intelligent interaction with Feishu/Lark documents via Feishu MCP. Use when analyzing, extracting content from, or querying Feishu documents (.docx, /wiki/ URLs) including text extraction, markdown conversion, table data analysis, and document search. Requires Feishu MCP server configured.

Run Octomark against the CommonMark spec tests to check for compliance.

iOS build, test, and simulator verification expert. Builds Xcode projects, runs tests, manages iOS Simulators, captures screenshots, parses xcresult bundles, and diagnoses build failures. Use when building iOS apps from the command line, running on simulators, extracting test results, or troubleshooting xcodebuild errors.

Autonomous QA verification loop for macOS applications. Builds the app, screenshots every screen, compares against design mocks using vision, verifies spec compliance, and loops until the app matches or reports remaining gaps. Use when validating a macOS app against its specification and design mocks before release. Triggers on "verify app against mocks", "QA loop", "check app matches spec", "validate macOS app".

iOS app code signing, provisioning, and distribution expert. Guides developers through certificate and provisioning profile management, TestFlight distribution, App Store submission, Ad Hoc builds, and CI/CD automation with GitHub Actions, Xcode Cloud, and Fastlane. Use when preparing an iOS app for release, debugging signing or provisioning errors, setting up TestFlight pipelines, or troubleshooting distribution failures.

Suite of Sanskrit learning skills covering verse analysis, grammar, vocabulary, literature, and devotional hymns. Use as an entry point when users ask general Sanskrit questions or need guidance on which specific skill to use.

Sanskrit devotional hymns and prayers covering major stotras by deity (Vishnu, Shiva, Devi, Ganesha), stotra types (ashtakam, sahasranama, kavacham), famous composers (Shankaracharya, Vedanta Desika), and recitation guidance. Use when explaining stotras, providing hymn texts, discussing devotional poetry, or answering questions about Hindu prayers and their significance.

Shared Sanskrit resources including Devanagari script guide, transliteration systems, terminology glossary, online resources, and Python utility scripts. Use for script conversion, general Sanskrit reference, or when other skills need common resources.

Sanskrit grammar analysis including sandhi (euphonic combinations), samasa (compounds), vibhakti (case declensions), dhatu (verbal roots), pratyaya (suffixes), and lakara (tenses/moods). Use when explaining Sanskrit grammar rules, breaking down word formations, analyzing declensions or conjugations, identifying compound types, or teaching Paninian grammar concepts.

Sanskrit literature guide for text-level discussions — plot summaries, author biographies, literary genres, kavya theory (rasa, dhvani, alankara schools). Use when asking about poets (Kalidasa, Bharavi), texts as wholes (what is Meghaduta about?), literary history, or aesthetic theory. For analyzing a specific verse, use sloka instead.

Sanskrit vocabulary and lexicon skill covering word meanings, synonyms (paryaya), etymology (nirukta), gender, and technical terminology. Based on Amarakosha and traditional lexicography. Use when looking up Sanskrit word meanings, finding synonyms, explaining word derivations, identifying gender of nouns, or exploring vocabulary by category (gods, nature, body parts, etc.).

Detailed analysis of individual Sanskrit verses (shlokas) including anvaya (prose order), padachheda (word-by-word breakdown), chandas (meter), alankara (figures of speech), traditional commentary, and meaning. Use when a user provides a specific verse to analyze or asks to explain a particular shloka. For text-level discussions (author info, plot summaries, literary history), use sahitya instead.

Manage the Namastex Juice router (router-for.me / CLIProxyAPI) and its OpenAI/Anthropic-compatible inference endpoints. Use when probing which endpoints work (/v1/models, /v1/chat/completions, /v1/responses, /v1/messages), inspecting usage and runtime config via the Management API (/v0/management/*), managing auth files, rotating keys, changing router config.yaml safely, or wiring OpenClaw model providers/defaults to use Juice and/or google-antigravity Claude Opus.

当用户需要开发需求、创建技术方案/设计文档、规划任务、或遵循规范化开发流程时使用此技能。触发关键词包括"开发需求"、"技术方案"、"设计文档"、"任务规划"、"TAPD链接"、"需求开发流程"、"执行需求"等。引导用户完成4阶段标准化开发流程（准备→设计→规划→执行），包含自动化质量检查、人工审批门禁和wiki文档更新。

The social network for AI agents. Post, comment, upvote, and search on Moltbook. Use when Agent needs to Post updates or thoughts to Moltbook, Check feed/notifications, Comment on or vote for posts, Search for content/users/communities, Register a new agent.

