AI Skills Hub - Browse 180,000+ Agent Skills

コマンドのエラーハンドリング（引数検証/事前チェック/ロールバック/ユーザー確認/エラーメッセージ設計）を整理し、失敗時の安全性と説明の一貫性を支援するスキル。 パターン選定、検証手順、テンプレート運用を一貫して整理する。

アプリケーションの安全な終了処理を実装するスキル。シグナルハンドリング、リソースクリーンアップ、リクエストドレイニングを含む完全な終了フローを設計。

GitHub Actionsの並列ジョブ実行とジョブ依存関係管理のスキル。needs構文による依存関係制御、outputs/artifacts/cacheを活用したデータ受け渡し、matrix戦略による並列度調整を提供する。

ユーザーストーリーマッピングの専門スキル。 バックボーン設計、リリース計画、ストーリー分割を提供します。

ドメイン駆動設計におけるユビキタス言語の確立と適用を専門とするスキル。 ドメインエキスパートと開発者が共有する厳密な語彙体系を構築し、コミュニケーションの齟齬を防ぐ。

データベース接続プール設計と運用を支援するスキル。 サーバーレス環境やTursoの接続制約を踏まえたサイジングと検証手順を整理する。

GitHub Actions の Composite Actions 設計と実装を支援するスキル。 action.yml の構造、入出力設計、再利用性、検証手順を整理する。

GitHub Actionsのジョブ出力管理スキル。ジョブ間でのデータ共有、outputs定義、 依存関係設定、条件分岐、マトリックス戦略での出力集約を提供。

GitHub Actions のキャッシュ戦略を設計し、キー設計、パス選定、ヒット率改善、10GB制限管理を行うスキル。 actions/cache の最適化、依存キャッシュの分割、Dockerレイヤー連携などを体系化する。

GitHub Actionsワークフロー実行時のデバッグとトラブルシューティング。

GitHub Actions通知統合スキル。Slack、Discord、MS Teams、Emailへの ビルド/デプロイ状態通知を自動化。成功/失敗メッセージのカスタマイズと インタラクティブ要素をサポート。

構造化ログのスキーマ設計、ログレベル設計、PIIマスキング、JSONログ実装を支援するスキル。 ログ要件整理から検証までを一貫して整理する。

エージェント向けプロンプトエンジニアリングを専門とするスキル。System Prompt設計、Few-Shot Examples、Role Prompting技術により、高品質なエージェント動作を実現します。

構造化ライティングを実践するためのスキル。DITAやトピックベースの原則に沿って文書を分割・再利用し、手順/概念/参照の役割を明確にする。

構造化出力を設計・生成・検証するためのスキル。JSON/YAML/CSV/Markdownなどの機械可読な出力を、用途と受け手に合わせて最小の仕様で定義し、一貫性と再利用性を確保する。

Zod schema validation and React Hook Form integration for TypeScript frontends. This skill should be used when creating forms, defining API schemas, validating form data, implementing type-safe validation, using ZodResolver with React Hook Form, or migrating legacy forms to the Zod + React Hook Form pattern.

Tools for reading and analyzing Arduino serial monitor output for enhanced debugging. Provides real-time monitoring, data logging, filtering, and pattern matching to help troubleshoot Arduino sketches using arduino-cli or Arduino IDE.

Build complete, production-ready Arduino projects (environmental monitors, robot controllers, IoT devices, automation systems). Assembles multi-component systems combining sensors, actuators, communication protocols, state machines, data logging, and power management. Supports Arduino UNO, ESP32, and Raspberry Pi Pico with board-specific optimizations. Use this skill when users request complete Arduino applications, not just code snippets.

Generate Arduino/embedded C++ code snippets and patterns on demand for UNO/ESP32/RP2040. Use when users request Arduino code for sensors, actuators, communication protocols, state machines, non-blocking timers, data logging, or hardware abstraction. Generates production-ready code with proper memory management, timing patterns, and board-specific optimization. Supports DHT22, BME280, buttons, I2C/SPI, EEPROM, SD cards, WiFi, and common peripherals.

