AI Skills Hub - Browse 180,000+ Agent Skills

Guide for sp.h, a single-header C standard library replacement. You must use this guide when using or discussing sp.h in any capacity.

Automate Chrome browser via DevTools Protocol. Navigate pages, interact with elements, inspect network/console, analyze performance, and capture screenshots for web testing and automation tasks.

Comprehensive shell/bash engineering guidelines based on Google's Shell Style Guide. This skill should be used when writing shell scripts, reviewing bash code, or answering questions about shell scripting best practices. Applies to .sh files, bash scripts, and any shell programming tasks.

Secure credential management using 1Password CLI with zero plaintext secrets on disk.

You are an expert browser automation engineer. Help users create, improve, and debug web automation scripts by exploring live browser pages via Chrome DevTools MCP.

ProcessWire CLI usage via ddev — running PHP scripts, bootstrapping the PW API, debugging with Tracy, and direct database queries. Use when executing PHP in a ProcessWire ddev project, writing CLI scripts, or querying the database directly.

Conservative, low-risk fixes for TypeScript errors introduced by enabling noUncheckedIndexedAccess, with different policies for test vs production code and a bias toward non-cascading changes.

iOS .xcstrings 파일의 번역을 추가, 수정, 삭제, 조회하는 스킬. .xcstrings 파일을 직접 읽지 말고 이 스킬 사용.

Complete game asset design, creation, implementation, and optimization team. Use when creating visual assets, art direction, sprites, UI elements, icons, textures, animations specs, audio design, or any game visuals. Covers AI image generation (Gemini), asset pipelines, optimization for web/mobile, style guides, and performance tuning. Triggers on requests for game art, icons, backgrounds, character designs, UI assets, promotional materials, or asset troubleshooting.

Node.js patterns for ws WebSocket server with Express, JSON envelope protocol, and chokidar file watching

Uses shared scripts from [openapi-toolkit](../../../../../.claude/shared/openapi-toolkit/README.md) with googleai_dart-specific configuration.

Create GitHub issues from TASK-???.md files. Use when you need to bulk-create GitHub issues from task markdown files with frontmatter containing title, label, parent, and project attributes. Automatically extracts frontmatter, creates issues via gh CLI, links parent issues, and adds to specified projects.

Generate the next sequential file or folder name for directories with numbered prefixes (e.g., 01-setup.md, 02-init.md). Use when creating a new file or folder that should follow an existing numbering sequence, when adding to a sequentially-named series, or when the user asks for the "next" numbered item in a directory.

Convert repository-relative paths to absolute GitHub URLs for use in documentation.

Generate task files from decomposer output and architect responses. Use when you need to create TASK-*.md files from structured JSON containing task metadata and LLD content.

Expert guidance for Claude Code plugin development. Use when creating or modifying plugins, working with plugin.json or marketplace.json, or adding commands, agents, Skills, or hooks.

Instrument agent tool executions with proper context and error handling

Bidirectional sync between Markdown and Notion. Upload .md files with images to Notion pages/databases, append to existing pages, or download Notion content back to markdown. Supports rich formatting, tables, code blocks, GitHub-flavored markdown, and recursive page hierarchy downloads with YAML frontmatter for round-trip sync.

Hidden quality gate that runs before showing "Done!" to user - ensures all tests pass, build succeeds, and requirements met before claiming completion

Manage Temporal workflows: server lifecycle, worker processes, workflow execution, monitoring, and troubleshooting for Python SDK with temporal server start-dev.

Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.

Use this skill when working with Graphite (gt) for stacked PRs, when the user mentions pull requests, Graphite, stacking, or gt commands. Ensures proper use of gt commands instead of raw git for stack-aware operations.

Registers error mappings for new domain errors to ensure proper HTTP response conversion.

Creates a versioned ASP.NET Core API endpoint following project conventions including error mapping, Result pattern, and proper HTTP semantics.

Creates a Provider class that orchestrates business logic by coordinating multiple services. Providers sit between Controllers and Services in the architecture.

This skill should be used when building web applications where an AI agent dynamically generates HTML UI, using the hexagonal/ports-and-adapters architecture with HTMX for interactivity and MCP tools for data operations.

Configure Claude Code permissions to control tool access and protect sensitive files.

Configure Claude Code hooks to control Clauduino Status LED indicator. Use when users need to: (1) Set up ~/.claude/settings.json hooks, (2) Configure device IP address, (3) Add sound notifications (macOS), (4) Test hook execution with /hooks command, (5) Troubleshoot hook triggers.