Full local Solana toolkit (RPC-first) for pump.fun deploy + bonding trades, PumpSwap, Raydium AMM v4, atomic SOL fee cuts, creator fee claim, autostrategy automation, and optional Moltium HTTP API (register/posts/agents/orders/release notes).

Query Garmin Connect for activities, health metrics, training status, and device info.

Render web pages with JavaScript using Playwright for sites that need browser rendering or have issues with simple HTTP fetching.

This skill should be used when the user asks to "create an update", "announce a feature", "write release notes", "add to the updates modal", "create an announcement", or mentions "/updates". Generates polished markdown announcements in /public/updates/ for the app's updates modal.

Provides optional NotebookLM integration for the Flatline Protocol, enabling external knowledge retrieval from curated AI-powered notebooks.

Manage multi-session AI agent workflows using klondike CLI. Use when working on klondike-managed projects (those with .klondike/ directory), when starting/ending coding sessions, tracking features through lifecycle, or maintaining coherence across context window resets. Triggers on session management, feature tracking, progress handoffs, and verification workflows.

Expert skill for yt-dlp (youtube-dl fork) - a powerful command-line media downloader supporting 1000+ websites. Use for: downloading videos/audio from YouTube, Bilibili, Twitch, Twitter, etc; format selection and conversion; subtitle downloading and embedding; playlist handling; metadata embedding; cookies/authentication; SponsorBlock integration; custom extractor development; understanding yt-dlp codebase architecture. Examples: "download YouTube video 4K", "extract audio mp3", "yt-dlp best format", "embed subtitles", "Bilibili downloader", "sponsorblock skip ads", "cookies authentication", "write custom extractor", "XiaoHongShu download complete package"

Python testing with pytest using uv package manager. Use when: (1) Running Python tests, (2) Writing test files or test functions, (3) Setting up fixtures, (4) Parametrizing tests, (5) Generating coverage reports, (6) Testing FastAPI applications, (7) Debugging test failures, (8) Configuring pytest options. Triggers: "run tests", "write tests", "test coverage", "pytest", "unit test", "integration test", "test FastAPI".

Use SAP-RPT-1-OSS open source tabular foundation model for predictive analytics on SAP business data. Handles classification and regression tasks including customer churn prediction, delivery delay forecasting, payment default risk, demand planning, and financial anomaly detection. Use when asked to predict, forecast, classify, or analyze patterns in SAP tabular data exports (CSV/DataFrame). Runs locally via Hugging Face model.

Production-grade skill for creating comprehensive user guides, tutorials, step-by-step instructions, troubleshooting guides, and FAQ sections with quality metrics and validation.

Manage research documentation in workspace platforms. Structures research findings, sources, and analysis in organized research databases.

Systematically debug and diagnose issues methodically. Uses diagnostic techniques to identify root causes and implement fixes.

Secure Gmail access via IMAP/SMTP with 1Password credential storage. Supports listing, reading, searching, sending, and replying to emails with proper threading and attachments.

This skill should be used when the user asks about "coordinate coding agents", "orchestrate agent team", "manage multiple agents", "vibekanban workflow", "task delegation to agents", "agent swarm coordination", "parallel agent execution", "chief of staff mode", "cos mode", "you're my cos", "your my cos", "act as cos", "be my cos", "you are my chief of staff", "create tasks for agents", "dispatch agents", or needs guidance on coordinating autonomous coding agents, task breakdown strategies, or multi-agent workflow patterns.

Preprocess training images to extract DINOv2 features and depth maps

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.

Generate and maintain citation-backed repository wikis as MkDocs-compatible Markdown. Creates baseline docs, detects changes, and incrementally updates only affected pages with file path and line number citations.

Extract and display the full verbatim transcript from a Granola meeting. Searches synced meeting files by partial title, then fetches the complete transcript from Granola's local cache.

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.

Create and refine Codex skills (folders containing `SKILL.md`). Use when you need help naming a skill, writing effective `name`/`description`, structuring the on-disk instructions, or adding scripts/references/assets for repeatable workflows.

This skill should be used when the user wants to download or retrieve a file from the CRM database and save it to the filesystem. Triggers on requests like "download the contract from CRM", "save the database file to disk", "get the PDF from the database", or "retrieve the attachment from CRM". Uses the bel-crm-db skill for schema knowledge.