Systematic hardware debugging guide for Arduino/ESP32/RP2040 circuits. Use when user reports: circuit not working, components getting hot, no power, intermittent failures, unexpected behavior, sensor not responding, LED not lighting, motor not spinning. Guides through power checks, continuity testing, signal tracing, and component isolation using multimeter techniques.

Ingest data from S3 into bauplan using the Write-Audit-Publish pattern for safe data loading. Use when loading new data from S3, performing safe data ingestion, or when the user mentions WAP, data ingestion, importing parquet/csv/jsonl files, or needs to safely load data with quality checks.

Build Mini Apps for MiniPay wallet. Use when building applications for MiniPay, detecting MiniPay wallet, or creating mobile-first dApps for Celo.

Instantly.ai cold email outreach API - manage campaigns, leads, accounts, and analytics. Use for cold email automation, lead management, campaign creation/monitoring, and email account warmup.

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.

UTF-8 JSON file I/O utilities to avoid Windows encoding issues (CP-1252 vs UTF-8)

Protocol fuzzer script development using boofuzz framework. Use when creating network protocol fuzzers, defining protocol PDUs (Protocol Data Units), writing mutation-based fuzzing scripts, or contributing to the boofuzz project. Covers binary protocol definitions, session management, crash detection, and reporting findings.

Deep-dive code analysis with periodic saving. Contributor mode reads every commit diff for annual reviews, accuracy rates, and promotion readiness. Codebase mode maps repository structure, cross-repo relationships, and enterprise governance. Works with GitHub (gh) and GitLab (glab). Saves checkpoints incrementally for resume across sessions.

채널톡 기능 구현을 도와줍니다. ALF 태스크, 코드노드, 스니펫, Open API, SDK 연동 작업 시 사용하세요. 채널톡 관련 코드 생성, 파일 수정, API 호출을 지원합니다.

Designs, builds, debugs, and documents OpenClaw workflows, skills, and AI assistant configurations. Use when the user mentions "OpenClaw," "personal AI assistant," "local AI," "ClawdHub," "openclaw skills," "chat platform AI," or wants to set up AI assistants across WhatsApp, Telegram, Discord, or Slack.

Perform a comprehensive CRAN pre-submission check on an R package. Use this skill when the user asks to "check the package", "verify CRAN compliance", or "prepare for submission".

Полный пайплайн: скачивает аудио из YouTube и транскрибирует через Groq Whisper API.

Assign and resolve first backlog issue from viban board through to PR completion

Use when writing or modifying React components, planning React features, or working with .jsx/.tsx files - provides modern React patterns with TypeScript, hooks usage, component composition, and common pitfalls to avoid

Create professional terminal recordings with VHS tape files - guides through syntax, timing, settings, and best practices

Deploy production LangGraph agents on AWS Bedrock AgentCore. Use for (1) multi-agent systems with orchestrator and specialist agent patterns, (2) building stateful agents with persistent cross-session memory, (3) connecting external tools via AgentCore Gateway (MCP, Lambda, APIs), (4) managing shared context across distributed agents, or (5) deploying complex agent ecosystems via CLI with production observability and scaling.

Use when generating BAML code for type-safe LLM extraction, classification, RAG, or agent workflows - creates complete .baml files with types, functions, clients, tests, and framework integrations from natural language requirements. Queries official BoundaryML repositories via MCP for real-time patterns. Supports multimodal inputs (images, audio), Python/TypeScript/Ruby/Go, 10+ frameworks, 50-70% token optimization, 95%+ compilation success.

Manage PARA-based personal knowledge management (PKM) systems using Projects, Areas, Resources, and Archives organization method. Use when users need to (1) Create a new PARA knowledge base, (2) Organize or reorganize existing knowledge bases into PARA structure, (3) Decide where content belongs in PARA (Projects vs Areas vs Resources vs Archives), (4) Create AI-friendly navigation files for knowledge bases, (5) Archive completed projects, (6) Validate PARA structure, or (7) Learn PARA organizational patterns for specific use cases (developers, consultants, researchers, etc.)

Diagnose ComfyUI errors, workflow failures, and quality issues. Suggests fixes based on error patterns, missing dependencies, and community-known workarounds. Use when ComfyUI workflows fail or produce unexpected results.

