AI Skills Hub - Browse 180,000+ Agent Skills

Generates Agent Skills optimized for AI agent consumption with structured, parseable instructions.

Discord Bot API経由でメッセージの読み取り・送信・アーカイブを行う。チャンネル一覧取得、メッセージ読み取り、メッセージ送信、R2へのメッセージアーカイブが可能。DISCORD_BOT_TOKEN環境変数が必要。

RSS/Atomフィードの取得・解析を行う汎用RSSリーダー。単一フィードの取得、複数フィードの一括チェック、新着記事の検出が可能。外部API不要（フィードURLに直接アクセス）。

Gmail API経由でメールの読み取り・送信・検索を行う。メール一覧取得、本文読み取り、メール送信、検索クエリによるフィルタリングが可能。GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, GOOGLE_REFRESH_TOKEN環境変数が必要。

Enable AI-driven Todo management using natural language via MCP tools. Use when building conversational todo agents, implementing natural language task management, designing AI assistants for todo apps, or creating MCP-based tool integrations. Covers intent interpretation, safe tool invocation, and stateless agent design.

Domain expert for Todo applications providing entity structure definitions, CRUD operation rules, task state management (pending, completed, archived), and edge case validations. Use when designing, implementing, or reviewing Todo app features, validating Todo data models, handling task state transitions, or enforcing business rules for task management systems.

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

Package and deploy applications to Kubernetes with Dockerfiles, Helm charts, and local Minikube deployment. Use when containerizing applications, creating Kubernetes manifests, setting up Helm charts, deploying to Minikube, or preparing cloud-ready configurations. Focuses on local-first deployment with stateless services.

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

Generate YARA rules from malware samples using yarGen-Go. Manage goodware databases, use CLI or API for rule generation, and integrate with yarGen web server. Use when generating YARA rules, managing goodware databases, creating custom string/opcode databases, or interacting with yarGen web API.

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. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Write Ruby gems following Andrew Kane's proven patterns and philosophy. Use when creating new Ruby gems, refactoring existing gems, designing gem APIs, or when the user wants clean, minimal, production-ready Ruby library code. Triggers on requests like "create a gem", "write a Ruby library", "design a gem API", or mentions of Andrew Kane's style.

Advanced Next.js patterns - middleware, Server Actions, caching with Clerk.

Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.

Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.

Synchronize all sub-issues to Closes statements in tracking PR

Clean up after merging a PR - checkout base, fetch, pull, delete feature branch

스프린트 기반 주간업무보고서 생성. 스프린트 이름을 입력하면 Jira에서 이슈와 코멘트를 가져와 CATEGORY_CONFIG.md에 정의된 섹션별 마크다운 보고서를 자동 생성한다.

Use after /dream-team:plan to write a sequential execution spec. No arguments needed — picks up conversation context from the brainstorming session.

Codex-led multi-model workflow (Codex + Claude + Gemini). Use when the user asks to run `synapse <cmd> ...` to generate draft diffs/audits and persist artifacts to `./.synapse/**`.

Token-efficient library API documentation fetcher using Context7 MCP with 77% token savings. Fetches code examples, API references, and usage patterns for published libraries (React, Next.js, Prisma, etc). Use when users ask "how do I use X library", need code examples, want API syntax, or are learning a framework's official API. Triggers: "Show me React hooks", "Prisma query syntax", "Next.js routing API". NOT for exploring repo internals/source code (use researching-with-deepwiki) or local files.

Revoke risky token approvals to protect wallet security

Get comprehensive portfolio view of TRON wallet including all token balances, USD valuations, and portfolio composition analysis.

Check TRON addresses for security risks using TronScan labels, blacklists, scam detection, and fraud transaction history before interacting.

Get real-time and historical cryptocurrency prices for TRON ecosystem tokens (TRX, USDT, BTT, etc.) from multiple sources including Binance, CoinGecko, and DEX aggregators.

Detect malicious TRON addresses using TronScan's official tag/label database to identify scam, phishing, and fraudulent addresses.

Generate and maintain project documentation using Material for MkDocs and mkdocstrings. Use when creating API references, building documentation sites, or writing user guides.