This skill should be used when the user wants to view, display, or show a file stored in the CRM database. This is an orchestration skill that combines downloading from the database and opening with the OS default application. Triggers on requests like "show me the contract from CRM", "display the image from the database", "view the PDF for company X", or "open the attachment from the database".

Search arXiv preprint repository for papers in electronic engineering, embedded systems, computer science, physics, mathematics, and related fields.

Hexo Butterfly 主题配置与使用指南，包括主题安装、页面配置、主题配置、标签外挂、FAQ、进阶教程

Python nb_log 日志库官方文档，配置高性能日志记录，包括多handler支持、彩色控制台、日志文件切割等

Search Signal Desktop message history on macOS with sub-second query times. Queries the encrypted SQLite database directly without export overhead.

Search Apple Mail messages on macOS via direct SQLite queries. Sub-second search across all configured mail accounts without launching Mail.app.

Delegate diagram creation to GitHub Copilot CLI with drawio MCP. Use on 'create diagram', 'architecture diagram', 'delegate drawio'. Runs as subprocess - no MCP required in current session.

Chrome debugging and inspection via local CDP Docker container

Frontend debugging using browser automation with logged-in sessions, DOM inspection, console access, and network monitoring. Use when debugging UI issues, investigating browser errors, testing user workflows, or analyzing frontend behavior in authenticated contexts. Supports Claude-in-Chrome, Playwright, Chrome DevTools, and agent-browser tools.

Manage OmniFocus projects and tasks programmatically. This skill should be used when creating, reading, updating, or listing OmniFocus tasks and projects. Supports all OmniFocus versions through intelligent automation method detection (Omni Automation → AppleScript → SQLite read-only fallback). Use for task management workflows, project queries, task completion tracking, and OmniFocus data operations.

Expert guide for creating OpenCode skills. Use when: (1) Creating new skills with scripts and resources, (2) Learning skill design patterns, (3) Validating existing skills, (4) Choosing the right skill archetype.

Interact with Jira and Confluence via REST API - search, create, update issues and pages

Convert Word documents (.docx) to LaTeX format with full support for OMML mathematical formulas, images, tables, and text formatting. Use when the user wants to convert a Word document to LaTeX, particularly documents containing mathematical equations, formulas, or scientific content.

Emacs 키바인딩을 검사하고 분석합니다. 키 충돌 확인, 특정 키에 바인딩된 명령 찾기, 명령에 할당된 키 검색에 사용합니다. "키바인딩", "키맵", "단축키", "keybind", "충돌" 등의 키워드에 활성화됩니다.

Browser automation via executable Puppeteer scripts. All scripts output JSON for easy parsing.

Use for Android development tasks when simulators, AVDs, app testing, or device automation are mentioned. Handles simulator lifecycle, APK management, UI testing, and ADB commands.

Validate STIX 2.1 JSON files and bundles against the STIX specification. Use when validating threat intelligence data, checking STIX bundle integrity before ingestion, verifying indicator/malware/attack-pattern objects have required fields, or bulk-validating directories of STIX files. Provides detailed error reports showing which objects failed and why.

Manage complete module lifecycle - install, uninstall, reset, destroy

Migrate codebase from try/catch or Promise-based error handling to better-result. Use when adopting Result types, converting thrown exceptions to typed errors, or refactoring existing error handling to railway-oriented programming.

Creates GitHub pull requests with comprehensive descriptions by analyzing git history and code changes

Creates or updates PLAN.md based on session - auto-detects create vs update mode

Query weather via QWeather Enterprise API with automatic JWT auth + geo resolution, and Open-Meteo fallback for current conditions.

Landing page component registry integration for searching, browsing, and pulling pre-built React/TypeScript components from the monet MCP server. Use this skill when users want to (1) search for UI components (hero sections, pricing tables, testimonials, etc.), (2) pull/add components to their project, (3) browse available component categories, (4) get component details or code, or (5) explore the component registry statistics.

Interactive command-line tool for Atlassian Jira. This skill should be used when users want to interact with Jira issues, epics, sprints, or when they mention Jira workflows, issue management, or need help with jira-cli commands and workflows.

Kubernetes cluster operations on minikube including observability (Grafana, Prometheus, Alertmanager, Loki, Tempo), debugging (kubectl debug, ephemeral containers), and cluster management (ArgoCD). Use when working with cluster/manifests/, Kubernetes workloads, pods, deployments, operators, controllers, or cluster components.