AI Skills Hub - Browse 180,000+ Agent Skills

Expert guidance for tmux-based development workflow with neovim, happy (Claude Code wrapper), and R/Julia REPLs.

Use when reviewing code for production readiness. Identifies critical issues causing production failures: data loss, security breaches, race conditions, performance degradation. Focuses on measurable impact, not style preferences. Triggers: reviewing code changes, verifying code safety/correctness, pre-commit reviews, after implementing significant changes.

| Field | Value | |-------------|--------------------------------------------------------------| | **Name** | ClawPinch | | **Version** | 0.1.0 | | **Author** | ClawPinch Contributors | | **License** | MIT | | **Platform**| macOS, Linux |

Create or update a PR from current branch to main, watch CI, and address feedback

Review FastAPI security audit patterns for dependencies and middleware. Use for auditing auth dependencies, CORS configuration, and TrustedHost middleware. Use proactively when reviewing FastAPI apps. Examples: - user: "Audit FastAPI route security" → check for Depends() and Security() usage - user: "Check FastAPI CORS setup" → verify origins when allow_credentials=True - user: "Review FastAPI middleware" → check TrustedHost and HTTPSRedirect config - user: "Secure FastAPI API keys" → move from query params to header schemes - user: "Scan for FastAPI footguns" → check starlette integration and dependency order

Generate AGENTS.md for end-user assistance. Covers setup, installation, running, and troubleshooting. This is for END-USER help, NOT developer/contributor docs. Use for /init user workflow. Examples: - user: "/init user" → user assistance AGENTS.md with official docs - user: "Create getting started guide" → installation + setup + troubleshooting - user: "Document how to use this repo" → user-focused AGENTS.md - user: "Help users run this software" → setup, prerequisites, usage patterns

ALWAYS use this skill when user says "Note that", "Remember that", "Add a note about", or explicitly asks about their notes with phrases like "What did I note about", "Show me my notes on", "Search my notes for", "Find in my notes", or "What have I noted about". This searches the user's persistent note-taking system (their second brain), NOT conversation history or general knowledge. Only trigger when the user explicitly mentions "note/notes/noted" or clearly refers to their personal knowledge system.

Access AI-generated documentation and insights for GitHub repositories via DeepWiki. This skill should be used when exploring unfamiliar codebases, understanding repository architecture, finding implementation patterns, or asking questions about how a GitHub project works. Supports any public GitHub repository.

Interact with GitHub repositories, issues, pull requests, and code via the GitHub MCP server. This skill should be used when managing repositories, creating/updating files, working with issues and PRs, searching code/repos/users, creating branches, and performing code reviews. Supports all major GitHub API operations.

プレゼンテーションの作成、編集、分析機能。Claudeがプレゼンテーション（.pptxファイル）を扱う必要がある場合：(1) 新規プレゼンテーションの作成、(2) コンテンツの変更または編集、(3) レイアウトの操作、(4) コメントや発表者ノートの追加、その他のプレゼンテーションタスク

変更履歴、コメント、書式保持、テキスト抽出をサポートした包括的なドキュメントの作成、編集、分析機能。Claudeがプロフェッショナルなドキュメント（.docxファイル）を扱う必要がある場合：(1) 新規ドキュメントの作成、(2) コンテンツの変更または編集、(3) 変更履歴の操作、(4) コメントの追加、その他のドキュメントタスク

モダンなフロントエンドWeb技術（React、Tailwind CSS、shadcn/ui）を使用して、精巧なマルチコンポーネントのclaude.ai HTMLアーティファクトを作成するためのツールスイート。状態管理、ルーティング、またはshadcn/uiコンポーネントを必要とする複雑なアーティファクトに使用 - シンプルな単一ファイルHTML/JSXアーティファクトには不向き。

使用MCP浏览器自动化工具进行前端测试和网页交互。当用户需要测试前端页面、自动化网页操作、验证UI交互、截图对比、或询问如何使用浏览器MCP工具时使用此skill。

Conversational GDB debugging for Breenix kernel. Use for interactive debugging sessions - set breakpoints, inspect registers, examine memory, step through code, investigate crashes.

