AI Skills Hub - Browse 180,000+ Agent Skills

Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).

Research profitable Amazon KDP categories for book publishing. This skill should be used when planning a book launch, analyzing competition, or optimizing category selection for discoverability. Guides the 3-category decision with BSR analysis and ghost category avoidance.

Claude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets), and refactor existing Skills for clarity, activation reliability, and quality gates.

Use when asked to add secret scanning, install git hooks, protect against committing API keys/passwords/tokens, set up security for a repo, or after running git clone on a new repository.

Day-to-day Renode development workflow for TMNL: .resc edits, firmware swaps, UART verification, and troubleshooting.

生成したAIニュースレターをMicrosoft Teamsに自動配信するスキル。 Incoming WebhookまたはGraph APIを使用して、指定されたチャンネルに投稿します。 Adaptive Cards形式でリッチな表示が可能です。 このスキルは「Teamsに投稿して」「ニュースレターを配信して」といったプロンプトで呼び出されます。

Use the VSCode CLI to open files at specific line and column positions when explaining code, debugging, pointing to TODOs, or guiding users to specific locations in files. Automatically invoked when Claude needs to show users exactly where in a file to look.

Automated video editing using FFmpeg. Use when trimming videos, merging clips, adding audio, or automating video production workflows.

AI-powered audio and video transcription using OpenAI Whisper or AssemblyAI. Use when converting recordings to text, generating subtitles, or creating searchable transcripts.

Guidelines for maintaining structured, RAG-optimized documentation and module metadata.

御見積書を作成するスキル。クライアント名、件名、項目、単価(原価)、粗利率から見積書を生成します。日付、支払条件などの情報も扱います。

Use when working with VueUse composables - provides reactive utilities for state, browser APIs, sensors, network, animations. Check VueUse before writing custom composables - most patterns already implemented.

Trade and monitor Hyperliquid perpetual futures. Check balances, view positions with P&L, place/cancel orders, execute market trades. Use when the user asks about Hyperliquid trading, portfolio status, crypto positions, or wants to execute trades on Hyperliquid.

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.

Convert .txt book files into leverageable Claude Code skills. Use when transforming books, articles, or written expertise into structured skills with frameworks, workflows, and reference material.

Systematically consume QA quality gate outputs and apply prioritized fixes for high-severity issues, NFR failures, and test coverage gaps. Use when quality review identifies issues requiring remediation.

Execute tests with coverage analysis using bmad-commands, identify coverage gaps, and suggest missing tests. This skill should be used for test execution and quality validation.

Manages crypto wallets, transfers tokens, swaps on DEXes, checks balances, and accesses paid APIs (search, image gen, prediction markets, web scraping, document parsing, sales prospecting) via x402 micropayments. Use when the user asks about wallet balances, token transfers, swaps, blockchain payments, or paid API services.

Kurocoドキュメントの検索・参照ガイド。使用キーワード：「Kurocoドキュメント」「Kuroco公式」「ドキュメント検索」「マニュアル」「チュートリアル」「リファレンス」「使い方」「やり方」「設定方法」「実装方法」「Kurocoヘルプ」「Kuroco仕様」「公式ガイド」「ドキュメント同期」「Kurocoの○○はどうやる」「Kurocoで○○したい」。ドキュメントから情報を探す場合に使用。

使用 Playwright 与本地 Web 应用程序交互并进行测试的工具包。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。

Check for Node.js and npm package updates in deep-interviewer. Handles Node.js LTS major version upgrades with compatibility checks, categorizes package updates by severity (patch/minor/major), and creates update PRs. Use when user asks to check for updates, upgrade dependencies, or review what packages need updating.

Convert GSD codebase mapping to Autocoder app_spec.txt. This skill should be used when the user has run /gsd:map-codebase and wants to use Autocoder on an existing project. Triggers: "convert to autocoder", "gsd to spec", "create app_spec from codebase", "use autocoder on existing project", after /gsd:map-codebase completion.

Use the Opper CLI (oppercli) for terminal-based AI task completion, function management, knowledge base operations, model configuration, trace inspection, and usage analytics. Activate when users want to call Opper functions from the command line, manage indexes, inspect traces, track costs, or configure models via terminal.

Automate first-pass customization of a new ShipAny (ShipAny Two) project from a short project brief (app name, domain/app URL, product description/features, reference links, and branding preferences). Use when the user says they are starting a new project.

Create reproducible replication packages using rix/nix for R projects. Use when setting up project environments, preparing code for journal submission, or ensuring computational reproducibility. Covers rix, nix-shell, Makefile pipelines, and DCAS-compliant 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.

Fetch metadata and transcripts from Apple Voice Memos synced via iCloud. Use when the user wants to list, search, or read voice memos.

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.

TikHub WeChat Channels (视频号) API workflow: search users by keyword, fetch a user home page/video list, download the latest video, and decrypt it into a playable MP4 using decode_key + local decrypt API. Use when integrating or troubleshooting TikHub WeChat Channels endpoints or turning a username/keyword into a playable video file.