Direct integration with Telegram Bot API for checking inbox messages and sending messages (text, photos, documents) to chats. Triggers when users request 'check Telegram inbox', 'check messages', 'send message to [chat]', or mention Telegram bot interactions. Requires TELEGRAM_BOT_TOKEN environment variable.

Generates diagrams from text using PlantUML. Use when creating sequence diagrams, class diagrams, activity diagrams, C4 architecture diagrams, Gantt charts, mind maps, ER diagrams, or any visual diagram. Triggers on: diagram requests, architecture visualization, UML, flowcharts, system design, data modeling.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

使用 Playwright 与本地 Web 应用程序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。

全面的文档创建、编辑和分析功能，支持修订追踪、评论、格式保留和文本提取。当 Claude 需要处理专业文档（.docx 文件）时使用，包括：(1) 创建新文档，(2) 修改或编辑内容，(3) 使用修订追踪，(4) 添加评论，或任何其他文档任务

Captures screenshots on Windows systems. Can take full screen screenshots or capture specific application windows (e.g., Chrome, Edge, Firefox, Visual Studio Code). Use when the user needs to capture screenshots on Windows, list available windows, or get information about the currently active window.

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.

对spec.md、plan.md和tasks.md三个核心文档进行非破坏性跨工件一致性和质量分析。在任务生成后识别不一致、重复、模糊和规范不足的项目。触发词包括："speckit-analyze"、"speckit分析"、"文档一致性分析"、"规范分析"、"质量检查"、"工件分析"、"spec分析"、"plan分析"、"task分析"。

Core data engineering capabilities: dataset profiling, schema validation, and data quality assessment. Use when analyzing datasets, validating schemas, or assessing data quality. Use when: - "profile this dataset" - "validate schema" - "check data quality" - "what's in this CSV/Excel file" - "analyze this data"

Policy interpretation and compliance guidance. Translates regulatory requirements into actionable controls, maps policies to code, and provides implementation guidance. Use when: "policy", "what does this mean", "how to implement", "policy guidance", "requirements translation"

GitHub CLI power utilities - workflow debugging, PR management, release automation, and repo operations. Use when working with GitHub via CLI for anything beyond basic git commands.

Debug EClaw issues. Use when things aren't working, container fails, authentication problems, or to understand how the system works. Covers logs, environment variables, mounts, and common issues.

Build and debug Pydantic AI agents using best practices for dependencies, dynamic system prompts, tools, and structured output validation. Use when the user wants to: (1) Create a new Pydantic AI agent, (2) Debug or fix an existing agent, (3) Add features like tools, validators, or dynamic prompts, (4) Integrate OpenRouter for multi-model access, (5) Add Logfire for debugging/observability, (6) Structure agent architecture with dependency injection.

Install Claude Code skills from GitHub URLs. Supports repositories, folders, and .skill files. Features smart updates (preserves personalized CONTEXT.md), batch installation, and update checking.

从 PRD/需求创建结构化 Issue，自动评估复杂度并拆分子任务。

Control a Playwright browser via CLI - navigate, interact, and screenshot

Show unified status of all community platforms. Use when user wants to check their setup, see sync status, or get an overview.

Sync Discord server members. Use when user asks to sync members, get member list, or fetch all members from Discord. Fetches complete member lists (100k+).

Sync Telegram messages to local storage. Use when user asks to sync, pull, fetch, or download Telegram messages.

Diagnose Telegram configuration and connectivity issues. Use when user reports problems with Telegram sync, connection errors, or wants to troubleshoot.

Diagnose Discord configuration and connectivity issues. Use when user reports problems with Discord sync, connection errors, or wants to troubleshoot.

Create or update feature requirements specification using EARS notation with examples and appendices

Create a test plan mapping EARS requirements and Critical Constraints to specific tests

Create, update, validate, and submit Homebrew Casks. Use when the user mentions Homebrew cask/cask, Homebrew/homebrew-cask, adding a new cask, updating a cask, cask token naming, sha256, url verified:, livecheck, zap/uninstall, or when asked to run brew style/audit for a cask.