This skill should be used when analyzing failed GitHub Actions CI/CD runs for Breenix kernel development. Use for diagnosing test failures, parsing QEMU logs, identifying kernel panics or faults, understanding timeout issues, and determining root causes of CI failures.

Write correct, idiomatic Apple MLX code for Apple Silicon ML. Use when working with MLX arrays, neural networks, training loops, lazy evaluation, unified memory, mx.eval, mx.compile, Metal GPU, memory optimization, quantization, or Apple Silicon performance. Covers critical API differences from PyTorch/NumPy, array indexing gotchas (lists must be mx.array, slices create copies), NHWC format for Conv2d, __call__ not forward(), float64 CPU-only, mlx-lm integration, and debugging patterns.

Expert guidance for Claude's memory_user_edits tool. Helps users understand how to effectively use memory edits for persistent facts across conversations. Key insight - memory edits work for FACTS, not BEHAVIORS. Triggers on memory-related questions, "remember", "forget", or memory_user_edits tool usage.

FluxCD is the standard GitOps approach for Kubernetes - diagnose issues, manage resources, and optimize deployments using declarative configuration synced from Git

Master Temporal CLI workflow management with smart query building, payload decoding, and history filtering using temporal, base64, and jq

当用户明确指定使用 Grok 生成图像、创建视频素材、让静态图片动起来或进行任何 AIGC 视觉创作时使用此技能。

Build stateful AI agents using the Cloudflare Agents SDK. Load when creating agents with persistent state, scheduling, RPC, MCP servers, email handling, or streaming chat. Covers Agent class, AIChatAgent, state management, and Code Mode for reduced token usage.

Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment. Generates server code, configures auth providers, and deploys to Workers. Use when: user wants to "build MCP server", "create MCP tools", "remote MCP", "deploy MCP", add "OAuth to MCP", or mentions Model Context Protocol on Cloudflare. Also triggers on "MCP authentication" or "MCP deployment".

Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest.

Inspect, build, and verify Office documents (PPTX, DOCX, XLSX) using the aurochs CLI. Use this skill when: (1) Inspecting existing Office files, (2) Building PPTX/DOCX/XLSX from JSON spec, (3) Previewing slide/document/sheet content in terminal, (4) Extracting text or data, (5) Verifying build results, (6) User asks about ".pptx", ".docx", ".xlsx" inspection or generation.

PubMed search with keyword optimization, result parsing, and metadata extraction

Generate songs, instrumentals, lyrics, and podcasts using EachLabs Mureka AI models. Also supports song extension, stem separation, and song recognition. Use when the user wants to create music, lyrics, or audio content.

Edit, transform, extend, upscale, and enhance videos using EachLabs AI models. Supports lip sync, video translation, subtitle generation, audio merging, style transfer, and video extension. Use when the user wants to edit or transform existing video content.

| Command | Description | |---------|-------------| | `/shader` | Interactive tool menu (recommended for first-time use) | | `/shader-help` | Full project shader health analysis | | `/shader-list` | List all shaders in the project | | `/shader-compile` | Compile and check for errors | | `/shader-analyze` | Analyze variant count and keywords | | `/shader-code` | Read shader source code | | `/shader-props` | View shader property definitions | | `/material-info` | Inspect material settings | | `...

Validate git commit messages, branch naming conventions, and check for sensitive files. Returns structured output with commit format validation, branch name compliance, and sensitive file detection (.env, credentials, .pem, .key). Used for git workflow validation and security checks.

Run ESLint and Prettier validation to check code style, formatting, and linting rules. Works with any TypeScript/JavaScript project using ESLint/Prettier. Returns structured output with error/warning counts, rule violations, and affected files.

Run npm audit to scan for security vulnerabilities and check for outdated packages. Returns structured output with vulnerability counts by severity (critical/high/moderate/low), affected packages, and recommended updates. Used for security audits and maintenance.

Run production build validation (npm run build, vite build, tsc) to ensure code compiles and builds successfully. Returns structured output with build status, duration, size metrics, and error details. Used for quality gates and deployment readiness checks.