Review recent changes - run all validators and report status

调用魔搭社区（ModelScope）Qwen3-VL 多模态 API 进行视觉解析。使用 OpenAI SDK 兼容方式调用，支持图片内容描述、OCR 文字提取、视觉问答、对象检测等功能。用户提到"魔搭"、"ModelScope"、"Qwen-VL"、"多模态视觉"、"解析图片"等关键词时应触发。

Decompose a spec, plan, or text description into structured task graph JSON, validate it against the Structured Task Template Spec, and record the tasks as Beads issues. Use when the user wants to break down work into trackable, validated tasks.

Manage dotfiles - installation, updates, adding configs, troubleshooting symlinks. Use when asked about dotfiles, system config, or shell setup.

Ask natural language questions about your data. Handles "what tables contain", "tell me about", "explain", "what do you know about", "describe".

Create, review, and maintain Claude Code skills. Use when creating new skills, auditing existing skills, understanding skill vs command vs agent patterns, or when the user mentions skill development, SKILL.md files, or skill best practices.

Generate synchronized VS Code + Obsidian themes from color palettes. Use when user asks about themes, colors, or visual customization.

Generating printable Goal Bingo cards for gamified goal tracking. Use when user asks to create, generate, or print bingo cards, mentions "goal bingo", wants to track annual or monthly goals with bingo format, or needs to update bingo goal completion status.

Apply resilience patterns for enterprise services (timeouts, retries with backoff+jitter, idempotency, circuit breakers, bulkheads/concurrency limits, safe fallbacks). Use when adding/refactoring outbound calls, consumers/jobs, retry behavior, or hardening a service against partial failures and flaky dependencies.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

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.

Enable agents and skills to challenge users for fresh two-factor authentication proof (TOTP or YubiKey) before executing sensitive actions. Use this for identity verification in approval workflows - deploy commands, financial operations, data access, admin operations, and change control.

Verify VitalArc Xcode project builds successfully. Use automatically before commits, after code changes, or when the user asks to check the build. Reports errors clearly and suggests fixes.

Display real-time progress visualization during long operations. Shows task status, progress bars, and estimated completion. Use during feature planning, multi-file operations, or any long-running task.

Check API keys, entitlements, and build settings. Reports configuration status and missing requirements. Read-only, works on both platforms.

Creates demo pages for research techniques with full frontend 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.

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.

rsync 文件同步与备份

既存のスライドプレゼンテーション（public/slides.json）に1枚のスライドを追加する。ユーザーがスライドの追加、ページ追加、スライド1枚追加を依頼したときに使用する。

スライドプレゼンテーション用のアドオンコンポーネントを新規作成する。ユーザーがアドオンの作成、カスタムコンポーネントの追加、ビジュアルコンポーネントの作成を依頼したときに使用する。

Download and install Claude Code skills from various sources. Supports GitHub repositories, compressed archives (.zip, .tar.gz, .skill), and direct URLs. Use when user wants to download, install, or add a skill from GitHub, URL, or archive file. Triggers on "download skill", "install skill", "add skill from", "get skill".

Deploy any project to Vercel instantly. No authentication required.

Create new dynamic pages from a short spec (keywords, route/path, reference content).

Automate first-pass customization of a new ShipAny (ShipAny Two) project from a short project brief (app name, domain/app URL, product description/features, reference links, and branding preferences). Use when the user says they are starting a new project.

Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before releasing openai-agents-python.

DEPRECATED - Use browsing-bluesky skill instead. Sample and analyze Bluesky firehose to identify trending topics and content clusters. Use when user asks about "what's happening on Bluesky", "Bluesky trends", "zeitgeist", "firehose analysis", or wants to see real-time topic clusters from the network.

Universal environment variable loader for AI agent environments. Loads secrets and config from Claude.ai, Claude Code, OpenAI Codex, Jules, and standard .env files.

Clone websites locally for study and analysis. Use when users ask to replicate, clone, mirror, download, or save a website for studying its structure, design, CSS, JavaScript, or overall architecture. Also use when asked to analyze a website's code structure or create an offline copy of a site.

How to debug tursodb using Bytecode comparison, logging, ThreadSanitizer, deterministic simulation, and corruption analysis tools

AT START OF EVERY TURN: Update avatar state in ~/.clawface/avatar_state.json. Flow: thinking→action→speaking→idle. Check if avatar running (pgrep -f avatar.py). If not running and user on main machine, offer to start. ALWAYS reflect current action in avatar state - this is your face!

Use the NanoBazaar Relay to search offers, create jobs, attach charges, and exchange encrypted payloads.

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.

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

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.

Guide for building Raspberry Pi development images locally using the 'act' tool inside the devcontainer.

Scan networks to discover devices, gather MAC addresses, vendors, and hostnames. Includes safety checks to prevent accidental scanning of public networks.

Rate-limited parallel execution patterns for LLM APIs and web services. Use when you need to prevent 429 errors and optimize throughput.