Streamline firmware upload for Clauduino Status ESP8266/ESP32 boards. Use when users need to: (1) Upload firmware/claude_code_led/claude_code_led.ino, (2) Configure Arduino IDE for ESP boards, (3) Set up board manager URLs, (4) Verify serial output at 115200 baud, (5) Troubleshoot upload failures.

Apply Roberto Rodriguez's threat hunting methodology with the Threat Hunter Playbook and HELK. Emphasizes documented hunts, open source infrastructure, and data-driven hunting. Use when building hunting programs or developing hunt playbooks.

Apply David Bianco's threat hunting frameworks including the Pyramid of Pain and Threat Hunting Maturity Model. Emphasizes prioritizing detection by adversary cost and building mature hunting programs. Use when designing detection strategies or assessing hunting capability.

Write Go code in the style of Robert Griesemer, co-creator of Go. Emphasizes clean syntax, precise semantics, and well-defined type system behavior. Use when designing APIs, type hierarchies, or code that requires precise specification.

Homebridge plugin development - scaffolding, HAP mappings, config schemas, debugging

Profile the Rust simulation engine to identify performance bottlenecks. Use when optimizing engine performance or investigating slow code paths.

Export patterns and barrel file conventions. Use when creating/modifying index.ts files or organizing module exports.

Agent Skill: PHP 8.x modernization patterns. Use when upgrading to PHP 8.1/8.2/8.3/8.4/8.5, implementing type safety, or achieving PHPStan level 10. By Netresearch.

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.

ClaudeSprint uses a **dual-loop architecture**:

Use when configuring ESLint - covers flat config, TypeScript integration, and custom rules

Use when creating Docusaurus plugins (remark, rehype, theme, content, lifecycle) to extend markdown, modify HTML, or add custom functionality

Fetch and analyze Readwise reading activity for any date range. Use when user asks about articles saved, highlights created, or most-highlighted content for today, yesterday, last week, last month, or custom date ranges (e.g., "show my Readwise activity from Jan 1-7"). Requires READWISE_API_TOKEN env var. Connects to Readwise Highlights API (v2) and Reader API (v3).

Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

No description available

Guide the user through the process of releasing a new version of the da_vinci packages.

The plugin manager supports five operations:

Generate images using Google's Gemini API. Use this skill when the user wants to generate, create, or edit images with AI. Keywords: image generation, create image, generate picture, AI art, edit image, Gemini, icon, render, illustration.

Teaches AI agents to properly manage VS Code terminal lifecycle — always use background terminals and kill them after commands complete. Prevents zombie terminal accumulation in GitHub Codespaces and VS Code.

Organize agent workspace knowledge using PARA method (Projects, Areas, Resources, Archives) with daily memory logs. Use when setting up a new workspace, reorganizing files, filing completed work, or doing periodic memory maintenance.

Use when creating new skills, editing existing skills, or verifying skills work before deployment. TDD applied to process documentation.

Detached PTY sessions — launch commands in a real pseudo-terminal, attach/view/record later. Use when: launching agents or processes that need a real TTY but should run detached, supervising running agents, recording terminal sessions, viewing agent output. Triggers: detached terminal, background agent, attach to session, view terminal, record session, holdpty.

Bootstrap a Vers VM into a golden image with pi, Node.js, dev tools, and swarm extensions installed. Creates a committed snapshot that can be branched for self-organizing agent swarms.

Control Arduino/ESP32 hardware — GPIO, servos, sensors, cameras

Unity C# 코드 작성 및 수정 시 적용하는 스타일 규칙. C# 파일(.cs)을 생성하거나 수정할 때 사용. BSD 중괄호, 한국어 주석, region 구조, 네이밍 규칙 등을 포함. Use when writing, editing, or reviewing C# code files.

This skill should be used when the conversation involves Metal compute pipeline architecture, command buffer lifecycle, compute command encoders, dispatch patterns, pipeline state management, argument buffers, resource heaps, indirect command buffers, synchronization primitives, or Metal 4 unified encoder features. Trigger keywords: MTLComputePipelineState, MTLCommandQueue, MTLComputeCommandEncoder, dispatchThreadgroups, indirect dispatch, hazard tracking, memory barriers, command buffer batching, GPU timeout, Metal 4 barriers.