Create properly named feature branch from development with remote tracking, following WescoBar naming conventions and git best practices

Record quality metrics baseline before refactoring or major changes, capturing audit scores, test coverage, and complexity for comparison

Load conductor workflow state from previous session and determine resumption point by analyzing git state and saved JSON state file

Parse GitHub AI analysis comment sections for architectural alignment, technical feasibility, implementation suggestions, and testing strategy

Modern C# asynchronous programming patterns using async/await, proper CancellationToken usage, and error handling in async code. Use when guidance needed on async/await best practices, Task composition and coordination, ConfigureAwait usage, ValueTask optimization, or async operation cancellation patterns. Pure .NET framework patterns applicable to any C# application.

UniTask library expert specializing in allocation-free async/await patterns, coroutine migration, and Unity-optimized asynchronous programming. Masters UniTask performance optimizations, cancellation handling, and memory-efficient async operations. Use PROACTIVELY for UniTask implementation, async optimization, or coroutine replacement.

VContainer dependency injection expert specializing in IoC container configuration, lifecycle management, and Unity-optimized DI patterns. Masters dependency resolution, scoped containers, and testable architecture design. Use PROACTIVELY for VContainer setup, service registration, or SOLID principle implementation.

Google Gemini CLI fundamentals for code analysis, review, and validation. Use when (1) executing gemini commands for code review/analysis, (2) configuring models (gemini-3-flash-preview (default)/gemini-3-pro-preview (complex only)), output formats (text/json/stream-json), or sandbox modes, (3) managing Gemini sessions with /chat save/resume, (4) integrating Gemini into automation scripts and CI/CD pipelines. Do NOT use for orchestration patterns (use gemini-claude-loop instead).

Scaffold and automate Grafana plugin projects using @grafana/create-plugin. Use when creating panel plugins, data source plugins, app plugins, or backend plugins. Handles project scaffolding, Docker dev environment setup, and plugin configuration.

Assist with Kubernetes interactions including debugging (kubectl logs, describe, exec, port-forward), resource management (deployments, services, configmaps, secrets), and cluster operations (scaling, rollouts, node management). Use when working with kubectl, pods, deployments, services, or troubleshooting Kubernetes issues.

Query Prometheus and Loki billing metrics from Grafana. Use when discussing observability costs, active series, ingestion rates, storage usage, or cardinality analysis.

Tauri v2 cross-platform app development with Rust backend. Use when configuring tauri.conf.json, implementing Rust commands (#[tauri::command]), setting up IPC patterns (invoke, emit, channels), configuring permissions/capabilities, troubleshooting build issues, or deploying desktop/mobile apps. Triggers on Tauri, src-tauri, invoke, emit, capabilities.json.

SOC II triage workflow for creating Linear tickets, branches, OpenSpec proposals, commits, and PRs. Use when asked to triage an issue, create a triage ticket, or start SOC II workflow.

Extracts knowledge from Amp threads and updates project docs. Use when asked to document recent work, sync docs after an epic, summarize what changed, or update AGENTS.md from thread history.

AI-supervised development workflow. Use when running /line-work, /line-prep, /line-cook, /line-serve, /line-tidy commands, managing beads issues during sessions, or following prep→cook→serve→tidy cycle. Covers workflow orchestration, guardrails, and session management.

统一记录 knowledge/news/lifelog/agent_kernel_memory/tasks 的通用 JSONL 记录技巧，支持新增/更新/删除（CRUD）、UUID 自动 id 与 auto record 到 lifelog。

移除 Google Gemini(Nano Banana)生成圖片中的浮水印，使用逆向 Alpha 混合演算法精確還原被覆蓋的像素

Setup and configure assistant-ui in a project. Use when installing packages, configuring runtimes, or troubleshooting setup issues.

Saves Claude Code or Codex CLI conversation threads to Nowledge Mem knowledge base via HTTP API. Use when user requests to save, persist, or backup the current session or conversation thread.

