AI Skills Hub - Browse 180,000+ Agent Skills

Azure Monitor Ingestion SDK for Python. Use for sending custom logs to Log Analytics workspace via Logs Ingestion API. Triggers: "azure-monitor-ingestion", "LogsIngestionClient", "custom logs", "DCR", "data collection rule", "Log Analytics".

Azure AI Projects SDK for Java. High-level SDK for Azure AI Foundry project management including connections, datasets, indexes, and evaluations. Triggers: "AIProjectClient java", "azure ai projects java", "Foundry project java", "ConnectionsClient", "DatasetsClient", "IndexesClient".

Azure Monitor Query SDK for Python. Use for querying Log Analytics workspaces and Azure Monitor metrics. Triggers: "azure-monitor-query", "LogsQueryClient", "MetricsQueryClient", "Log Analytics", "Kusto queries", "Azure metrics".

Azure Tables SDK for Python (Storage and Cosmos DB). Use for NoSQL key-value storage, entity CRUD, and batch operations. Triggers: "table storage", "TableServiceClient", "TableClient", "entities", "PartitionKey", "RowKey".

Azure Speech to Text REST API for short audio (Python). Use for simple speech recognition of audio files up to 60 seconds without the Speech SDK. Triggers: "speech to text REST", "short audio transcription", "speech recognition REST API", "STT REST", "recognize speech REST". DO NOT USE FOR: Long audio (>60 seconds), real-time streaming, batch transcription, custom speech models, speech translation. Use Speech SDK or Batch Transcription API instead.

Reference guide for Agentica multi-agent infrastructure APIs

Analyze Maestro sessions via Braintrust

Query the memory system for relevant learnings from past sessions.

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

Updates the 'Organiser' column in 'Event_Master' sheet to use a dropdown validation from the 'Organisers' sheet.

Commit all staged changes into a single git commit with an automatically generated one-line Conventional Commit subject based on staged diffs and repository context. Use when asked to write or run a Conventional Commit for staged changes.

Work with AI agent todo files in docs/agent-todos

Fetch and summarize AI/LLM热点 into a PM-focused daily digest from X API, account RSS mirrors, or RSS/Atom sources. Use when you need to collect AI大模型热点, run the bundled fetch script in keyword/account/feed mode, format results into Chinese with the required labeled lines (内容概要/AI PM关注点/如何设计/市场反馈/标签/评注), or publish to WeChat Official Account via draft/add and freepublish/submit (requires AppID/AppSecret and thumb_media_id).

Secure secrets and policy management for AI agents. Provides tools to interact with the VaultKeeper daemon via the Control Plane API.

Manage Linear issues via GraphQL API. List, filter, update, prioritize, comment, and search issues. Use when the user asks about Linear, issues, project management, or backlog.

Crawls job postings from Liepin, Boss Zhipin, and Zhaopin. Invoke when user requests multi-site recruitment data collection or automated job search.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Install and fix AI SDK patterns from registries (aisdkagents.com, local). Handles ModelSelector integration, API configuration, test setup, registry generation, and verification. Automatically creates todo lists and avoids common issues.

Use this skill when the user wants to install AI SDK patterns from aisdkagents.com into the playground.

Orchestrates long-running TDD-based autonomous coding. Use when building complete applications from specs using test-driven development with multiple agent handoffs. Manages the loop between initializer and feature agents, tracks progress, and ensures all features pass their test cases before completion. Supports multiple AI backends (Claude and Gemini).

Commits code after successful feature implementation in TDD projects. Use after a feature agent completes implementation and all tests pass. Creates meaningful commit messages, handles staging, and maintains clean git history with conventional commit format.

Expert in creating Duplocloud Terraform modules following standard patterns. Use when creating terraform modules, tenants, infrastructures, app modules, or working with duplocloud/terraform-duplocloud-components. Knows module.ctx patterns, JIT credentials, workspace references, and GitHub Actions workflows.

This skill defines standard output templates for consistent agent responses.

This skill defines non-negotiable constraints that apply to ALL CodeScribe agents (planner and executor).

This skill defines executor-only responsibilities. The executor validates bundles, runs CodeScribe commands, and reports results.

Natural-language queries over a read-only PostgreSQL database. Use when the user asks to get data from the database, pull pipeline/table data, run a query, or export to CSV. Requires DATABASE_URL (read-only user recommended).