Use when Claude Code needs to communicate with an OpenClaw agent running on the same machine or a remote host via WebSocket gateway. Triggers: (1) sending messages or tasks to an OpenClaw agent, (2) injecting context into an agent's session without triggering a run, (3) checking gateway status or listing sessions, (4) reading an agent's conversation history, (5) aborting a running agent, (6) managing cron jobs. Covers WebSocket authentication (protocol v3, token auth), session key targeting, and a bundled Node.js bridge script.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always. 中文触发场景：当声明工作完成之前、提交代码前、创建 PR 前，必须先验证并提供证据。

Transcribes audio to text with timestamps and optional speaker identification. Use when you need to convert speech to text, create subtitles, transcribe meetings, or process voice recordings.

Agent-first media toolkit for image, video, and audio processing. Use when you need to resize, convert, generate images, remove backgrounds, extract audio, transcribe speech, or generate videos. All commands return deterministic JSON output.

Ensures consistent use of X-components design system instead of Material3 when working on feature UI code. Automatically activates for Composable functions in feature modules or when user mentions UI/screens/components.

Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.

Use when creating Docusaurus plugins (remark, rehype, theme, content, lifecycle) to extend markdown, modify HTML, or add custom functionality

Helps develop and build Docusaurus plugins using this starter template

Generate data layer code (Freezed DTOs, repository implementations, data sources) from feature specifications or API references. Creates the bridge between domain entities and external data sources. Use after /domain to implement the data layer.

In-app purchases and subscriptions with RevenueCat. Product configuration, entitlements, paywalls, restore purchases, subscription status. Use when implementing subscriptions, one-time purchases, paywalls, or monetization.

Generate presentation layer code (Freezed states, Riverpod notifiers, screens, widgets) from feature specifications. Creates the UI layer with proper state management. Use after /data to implement screens and state handling.

Initialize new feature with Clean Architecture folder structure and skeleton files. Creates scaffold for domain, data, and presentation layers with TODOs. Use AFTER /plan to create the initial structure, then run /domain and /data to fill in details.

Analytics and crash reporting with Firebase Analytics, Crashlytics, Sentry, or PostHog. Event tracking, user properties, screen views, crash reports, error logging. Plug-and-play provider architecture. Use when implementing analytics, crash reporting, or switching providers.

Initialize a new Flutter project. Gathers requirements, runs flutter create, adds dependencies, configures environment, and sets up main.dart. Run this first when creating a new app.

Push notifications with Firebase Cloud Messaging (FCM). Platform setup, APNs certificates, foreground/background handling, deep linking, topic subscriptions, local notifications. Use when implementing push notifications or troubleshooting FCM.

Standard conventions for designing, implementing, releasing, and distributing Tim’s macOS/Unix CLI tools (especially those published via Homebrew). Use when creating a new CLI tool, reviewing CLI UX, or upgrading existing tools to a consistent standard.

Node.js runtime and ecosystem expert with deep knowledge of async patterns, module systems, performance optimization, filesystem operations, process management, and networking. Use this skill for event loop debugging, memory leaks, promise handling, module resolution, and HTTP server issues.

Agent Skill: Security audit patterns for PHP/OWASP. Use when conducting security assessments, identifying vulnerabilities (XXE, SQL injection, XSS), or CVSS scoring. By Netresearch.

とまだの文字起こし・音声入力（Whisper等）の誤変換・誤字脱字を自動修正するスキル。AI駆動開発、Claude Code、MCP、プログラミング用語の誤変換を専門的に修正。「文字起こしを修正」「誤変換を直して」「誤字脱字を修正」「音声入力を整理」「テキストをクリーンアップ」「変換ミスを直して」と言われたときに使用。Obsidianノートの文字起こし整理、技術用語の表記統一に最適。Use PROACTIVELY when fixing transcriptions, correcting voice input errors, or cleaning up Whisper output.

Synchronizes documentation (README.md, CHANGELOG.md, API docs) with implementation. Preserves user content outside speckit markers. Updates are non-destructive and clearly delineated. Always run after /speckit.implement completes.

MANDATORY for creating Zustand stores. This skill is required when users request state management, creating stores, or mention Zustand. Do NOT create Zustand stores without this skill - all stores must use the required StoreBuilder pattern with immer middleware and factory pattern separation

Read and extract content from EPUB ebook files. Use this skill when the user wants to read an EPUB file, extract text from an ebook, view EPUB metadata (title, author), list chapters or table of contents, search within EPUB content, or analyze ebook content.