Search and order pharmacy products from apohealth.de via apo-cli. Use for medication search (by name or PZN), product details, category browsing, and cart management. Trigger when the user mentions Apotheke, pharmacy, Medikament, medication, PZN, apohealth, or health products.

Use when creating, updating, or improving agent skills.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

Refine a project plan into an implementation-ready spec via a structured Q&A interview. Use when the user asks to refine a spec, turn a plan into a spec/PRD/tech spec/requirements/acceptance criteria/milestones/backlog, or provides a project plan that needs clarity.

自动化每日 AI 新闻聚合与推送。使用专业 AI 媒体（MarkTechPost、机器之心、量子位等）覆盖 OpenAI、Google、Anthropic、阿里、字节、智谱等各大厂动态。触发词包括"获取今日 AI 新闻"、"AI 新闻摘要"、"每日 AI 简报"。

Trustless USDC escrow for agent-to-agent payments on Base. Create, release, dispute escrows via simple commands.

Validate AI agents against production-level quality criteria with 0-100 scoring. Use when evaluating agent quality, identifying bugs/gaps, or improving agents to expert level. Evaluates agents across 9 categories: structure, role definition, methodology, user interaction, quality standards, context management, technical robustness, pedagogical effectiveness (tutors), and production readiness (operators). Returns actionable validation report with specific improvements.

Complete stenography guide for court reporting and legal transcription. Use when building steno projects from basic to professional level, learning court reporting workflows, optimizing legal dictionaries, setting up Plover for courtroom use, creating specialized legal briefs, or developing speed for legal documentation.

Guide for creating and incrementally building Claude Code plugins. Use when users want to create a new plugin, add components to an existing plugin, or package plugins for distribution.

C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: - Implementing RL algorithms in C++ for performance-critical applications - Building production RL systems with libtorch - Creating replay buffers and experience storage - Optimizing RL training with GPU acceleration - Deploying RL models with ONNX Runtime

Run all configured linters including mojo format, markdownlint, and pre-commit hooks. Use before committing code to ensure quality standards are met.

Generate comprehensive plan documentation following Template 1 format. Use when creating plan.md files for new components or subsections.

Switch between git worktrees for parallel development. Use when working on multiple issues simultaneously.

Create isolated git worktrees for parallel development. Use when working on multiple issues simultaneously.

Test agent delegation patterns to verify hierarchy and escalation paths. Use after modifying agent structure.

Validate type safety in Mojo code including parametric types and trait constraints. Use during code review or when type errors occur.

Automatically fix code formatting issues using mojo format, markdownlint, and pre-commit hooks. Use when formatting checks fail or before committing code.

Verify memory safety in Mojo code including ownership, borrowing, and lifetime management. Use when reviewing code or debugging memory issues.

Generate Architecture Decision Records (ADRs) to document significant architectural decisions. Use when making important technical decisions that need documentation.

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. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Write GLSL shaders for TouchDesigner's GLSL TOP, GLSL MAT, and GLSL COMP operators. Use when creating pixel shaders, vertex shaders, compute shaders, visual effects, image processing, generative art, GPU computations, or working with .glsl/.frag files for TouchDesigner.

Generate, package, and validate weighted outcome books for slot/casino game modes. Use when defining mode book schemas, producing `books_*.jsonl(.zst)` files, generating `lookUpTable_*.csv` weights, assembling `index.json`, or running publication-ready integrity checks across books/index/weights artifacts.

Optimize and validate slot/casino RTP against explicit targets using simulation evidence. Use when defining RTP targets per mode, tuning paytables and feature frequencies, validating convergence from simulation runs, comparing theoretical vs empirical RTP, or preparing release sign-off with pass/fail thresholds.

Design, sequence, and validate event-driven animation systems for games and interactive UI. Use when defining animation triggers, timeline ordering, transition guards, interruption/cancel rules, easing/duration consistency, event-to-animation mapping, or release readiness checks for animation flow contracts.