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration), ImageMagick (image manipulation, format conversion, batch processing, effects, composition), and RMBG (AI-powered background removal). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, removing backgrounds from images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests (HLS/DASH), generating thumbnails, batch processing images, creating composite images, or implementing media processing pipelines. Supports 100+ formats, hardware acceleration (NVENC, QSV), and complex filtergraphs.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

営業ターゲット企業のリストを自動作成。DuckDuckGo検索で企業を収集し、カスタム項目（技術スタック、資金調達情報など）を自動抽出。JSON/CSV/Markdown形式で出力。

Clinical copy-editor that reviews text for communication issues

Control Philips Hue smart lights - set brightness, turn on/off rooms or all lights

Manage Ghost blog posts via Admin API. Capabilities include list/filter posts (status, tag, featured, search), CRUD operations (create, read, update, delete, publish), bulk operations (mass publish/unpublish, add/remove tags), and tag management. Use when user mentions ghost blog, manage posts, publish drafts, bulk update, or blog management tasks.

Manage OpenProject attachments and wiki pages via API v3. Upload/download attachments to work packages, wiki pages, posts, meetings. Documents API is read-only. Use when handling files, documentation, or wiki content.

Manage work packages (tasks, issues, features) in OpenProject.

No description available

name: astro-react-zustand description: Build and hydrate React 19 islands inside Astro using @astrojs/react, with Zustand stores for shared state. Use when creating/updating React components with client directives, wiring Zustand stores, or debugging SSR/CSR hydration. ---

Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.

Download academic papers via DOI using Playwright browser automation. Use when users need to retrieve research paper PDFs. Searches Google Scholar first, falls back to Sci-Hub if blocked.

Use this skill when the user asks to "upgrade Angular", "update Angular version", "ng update", "migrate Angular X to Y", "update dependencies", or when performing any Angular major version upgrade. Provides the complete methodology for safely upgrading Angular through multiple major versions, including dependency ordering, third-party library compatibility, and build verification protocols. Encodes RULE 6 (duplicate selectors) and RULE 8 (ng update schematics).

Local, offline semantic search over OpenClaw memory files (MEMORY.md and memory/*.md) using Python embeddings + FAISS (no online LLM/API). Use when Dave asks for "memory search" without cloud billing, wants semantic recall across notes, or wants to share a reusable local-memory semantic search skill.

This skill should be used when the user asks about "voltaire branded types", "Effect Schema Ethereum", "Address schema", "Hash schema", "Uint8Array branded", "S.decode address", "ParseError", "voltaire primitives", "type safety Ethereum", or needs to understand how voltaire-effect handles type-safe Ethereum data.

This skill should be used when the user asks about "voltaire-effect errors", "typed errors Effect", "catchTag", "ParseError", "ProviderResponseError", "SignerError", "TransportError", "Either partial failures", "error composition", or needs to understand how voltaire-effect handles errors.

This skill should be used when the user asks about "voltaire-effect streaming", "watchBlocks", "block streaming", "event streaming", "reorg detection", "BlockStream", "TransactionStream", "subscribe", "real-time blockchain", or needs to understand how voltaire-effect handles real-time blockchain data.

小红书帖子创作与发布技能。用于:(1) 生成小红书风格的帖子内容(标题+正文+标签)(2) 获取/生成帖子配图 (3) 自动上传到小红书创作者平台。触发词:小红书创作、create redbook、小红书、红书、笔记创作、帖子创作

深度解读GitHub仓库，提供仓库用途、领域行业分析及本地使用指南。支持分析指定仓库或根据用户兴趣推荐热门仓库并解读。

YouTube 채널 성과 데이터를 기반으로 인사이트와 Next Action을 포함한 일일 운영일지를 자동 생성. Use when the user requests to: - Create daily operations logs ("/daily-ops-log", "운영일지 작성해줘", "오늘 성과 정리해줘") - Summarize YouTube channel performance for AI creators - Analyze content performance with actionable insights - Generate structured reports with Next Actions

Detect unchecked tasks in 10_Projects markdown files and push them to Todoist projects using todoist_project_id frontmatter; use when syncing project tasks from the knowledge repo to Todoist.

GROWI main application (apps/app) specific commands and scripts. Auto-invoked when working in apps/app.

Claude Code サブエージェント（カスタムエージェント）の作成・改善ガイド。「エージェントを作りたい」「サブエージェントを作成」「エージェントを改善」「agent を追加」で使用。新規作成と既存改善の両方に対応。

Comprehensive Hoosat blockchain development toolkit for building transactions, integrating wallets, creating dApps, and interacting with the Hoosat network (a Kaspa fork using Blake3 and Hoohash). Use when working with Hoosat blockchain development including: (1) Building and broadcasting HTN transactions, (2) Generating addresses with hoosat: prefix, (3) Creating dApps using hoosat-sdk or hoosat-sdk-web, (4) Integrating Hoosat wallets, (5) Using Hoosat SDKs (Node.js hoosat-sdk, Browser hoosat-sdk-web, Motoko hoosat-mo for IC), (6) Using the Hoosat REST API at proxy.hoosat.net, (7) Working with HRC20 tokens. Supports JavaScript/TypeScript (Node.js and Browser), Go, and Motoko (Internet Computer) development.