TypeScript Language Server Protocol capabilities for navigating TypeScript/JavaScript code. Resolves imported symbols to their definitions (including node_modules), finds all references to functions/classes/variables, gets type information and signatures, previews rename impacts, and checks TypeScript diagnostics. Use when you need to find where ToolLoopAgent or other imports are defined, locate all usages of a function, see TypeScript types, or get compiler errors.

멀티 스테이지 빌드(multi-stage builds), docker-compose 오케스트레이션, 이미지 최적화, 디버깅 및 운영 모범 사례를 포함하는 포괄적인 Docker 컨테이너화 워크플로우입니다. 애플리케이션 컨테이너화, 개발 환경 구축 또는 Docker 배포 시 사용합니다.

Use dtctl CLI tool for querying observability data in Dynatrace via DQL (logs, metrics, traces, ...) and to manage Dynatrace platform resources (workflows, dashboards, notebooks, SLOs, settings, buckets, lookup tables).

Interactive tutorial to master Claude Code. Use when user wants to learn Claude Code, understand how to use it effectively, or become a power user. Takes users through progressive hands-on exercises covering all features - from basic file operations to creating skills, hooks, MCP setup, and context management. 13 comprehensive modules with gamified achievements.

Create or update Playwright end-to-end tests for the Product Agents frontend in this repo, especially for settings validation, conversation artifact visibility, research plan approval/rejection, and clarifying-question flows. Use when asked to write, expand, or run Playwright tests for frontend/product-agent (including live E2E runs gated by E2E_LIVE).

Discover, create, and validate headless adapters for agent integration. Includes scaffolding tools and compliance testing for the Agent Client Protocol.

Validate skill directories against AgentSkills spec

CLI tool for capturing agent trajectories. Execute prompts against headless CLI agents via schema-driven adapters, capture full trajectories (tools, thoughts, plans), and output structured JSONL for downstream scoring.

Generate and update comprehensive documentation from workspace data sources, including code repositories, text files, and media assets. Use this skill when the user requests to: (1) create or generate documentation from code or files, (2) build document structure or details, (3) update, modify, or improve existing documentation, (4) rewrite specific sections or paragraphs, (5) process changeset files or PATCH-marked modification requests. Supports technical documentation, user guides, API references, and general documentation needs.

Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Activate for writing high-converting copy, crafting headlines, email campaigns, landing pages, or applying custom writing styles from assets/writing-styles/ directory.

Design schemas, write queries for MongoDB and PostgreSQL. Use for database design, SQL/NoSQL queries, aggregation pipelines, indexes, migrations, replication, performance optimization, psql CLI.

Build 3D web apps with Three.js (WebGL/WebGPU). Use for 3D scenes, animations, custom shaders, PBR materials, VR/XR experiences, games, data visualizations, product configurators.

View markdown files with calm, book-like reading experience via HTTP server. Use for long-form content, documentation preview, novel reading, report viewing, distraction-free reading.

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

Create, edit, analyze .docx Word documents. Use for document creation, tracked changes, comments, formatting preservation, text extraction, template modification.

Run safe diagnostic commands on the remote memory server. Use for checking logs, container status, disk usage, memory, and running read-only database queries.

Deploy the memory application to the remote server. Use when deploying code, syncing changes, restarting services, or running commands on the production server.

Best practices for creating, optimizing, and deploying MCP servers to Smithery. Use this skill when: (1) Creating new MCP servers for Smithery deployment (2) Optimizing quality scores (achieving 90/100) (3) Troubleshooting deployment issues (0/0 tools, missing annotations, low scores) (4) Migrating existing MCP servers to Smithery format (5) Understanding Smithery's schema format requirements (6) Adding workflow prompts, tool annotations, or documentation resources (7) Configuring smithery.yaml and package.json for deployment

Use when profiling native macOS or iOS apps with Instruments/xctrace. Covers correct binary selection, CLI arguments, exports, and common gotchas.

Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.

规范类型项目（apps/type）的代码组织方式、导出语法和文件结构。用于解决类型导出冲突、创建统一导出入口、处理重复导出等问题。适用于类型项目开发、类型错误修复、代码规范实施场景。在处理类型项目的代码写法时，请使用本技能。

Reasoning and Acting patterns for agentic LLM workflows

Core prompt design patterns and templates for effective LLM communication

Create and manage data pipelines using the FlowerPower framework with Hamilton DAGs and uv. Use when users request creating flowerpower projects, pipelines, Hamilton dataflows, or ask about flowerpower configuration, execution, or CLI commands.