レスポンシブWebデザインのベストプラクティスを提供する専門スキル。モバイルファースト、フルードグリッド、メディアクエリ、ブレークポイント設計、画像最適化、タイポグラフィのスケーリング、タッチターゲット設計を包括的にサポートする。プロジェクト固有のTailwind CSS設計システム、8pxグリッド、Electron対応を含む。

Clean Architecture の依存関係ルールとレイヤー境界設計を整理し、設計レビューと違反検出を支援するスキル。 アーキテクチャのレイヤー構成、境界インターフェース、依存違反の是正を扱う。

GitHub Actions の実行コストを最適化するためのスキル。 コスト計測、削減施策の設計、実装、継続的な監視を一連で扱う。

コマンドのセキュリティ設計（allowed-tools制限/disable-model-invocation/機密情報保護）を整理し、安全な実行フローと権限制御を支援するスキル。 セキュリティ要件、検証手順、テンプレート運用を一貫して整理する。

AIエージェント・システムロール・ペルソナのための役割プロンプト設計スキル。 責務分離、専門家思考様式の適用、効果的なプロンプト構造化の指針を提供する。

Node.jsアプリケーションのログローテーション戦略設計・実装スキル。PM2、logrotate、Winston、集中ログシステムを活用した効率的ログ管理を提供。

pre-commit hookセキュリティスキル。機密情報検出パターン、git-secrets/gitleaks統合、チーム展開戦略、Git履歴スキャンを実装し、コミット前の機密情報漏洩を防ぐ。

Guides the creation of new Agent Skills, including generating SKILL.md structure, descriptions, instructions, and optional supporting files/scripts. Use this skill when the user wants to build, design, or scaffold a new custom skill, or when discussing skill creation best practices.

Guide for using /ralph-loop command for long-running autonomous tasks. Use when starting iterative development loops, implementing Bedrock plugins, or running test-fix cycles. (project)

Write, debug, and optimize bash scripts and CLI solutions for macOS using modern tools (fd, rg, sd, jq) with shellcheck compliance. Use when creating shell scripts, one-liners, pipelines, automation, or solving complex CLI tasks.

Reference for rp-cli usage patterns. Consult before calling rp-cli via Bash.

Workflow pattern standards for creating multi-agent orchestrations including YAML frontmatter (name, description, tags, status, agents, parameters), execution phases (sequential/parallel/conditional), agent coordination patterns, and Gherkin success criteria. Essential for defining reusable, validated workflow processes.

Clear description including: - What the skill does - When to use it - Trigger phrases ("use when X", "create Y", "generate Z")

Post-checkout git hook for automatic worktree setup. Use when: (1) Setting up automatic configuration for new git worktrees, (2) Creating post-checkout hooks that detect new worktrees and run setup tasks, (3) Configuring worktrees to automatically copy env files and install dependencies

Extract transcripts from podcasts and YouTube videos, then create shareable show notes and summaries. Use when the user wants to: (1) Get transcripts from Apple Podcasts or podcast audio files, (2) Extract transcripts from YouTube videos, (3) Create show notes or summaries from audio/video content, (4) Search for podcast episodes or YouTube videos to transcribe, or (5) Turn any audio or video content into structured notes.

Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step workflows with conditional branches, (3) adding persistence/memory across turns with checkpointers, (4) implementing human approval with interrupt(), (5) debugging via time-travel or LangSmith. Covers StateGraph, nodes, edges, add_conditional_edges, MessagesState, thread_id, Command objects, and ToolMessage handling. Examples include chatbots, calculator agents, and structured workflows.

Use before any code changes - hard gate ensuring work never happens on main branch, with proper feature branch creation from correct base

HARD GATE before PR creation - verifies review artifact exists in issue comments, all findings addressed or tracked, blocks PR creation if requirements not met

Upload video files to Wistia projects using the Data API. Use when user wants to upload videos to their Wistia account for hosting, transcription, or sharing.

Fetch OpenRouter model details and provide guidance for adding models to acai-ts provider configuration.

This skill should be used for development tasks that require detailed technical planning with persistent documentation. Use when the task involves architectural decisions, multi-phase implementation, external dependencies, or when the user explicitly requests an execution plan.

GreyCat C API and GCL Standard Library reference. Use for: (1) Native C development with gc_machine_t context, tensors, objects, memory management, HTTP, crypto, I/O; (2) GCL Standard Library modules - std::core (Date/Time/Tuple/geospatial types), std::runtime (Scheduler/Task/Logger/User/Security/System/OpenAPI/MCP), std::io (CSV/JSON/XML/HTTP/Email/FileWalker), std::util (Queue/Stack/SlidingWindow/Gaussian/Histogram/Quantizers/Random/Plot). Keywords: GreyCat, GCL, native functions, tensors, task automation, scheduler.