Manage the fakoli-plugins marketplace: add/remove plugins, validate manifests, and regenerate registry indices.

Guide for creating effective skills. Use when creating a new skill, updating an existing skill, or extending Claude's capabilities with specialized knowledge, workflows, or tool integrations. Triggers on requests involving skill development, skill architecture, or reusable automation.

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

Execute read-only SQL queries against PostgreSQL databases. Use when: (1) querying PostgreSQL data, (2) exploring schemas/tables, (3) running SELECT queries for analysis, (4) checking database contents. Supports multiple database connections with descriptions for auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.

Manage Gandi domains, DNS, email, and SSL certificates via the Gandi API

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.

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.

List all active sessions in the Workstation. This skill is for the Manager session inside Workstation app. If you're in a standalone Claude Code session, suggest the user open the Workstation app and use this skill from the Manager terminal.

Auto-route a message to the best matching session based on repo name, task ID, or context. This skill is for the Manager session inside Workstation app. If you're in a standalone Claude Code session, suggest the user open the Workstation app and use this skill from the Manager terminal.

Show token usage statistics across sessions. Use when you want to understand resource consumption or usage patterns.

Show detailed status of a specific project by reading its archive, project_plan, and issues. Use for deep dive into one project's state.

Send a message/command to a specific session by ID. This skill is for the Manager session inside Workstation app. If you're in a standalone Claude Code session, suggest the user open the Workstation app and use this skill from the Manager terminal.

Scan for new project repos and add them to the Manager's project index. Use when you want to discover repos that aren't yet tracked.

Connect a Feishu (Lark) bot to OpenClaw via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a messaging channel, troubleshooting the Feishu bridge, or managing the bridge service (start/stop/logs). Covers bot creation on Feishu Open Platform, credential setup, bridge startup, systemd/launchd auto-restart, and group chat behavior tuning.

Comprehensive git worktree patterns for parallel development, environment isolation, and workflow optimization. Use when setting up worktrees, managing multiple branches, configuring isolated environments, or optimizing development workflows.

Extract structured data from websites using Tabstack API. Use when you need to scrape job listings, news articles, product pages, or any structured web content. Provides JSON schema-based extraction and clean markdown conversion. Requires TABSTACK_API_KEY environment variable.

Python testing best practices covering pytest, unittest.mock, property-based testing with Hypothesis, fixtures, and mocking patterns

Exa.ai search API integration for neural and keyword web search with content retrieval. Use when implementing web search features, integrating Exa SDK (exa_py, exa-js), or retrieving web content. Triggers on: Exa, exa_py, exa-js, neural search, web search API, search_and_contents, searchAndContents, find_similar, findSimilar, domain filtering, date filtering, text extraction, page summaries, highlights, search auto mode, fast search, search categories, livecrawl, excluding domains, include text, exclude text, EXA_API_KEY.

Svelte 5 runes, snippets, SvelteKit patterns, and modern best practices for TypeScript and component development. Use when writing, reviewing, or refactoring Svelte 5 components and SvelteKit applications. Triggers on: Svelte components, runes ($state, $derived, $effect, $props, $bindable, $inspect), snippets ({#snippet}, {@render}), event handling, SvelteKit data loading, form actions, Svelte 4 to Svelte 5 migration, store to rune migration, slots to snippets migration, TypeScript props typing, generic components, SSR state isolation, performance optimization, or component testing.

This skill provides patterns and guidelines for backend development in the my-juntas-app project, a Next.js application with MongoDB/Mongoose for database operations.

Comprehensive frontend architecture analyzer that identifies technology stacks, build tools, and architectural patterns. Use when you need to quickly understand a project's structure, dependencies, and technical configuration. Provides analysis for Vue/React/Angular frameworks, Node.js environments, package managers, TypeScript usage, linters, and architecture patterns with multiple output formats including executive summaries and visualizations.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Generates section list for a page. Deterministic mapping. Does not write content.

Multi-step calculator UI for Astro. Quote tools, pricing calculators. Uses astro-forms for backend.

Form infrastructure for Astro. Zod validation, email, rate limiting, Turnstile, GDPR, Sheets. FAIL = no conversion.

Deployment workflow for Astro sites on Cloudflare Pages + GitHub. Staging → Production flow. Use before first deploy.

Extracts marketing elements from competitor websites. Structured observation only. Does not write copy or make recommendations.

Generates H1-H4 heading structure for a page. SEO-optimized hierarchy. Stateless, deterministic.

Local SEO dominance system for UK service businesses. FAIL/PASS enforcement. GBP + area pages + reviews.

UI component library for Astro lead generation sites. Buttons, forms, cards, badges. Requires design-tokens skill.

Required legal pages for UK/HU lead generation websites. Privacy Policy, Cookie Policy. GDPR compliant. Bilingual templates (EN/HU).

Security patterns for Astro lead generation websites on Cloudflare. Forms, headers, bot protection, GDPR. Use for any production lead gen site.