Integrate, validate, and harden WebAssembly modules in frontend/backend application pipelines. Use when wiring WASM build artifacts with JS/TS loaders, validating module/loader contracts, checking init symbols and runtime assumptions, triaging WASM loading failures, or preparing release sign-off for wasm bundle integrity.

Build, integrate, and validate AI-driven gameplay systems for production game runtimes. Use when implementing AI behavior modules, wiring inference providers into game loops, enforcing latency/fallback budgets, validating safety and telemetry contracts, or auditing AI game features before release.

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.

Multi-agent development pipeline that takes features from idea to PR. Five specialized agents (plan, validate, develop, review, test) work in sequence with automatic retry, model escalation, and traceability. Use when implementing features, fixing complex bugs, or running structured development workflows.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as 'Deploy my app', 'Deploy this to production', 'Create a preview deployment', 'Deploy and give me the link', or 'Push this live'. No authentication required - returns preview URL and claimable deployment link.

Observe and troubleshoot WhatsApp in Kapso: debug message delivery, inspect webhook deliveries/retries, triage API errors, and run health checks. Use when investigating production issues, message failures, or webhook delivery problems.

Use when interpreting Culture Index surveys, CI profiles, behavioral assessments, or personality data. Supports individual interpretation, team composition (gas/brake/glue), burnout detection, profile comparison, hiring profiles, manager coaching, interview transcript analysis for trait prediction, candidate debrief, onboarding planning, and conflict mediation. Handles PDF vision or JSON input.

Helps choose the right battery type and charging solution for Arduino/ESP32/RP2040 projects. Use when user asks about battery options, charging circuits, power source selection, or says "what battery should I use". Covers chemistry selection, safety, voltage regulation, and charging circuits.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

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.

Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.

Build 3D web apps with Three.js (WebGL/WebGPU). 556 searchable examples, 60 API classes, 20 use cases. Actions: create 3D scene, load model, add animation, implement physics, build VR/XR. Topics: GLTF loader, PBR materials, particle effects, shadows, post-processing, compute shaders, TSL. Integrations: WebGPU, physics engines, spatial audio.

Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use --skip to bypass). 3 modes: search, creative, wild. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.

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

Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use --skip to bypass). 3 modes: search, creative, wild. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.

Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.

Steuere Bambu Lab 3D-Drucker (A1, P1P, X1) über MQTT. Nutze diesen Skill für Druck-Überwachung, Status-Abfragen, Steuerung (Pause/Stopp) und Benachrichtigungen bei Druckende oder Fehlern. Erfordert LAN-Mode mit Access Code.

Execute a Flow epic or task systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan or working through a spec. Triggers on /flow-next:work with Flow IDs (fn-1-add-oauth, fn-1-add-oauth.2, or legacy fn-1, fn-1.2, fn-1-xxx, fn-1-xxx.2).

Epic completion review - verifies all epic tasks implement spec requirements. Triggers on /flow-next:epic-review.

All 6 skill files have been created. Here's a summary of what was generated:

Implements Redis caching, session storage, and BullMQ job queues for the SocialHub monorepo. Use when: adding cache layers, configuring Redis connections, creating BullMQ queues/workers, implementing rate limiting, or debugging Redis-related issues.

The skill files have been generated. Here's a summary of what was created:

All three BullMQ skill files have been created:

The Zustand skill files have been generated:

The skill files have been generated. Here's a summary of what was created:

Creates validation schemas for shared types and API request validation. Use when: defining or modifying Zod schemas in packages/shared/src/schemas/, adding tRPC input validation, validating environment variables, or inferring TypeScript types from schemas.

Safety-first camping planning for beginners, families, and casual campers. Use when asked to plan a camping trip, build a gear checklist, create meal and itinerary plans, prepare for weather or wildlife risks, compare campsite options, or provide permit and Leave No Trace preparation.