Comprehensive OpenTUI skill for building terminal user interfaces. Covers the core imperative API, React reconciler, and Solid reconciler. Use for any TUI development task including components, layout, keyboard handling, animations, and testing.

Analyze OpenCode conversation history to identify themes and patterns in user messages. Use when asked to analyze conversations, find themes, review how a user steers agents, or extract insights from session history.

Updates existing secrets in 1Password using the op CLI. Use when the user needs to modify passwords, edit field values, add or remove fields, rename items, move items between vaults, or manage tags on existing 1Password items. Supports all item types including Login, Password, API Credential, and Secure Note.

Assists in creating Agent Skills of varying complexity levels (simple, moderate, complex). Use when the user wants to create, design, or build a new Agent Skill, or when they need guidance on skill architecture, workflow design, schema validation, or template structure.

Manages to-do items across multiple Google accounts using the Google Tasks API. Use when the user needs to create, update, complete, or organize tasks in Google Tasks, manage task lists, or view tasks across multiple Google accounts. Supports personal Gmail, Google Workspace, and organization-provisioned accounts with secure OAuth authentication.

Deep analysis of clinical trials including design, enrollment, outcomes, and competitive positioning. Use for trial monitoring, landscape analysis, and competitive intelligence.

ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) prediction for drug candidates. Use for assessing drug-likeness, PK properties, and safety risks early in drug discovery.

このプロジェクトでの Marp スライド作成ルール。スライド作成、画像配置、ビルド、プレビュー時に使用。画像は slides/images/ に配置、bun run preview/build を使用。

Use when searching academic papers on arXiv, understanding research content, building literature reviews, or generating citations for academic writing

Convert PDFs to Markdown using Mistral OCR API with image extraction. Use when you need to extract structured text and images from PDFs, especially for scanned documents or documents with complex formatting. Outputs Markdown with embedded images.

Training manager for RunPod GPU instances - configure pods, launch training, monitor progress, retrieve checkpoints

Validate datasets for Unsloth fine-tuning. Use when the user wants to check a dataset, analyze tokens, calculate Chinchilla optimality, or prepare data for training.

Creates concise, executable implementation plans for solo developer working with AI agents. Validates assumptions, avoids timelines, focuses on actionable steps with clear human/AI delegation.

Maintain and improve code quality using PHPInsights without decreasing quality thresholds. Use when PHPInsights fails, cyclomatic complexity is too high, code quality drops, or when refactoring for better maintainability. Always maintains 93% complexity for src/ and 95% for tests/, plus 100% quality/architecture/style scores.

Create and manage K6 load tests for REST and GraphQL APIs. Use when creating load tests, writing K6 scripts, testing API performance, debugging load test failures, or setting up performance monitoring. Covers REST endpoints, GraphQL operations, data generation, IRI handling, configuration patterns, and performance troubleshooting.

Comprehensive Ash framework guidelines for Elixir applications. Use when working with Ash resources, domains, actions, queries, changesets, policies, calculations, or aggregates. Covers code interfaces, error handling, validations, changes, relationships, and authorization. Read documentation before using Ash features - do not assume prior knowledge.

Docker and Docker Compose reference for container deployment, networking, volumes, and orchestration. Includes Proxmox hosting and LXC comparison patterns. Use when working with docker-compose.yaml, Dockerfiles, troubleshooting containers, or planning container architecture. Triggers: docker, compose, container, dockerfile, volume, network, service, lxc.

HashiCorp Packer reference for building machine images and VM templates. Use when working with Packer configurations (.pkr.hcl files), running packer commands, troubleshooting builds, or designing image pipelines. Includes Proxmox builder patterns for homelab environments. Triggers: packer, pkr.hcl, image, template, ami, builder, provisioner, cloud-init.

Terraform infrastructure-as-code reference for HCL syntax, state management, module design, and provider configuration. Use when working with Terraform configurations (.tf files), running terraform commands, troubleshooting state issues, or designing modules. Includes Telmate Proxmox provider patterns. Triggers: terraform, tfstate, .tf files, HCL, modules, providers, proxmox_vm_qemu.