GitHub CLI operations for issue tracking, commits, and repository management

SAST Round 4: Exploit PoC Generation — Generate safe proof-of-concept tests for CRITICAL and HIGH severity findings.

Comprehensive security scanner for AI-generated and vibe-coded applications. Use this skill when reviewing, auditing, or validating code generated by AI tools (Cursor, Copilot, Claude Code, Replit, Lovable, Bolt, v0, etc.) for security vulnerabilities. Triggers on requests to check code security, audit AI-generated code, find vulnerabilities, security review, scan for risks, validate before deployment, or any mention of vibe coding security. Covers OWASP Top 10, injection flaws, authentication issues, supply chain risks, cloud misconfigurations, secrets exposure, and AI-specific vulnerabilities like prompt injection.

Build and maintain Backstage backend plugins following best practices.

Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y. Use for Playwright/Cypress/Vitest/Jest/RTL, flaky test triage, CI stabilization, and canvas/WebGL games (Phaser) needing deterministic input + screenshot/state assertions.

Build 2D browser games with Phaser 3 (JS/TS): scenes, sprites, physics (Arcade/Matter), tilemaps (Tiled), animations, input. Trigger: 'Phaser scene', 'Arcade physics', 'tilemap', 'Phaser 3 game'.

プロジェクトの依存関係を包括的に監査する（脆弱性、ライセンス互換性、未使用検出、アップデート計画）。 Use when user asks to audit dependencies, check licenses, find unused packages, plan dependency updates, run npm audit analysis, or clean up package.json. Avoid using for installing new dependencies, implementing features, fixing runtime bugs, or security review of application code (use security-review instead).

Use when producing implementable technical plans with task breakdown and verification matrix. After context gathering, before implementation.

GTD task management with Python CLI. Use for capturing, clarifying, organizing, and reviewing tasks following David Allen's Getting Things Done methodology with proper Horizons of Focus support.

GitHub CLI operations for issues, PRs, reviews, CI, and Copilot workflows. Auto-invokes when user asks about PRs, issues, CI status, code review, or GitHub Copilot. Supports triage, PR review, and Copilot iteration patterns.

Creates and navigates hierarchical code maps for AI agent and human orientation. Use when bootstrapping understanding of a codebase, creating documentation for navigation, or validating map integrity.

Web crawling and data extraction using the crwl CLI. Use this skill when users need to scrape websites, extract markdown content, handle JavaScript-heavy pages, or extract structured data from web pages.

Detect leaked secrets with Gitleaks. Use for secret leaks, credentials, keys, tokens, or code security checks.

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

Apply when automating browser interactions, web scraping, or UI testing with AI agents

Apply when doing planning for long-running tasks in sessions on top level

Utilities for Windows desktop automation: screenshots, window management, keyboard/mouse simulation.

Use after code review passes to present acceptance criteria and wait for explicit human verification - stops workflow until human confirms implementation meets requirements

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

This skill should be used when working with the Nostr protocol, implementing Nostr clients or relays, handling Nostr events, or discussing Nostr Implementation Possibilities (NIPs). Provides comprehensive knowledge of Nostr's decentralized protocol, event structure, cryptographic operations, and all standard NIPs.

Use when writing or reviewing code - orchestrates sub-skills for FCIS patterns, testing, database access, and Python idioms. Load this skill to get the full coding standards framework.

Use when planning features and need current API docs, library patterns, or external knowledge; when testing hypotheses about technology choices or claims; when verifying assumptions before design decisions - gathers well-sourced, current information from the internet to inform technical decisions

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization

Use when integrating changes from upstream ed3d-plugins into this fork - handles the ed3d->denubis rename, conflict resolution, and merge workflow

运行和测试 MediMind 健康助手项目

Binance 公开历史数据查询与下载助手。帮助用户了解 Binance 提供的历史市场数据类型、数据 schema、URL 结构，并协助下载数据。使用场景：(1) 查询 Binance 有哪些历史数据可用，(2) 了解数据字段含义和 schema，(3) 构建数据下载 URL，(4) 下载 klines/trades/aggTrades/fundingRate/metrics 等历史数据，(5) 获取交易对列表。触发词：Binance 数据、历史行情、K线下载、交易数据、aggTrades、资金费率、fundingRate、币安数据。

Interact with Linear for issue tracking. Use when creating, updating, listing, or searching issues. Supports viewing assigned issues, changing status, adding comments, and managing tasks.

File download implementation pattern for Tauri applications. Use this skill when implementing file save/download functionality in PhotoClove.

Generate images via Zenmux Vertex AI API using Gemini image models.

Build and test commands for the Dongting project. Use for compiling, running unit tests, and executing integration tests. Supports full build, protobuf compilation, and various test execution patterns.