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.

Calculates total power consumption and battery life for Arduino/ESP32/RP2040 projects. Use when user asks about battery life, power requirements, current draw, or needs to estimate runtime. Includes sleep mode analysis, power optimization tips, and battery sizing recommendations. Run scripts/calculate_power.py for accurate calculations.

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.

Extracts specific fields from YAML files efficiently using yq instead of reading entire files, saving 80-95% context. Use this skill when querying YAML files, filtering/transforming configuration data, or getting specific field(s) from large YAML files like docker-compose.yml or GitHub Actions workflows

Extracts file structure (functions, classes, exports) efficiently without reading entire files, using ast-grep, Dart/Flutter analyzer, ctags, or other language-specific tools to get outlines and signatures. Use this skill when listing all methods, functions, or classes in a file, exploring unfamiliar code, getting API overviews, or deciding what to read selectively

Provides intuitive find & replace CLI with JavaScript regex and string-literal mode. Use this skill when performing text replacements, batch transformations, or need JavaScript-style regex syntax

Provides interactive fuzzy finder for selecting items from any list with preview capabilities. Use this skill when choosing from search results, files, processes, or any command output

Performs fast text search with one-shot patterns that minimize iterations by getting files, lines, and context in a single call. Use this skill when searching for text patterns, finding specific code locations, or getting context around matches

Performs fast file discovery with parallel search and smart defaults. Use this skill when searching for files by name, pattern, or type, especially when performance matters or when working with large directories

Analyzes code statistics by language for project insight, CI/CD metrics, or before refactoring. Use this skill when understanding project composition, measuring change impact, or generating CI/CD metrics

Send messages to Discord channels via the Discord API. Use this skill when the user wants to send text messages, notifications, or formatted content to a Discord channel.

Search, read, and manage Bear notes. Use when user asks about their notes, wants to find information in Bear, create notes, or manage tags.

Fetch source code for npm, PyPI, or crates.io packages and GitHub/GitLab repos to provide AI agents with implementation context beyond types and docs. Use when needing to understand how a library works internally, debug dependency issues, or explore package implementations.

Tmux terminal multiplexer commands and workflows. Use when managing tmux sessions, windows, panes, or capturing terminal output for debugging.

Probability, distributions, hypothesis testing, and statistical inference. Use for A/B testing, experimental design, or statistical validation.

Bundle: {description}

한 줄 설명 (활성화 키워드 포함)

Callabo 서비스 워크스페이스를 초기화합니다. 새 워크스페이스 생성, 브랜치 생성, 서비스 컴포넌트(callabo-server, callabo-webapp, magi) 선택 및 포트 설정, 서비스 간 연동 설정을 지원합니다.

Callabo 서비스들을 tmux로 한번에 실행합니다. callabo-server, scheduler, callabo-webapp, magi를 4개의 pane으로 구성하여 개발 환경을 빠르게 시작합니다.

Enforce semantic commit practices with proper file staging and prefix usage. Use when committing code, managing git history, or when user mentions git/commit/コミット.

Guide Claude through creating well-structured Agent Skills following best practices. Use when creating new Skills, authoring SKILL.md files, or when the user asks to build a Skill for Claude Code.

在输出包含中文字符与中文标点符号、编写中文文档、根据中文文档生成中文的交互回应、回复用户用中文提出的问题或任务、需要进行中文与非中文混排操作等涉及中文文字与标点符号的使用的场景中，必须使用本 Skill 以获得专业的中文字符的操作指导与行为规范引导。

Автоматизация создания REST API endpoints для проекта Family Budget

Автоматизация JWT аутентификации, Telegram OAuth и security middleware

Search GitHub code across millions of repositories using grep.app. Use when you need to find code patterns, implementations, examples, or understand how features are built in public codebases. (project)

Verify .claude directory configuration is complete and correct. Use when checking if agents, hooks, rules, and memory are properly set up, or after making changes to .claude configuration.

分散システムのためのTemporalを使用した耐久性のあるワークフローを設計します。ワークフローとアクティビティの分離、Sagaパターン、状態管理、および決定論の制約をカバーします。長時間実行プロセス、分散トランザクション、またはマイクロサービスオーケストレーションを構築する際に使用します。