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. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Multi-platform favorites/bookmarks router that calls atomic skills (bilibili/zhihu/xiaohongshu) to list your favorites (folders/collections/boards) and fetch item text/transcripts for summarization. Use when the user asks "看看我收藏了哪些/最近收藏了什么", or provides a B站/知乎/小红书 link and asks what it's about.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

This skill should be used when the user asks to "查 AKShare 数据字典", "在 AKShare 里找接口", "AKShare 有哪个接口", "查询板块/行业/概念成分", "查询期货/商品/股指期货数据", "查询基金/宏观/债券数据", "sync AKShare docs", "建立 AKShare 索引", "api_search", or "ak_call".

This skill should be used when the user asks to "个股分析报告", "分析某只 A 股", "查询个股实时行情", "查询个股历史K线", "查询估值指标", "查询资金流向", "查询财务摘要", "查询十大股东", or "查询分红数据" (focused on single-stock A-share analysis via AKShare scripts).

This skill should be used when the user asks to "将 FinancialBot 变成 Claude Skill", "启动 FinancialBot", "运行 FinancialBot API", "配置 FinancialBot 存储路径", "配置 FINANCIALBOT_SKILL_HOME", or mentions "skill-home" / "FINANCIALBOT_SKILL_HOME".

Use when provisioning cloud Kubernetes clusters on GCP (GKE), Azure (AKS), or Oracle Cloud (OKE). Triggers for: setting up production Kubernetes infrastructure, deploying clusters with free tier credits, configuring cloud-managed K8s environments, or when user specifies GCP/Azure/Oracle Cloud deployment. NOT for: local Kubernetes (use Minikube/kind instead), bare metal clusters, or managed K8s platforms other than GKE/AKS/OKE.

Security audit and threat model for OpenClaw gateway hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes.

Package and deploy applications to Kubernetes with Dockerfiles, Helm charts, and local Minikube deployment. Use when containerizing applications, creating Kubernetes manifests, setting up Helm charts, deploying to Minikube, or preparing cloud-ready configurations. Focuses on local-first deployment with stateless services.

Domain expert for Todo applications providing entity structure definitions, CRUD operation rules, task state management (pending, completed, archived), and edge case validations. Use when designing, implementing, or reviewing Todo app features, validating Todo data models, handling task state transitions, or enforcing business rules for task management systems.

Enable AI-driven Todo management using natural language via MCP tools. Use when building conversational todo agents, implementing natural language task management, designing AI assistants for todo apps, or creating MCP-based tool integrations. Covers intent interpretation, safe tool invocation, and stateless agent design.

Audit Codex skills (folders containing SKILL.md) for security risks such as hidden content, network calls, shell execution, obfuscated code, destructive commands, credential access, and bundled binaries. Use when reviewing or installing third-party skills, before publishing a skill, or when a skill behaves unexpectedly.

Analyze CI build and test status from Azure DevOps and Helix for dotnet repository PRs. Use when checking CI status, investigating failures, determining if a PR is ready to merge, or given URLs containing dev.azure.com or helix.dot.net.

使用 @aptx/token-store 定义或实现 token 持久化。用于：实现 TokenStore 接口、支持同步/异步 API（getToken/setToken/clearToken）、可选的元数据方法、实现不同存储后端（cookie、localStorage、小程序、内存）、配合 @aptx/api-plugin-auth 使用。当代码需要实现自定义 TokenStore 时触发。

使用 @aptx/api-plugin-csrf 添加 CSRF 保护。触发条件：当代码需要在请求中添加 CSRF token、配置 cookie/header 名称、处理 SSR/Node 环境的 cookie 读取、或使用 createCsrfMiddleware 时使用。

使用 @aptx/api-plugin-auth 实现 token 认证中间件和控制器。支持自动添加 Authorization header、token 刷新（主动/被动401处理）、防止重复刷新、失败回调。触发条件：用户请求认证功能（配置中间件、处理401刷新、管理token）或代码涉及 createAuthMiddleware/createAuthController 时使用。

A builder that generates Agent Skills with a practical focus — one script, inline smoke tests, and usage examples embedded in the SKILL.md.

Launch Solana tokens on Pumpfun, manage fee sharing, claim earnings, and track portfolio. All via chat.

A validation-first builder with refined test patterns, smart language selection, and mandatory cross-platform compatibility checks.

Validates that required development tools are installed on a machine, with version checking and requirements file support.