Reclaims SSD disk space consumed by WSL2/Docker. Use when user reports disk space issues, Docker build failures due to space, or slow WSL performance. Handles Docker prune, cache cleanup, VHDX compaction, and prevention setup. MUST BE USED when "disk full", "out of space", or "VHDX" mentioned.

Deploys AWS infrastructure with research-first approach. Uses AWS MCP tools for documentation, regional availability, and resource management. ALWAYS searches AWS documentation before writing code, explains services and abbreviations, considers alternatives, maintains organized aws/ folder, and CRITICALLY offers to destroy resources after testing. Use PROACTIVELY for any AWS deployment, Terraform, ECS, Fargate, Lambda, S3, RDS, or cloud infrastructure tasks. MUST BE USED for prototype/learning projects to avoid unexpected costs. (project)

Generate clean table images from data. Perfect for Discord/Telegram where ASCII tables look broken. Supports dark/light mode, custom styling, and auto-sizing. No Puppeteer required. Companion to chart-image skill.

Generate and deploy multi-agent swarms with hooks. Auto-detects tech stack, selects templates, installs hooks, spawns teammates. Use for dev pipelines, code review, refactoring workflows.

Launch parallel multi-domain search workflows using the Dream Swarm orchestrator. Use when (1) searching across multiple data sources simultaneously, (2) aggregating information from APIs, databases, and web sources, (3) comparing findings across domains, (4) rapid parallel data gathering. Requires the MCP server to be running.

自动剪辑 AI 生成的视频片段，输出社媒短视频（抖音/TikTok、YouTube Shorts）。 触发场景：(1) 用户说"剪辑视频"、"合成视频"、"处理AI视频" (2) 用户提供视频目录要求自动剪辑 (3) 用户说 /ai-video-editor

AI短剧自动制作工作流。通过九宫格故事版方法制作角色一致、风格统一、可连载的AI短剧。触发场景：(1) 制作AI短剧 (2) 生成九宫格故事版 (3) 首尾帧视频生成 (4) AI视频创作 (5) 短视频批量制作 (6) 故事分镜制作

将音频或视频文件转换为文字稿。支持 mp3, wav, m4a, mp4, flac, ogg, webm 等格式。 使用云雾AI Whisper API进行高质量语音识别，支持中文、英文等多语言。 触发场景：(1) 转录音频 (2) 音频转文字 (3) 语音识别 (4) 会议录音整理 (5) 播客转文字 (6) 视频字幕提取 (7) 语音笔记转文字

下载在线视频和音频。当用户提供视频链接（如 YouTube、Bilibili、Twitter/X、抖音等）并要求下载时触发。触发词：下载视频、下载音频、保存视频、video download

Core engineering principles for implementation tasks

MANDATORY security foundation for OpenClaw. Consolidate scattered API keys and credentials into a secure .env file with proper permissions. Use when setting up OpenClaw, migrating credentials, auditing security, or enforcing the .env standard. This is not optional — centralized credential management is a core requirement for secure OpenClaw deployments. Scans for credential files across common locations, backs up existing files, creates a unified .env with mode 600, validates security, and enforces best practices.

Manage todos across projects with a global skill and project-scoped default view. Use when the user needs todo operations like add, list, update, delete, mark done, or wants to view all projects while defaulting to the current project.

Non-obvious project setup patterns for environment config, gitignore hygiene, and release versioning. Use when initializing projects, auditing tracked files, setting up env validation, or planning releases. Focuses on common mistakes Claude makes without guidance.

Error propagation patterns, custom error types, user-facing vs internal errors, and HTTP error mapping. Use when designing error handling strategy, creating custom error classes, or deciding how to propagate and present errors.

Structured research methodology with scoping, multi-source collection, triangulation, source credibility scoring, and anti-hallucination guards. Use when investigating technologies, comparing tools, evaluating libraries, exploring unfamiliar codebases, or producing research reports.

安全检查工具用于在安装新skill前分析其内容，检测潜在的安全风险（如提示注入、恶意代码、数据泄露、权限滥用等）。触发条件：(1) 用户要求安装或启用新的skill文件, (2) 用户上传.skill文件, (3) 用户要求检查某个skill的安全性, (4) 在执行skill安装操作前。此skill会分析SKILL.md、脚本和其他资源文件，识别安全风险并向用户报告，需经用户明确同意后才允许继续安装。

Nest.js framework expert specializing in module architecture, dependency injection, testing with Jest/Supertest, TypeORM/Mongoose integration, and Passport.js authentication. Use PROACTIVELY for any Nest.js application issues including architecture decisions or debugging complex DI problems.

Daycare 專案的 API 使用規範和方法。定義如何使用 api.js 模組進行資料庫操作、檔案上傳等。當需要進行資料庫查詢、新增、更新、刪除操作，或呼叫後端 API 時使用。