Comprehensive Azure cloud expertise covering all major services (App Service, Functions, Container Apps, AKS, databases, storage, monitoring). Use when working with Azure infrastructure, deployments, troubleshooting, cost optimization, IaC (Bicep/ARM), CI/CD pipelines, or any Azure-related development tasks. Provides scripts, templates, and best practices for production-ready Azure solutions.

Work with markdown-based task lists in .llm/todo.md files. Use when managing tasks, working with todo lists, extracting incomplete tasks, marking tasks complete, or implementing tasks from a task list.

Elite UX agency capabilities for designing products users intuitively love. Use when creating user journeys, conducting UX research, designing flows, testing with Playwright, performing design critiques, building wireframes, writing microcopy, accessibility audits, competitive analysis, or any product design work. Triggers on UX, user journey, user experience, flow design, usability, design critique, persona creation, emotional mapping, or product design discussions.

Helps users discover patterns and insights in their Knowledge Graphs. Use when users ask about important entities, connections, patterns, or want to understand what they can do with their graph. Triggers proactively after extraction to show what's possible.

Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.

Enables JMAP email operations using Node.js and jmap-jam library. Use when working with JMAP email servers, FastMail, Cyrus IMAP, Stalwart Mail Server, or when user mentions email search, reading, sending, or mailbox management.

リリースワークフロー管理スキル。CHANGELOG更新、セマンティックバージョニング、GitHub Release作成、リリースブランチ運用のベストプラクティスを提供。「リリース」「バージョン」「CHANGELOG」「タグ」「GitHub Release」などのキーワードで自動適用。

Use when PRD/TRD contains architectural decisions to document - extracts decisions from refined requirements (architecture choices, data model decisions, API patterns, technology selections, integration strategies, reuse patterns) and generates MADR-format ADRs. One ADR per decision point. Also use when asked to document decisions, create decision records, or retrospectively capture architectural choices.

Use this skill when the user asks to implement off-screen rendering in RealityKit, create custom rendering pipelines, generate shadow maps, or implement stereoscopic 3D rendering with MTLTexture output on visionOS.

Use this skill when the user asks to track hand joints, recognize hand gestures, drive hand models with skeleton data, or implement hand-object interaction on visionOS. Supports both simple AnchorEntity (no permissions) and full ARKit HandAnchor (27 joints, requires Full Immersive).

Use this if the user wants to connect to Ollama or leverage Ollama in any shape or form inside their project. Guide users integrating Ollama into their projects for local AI inference. Covers installation, connection setup, model management, and API usage for both Python and Node.js. Helps with text generation, chat interfaces, embeddings, streaming responses, and building AI-powered applications using local LLMs.

Write content to a file with path validation. Use when you need to create or overwrite files in .ui/ or .claude/ directories.

Definition-of-Done workflow using `verify-loop` plus Bun formatting, typecheck, and tests; includes placement rules and reporting expectations.

图像理解分析工具 - 使用豆包视觉模型解析、分析和理解图像内容。支持物体识别、文字提取（OCR）、场景分析、风格评估等功能。当用户需要"分析图片"、"理解图像"、"提取图片内容"、"描述图片"时触发。

Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.

E2E Testing & Automation for Electron Apps (Playwright)

Mac system monitoring skill. Returns CPU, memory, temperature, disk, and Docker status. Trigger when: - "How's the Mac?" or "How's the server?" - "System status" or "Server status" - "Check server health" or "Mac health" - "What's eating CPU?" or "What's using memory?" - "Disk space?" or "Storage status?" - "Temperature?" or "Is the Mac hot?" - "Docker containers?" or "Are containers running?" - Any question about Mac hardware health or resource usage

将 Markdown 文本自动渲染为飞书云文档，按指令块调用 lark-cli 创建/写入内容，并支持高亮块、画板与 PlantUML/Mermaid 图表。适用于任何需要 Markdown → 飞书文档自动落地的场景。

使用 lark-cli send-message 向飞书用户或群聊发送消息，构造 content JSON 并自动判断 msg_type（text/post/image/file/audio/media/sticker/interactive/share_chat/share_user/system）。当用户需要“发送飞书消息”“把内容转成消息 JSON”“选择消息类型”“用 lark-cli 发送消息/回复消息/编辑消息”时使用。