AI Skills Hub - Browse 180,000+ Agent Skills

Quality-check Starlifter docs for broken links, missing sidebar entries, asset paths, and consistency after edits.

Generate videos using Flyworks (a.k.a HiFly) Digital Humans. Create talking photo videos from images, use public avatars with TTS, or clone voices for custom audio.

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.

YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video

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.

Spawn a new Claude Code tmux session as a subagent worker

Parse Pentaho XML files (.ktr/.kjb) and extract structured metadata for DBT migration

Frontend end-to-end feature testing using Playwright with Chrome. Opens Chrome browser, interacts with web pages based on feature requirements, captures screenshots at key points, analyzes results visually, and cleans up screenshots after successful verification. Use this skill when asked to test a web application feature end-to-end, verify UI functionality by interacting with and screenshotting a page, automate browser testing with visual verification, check if a frontend feature works correctly, or debug UI issues by capturing screenshots during interaction.

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.

ALWAYS use this skill immediately after running 'ansible-galaxy init' to create a new Ansible role. Also use when the user asks to fix ansible-lint errors or when ansible-lint output shows fixable issues like yaml[comments], schema[meta], meta-incorrect, name[play], or role-name[path] violations.

Trigger when: (1) User mentions "manim" or "Manim Community" or "ManimCE", (2) Code contains `from manim import *`, (3) User runs `manim` CLI commands, (4) Working with Scene, MathTex, Create(), or ManimCE-specific classes. Best practices for Manim Community Edition - the community-maintained Python animation engine. Covers Scene structure, animations, LaTeX/MathTex, 3D with ThreeDScene, camera control, styling, and CLI usage. NOT for ManimGL/3b1b version (which uses `manimlib` imports and `manimgl` CLI).

Use when user needs to convert project documentation (websites, GitHub repos, PDFs) into Claude skills. Triggers on "create a skill from docs", "codify documentation", "convert [framework] docs to skill", or "make this documentation searchable for Claude". Handles documentation scraping, GitHub analysis, PDF extraction, and multi-source unification.

Generate SEO-compliant Etsy listing copy with deterministic validation of title, tags, description, and brand voice integration.

This skill should be used when the user asks to 'create a page', 'add a route', 'create a layout', 'add metadata', or 'set up a dynamic route'. Provides guidance for Next.js 15 App Router pages, layouts, and route handlers in app/**/*.tsx.

driver-to-navigator collaboration using `pp` (send messages, attach files, download artifacts). the driver (agent) must collaborate with the navigator to solve problems.

Creates validated .athena import packages for the Athena note-taking app. This skill should be used when the user wants to send notes, research results, or documents back into Athena, when packaging conversation results for Athena, or at the end of an athena-work processing session. Produces ZIP packages conforming to the .athena import specification with manifest, markdown notes, aurora tags, and optional assets.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

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.

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

Execute efficient Google Ads GAQL queries with correct field names and token optimization. Handles campaign analysis, shopping performance, creative extraction, and ROAS calculations. Triggers: Google Ads, GAQL query, campaign metrics, ad performance, shopping feed, ROAS.

This skill should be used when the user says "let's land the plane", "land the plane", "end the session cleanly", "wrap up the session", or asks to prepare for a clean handoff between coding sessions. Provides a systematic protocol for ensuring all work is committed, tested, tracked, and ready for the next session.

Guide for integrating and configuring premailer-rails gem in Rails applications to automatically convert CSS to inline styles for HTML emails. Use when working with Rails ActionMailer and email styling, setting up email CSS inlining, configuring premailer options, troubleshooting email rendering issues across email clients (Gmail, Outlook, Apple Mail), or when users mention premailer-rails, CSS inline styles, or email compatibility problems.

Search Twitter/X posts using Twitter API v2. Use when user wants to search for tweets, find trending topics, monitor keywords, check competitor activity, or analyze social media content. Supports keyword search with automatic rate limiting (Basic plan 10,000 posts/month).

HTMLモックアップからPNG画像を生成するスキル。 Playwrightを使用して高品質なスクリーンショットを作成し、画面設計書用の画像を自動生成します。

Search, discover, and dynamically load skills from the ClawHub registry at skills.droyd.ai. Use when an agent needs a capability it doesn't have, wants to find tools for a specific task, or needs to browse trending/popular skills. Triggers include requests to find skills, search for tools, discover capabilities, load a skill dynamically, check what skills exist for a domain, or run a skill without installing it. Also use when the user asks about available OpenClaw/ClawHub skills, wants to explore skill categories, or needs to fetch and execute skill content on the fly.

This skill validates environment configuration against baseline. Triggers on "check my config", "sync config", "validate environment", "check environment", or "is my environment set up correctly". Provides environment validation and auto-remediation for plugin dependencies and CLI tools.

Build with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when developing a scalable or distributed database/application or user requests DSQL.

Schedules Claude Code tasks to run automatically at specific times using native OS schedulers (launchd on macOS, crontab on Linux, Task Scheduler on Windows). Handles one-time tasks like "today at 3pm remind me to deploy", "tomorrow morning run the test suite", "next Tuesday at 2pm review the API changes", "January 15th check the quarterly metrics". Also handles recurring tasks like "every weekday at 9am review yesterday's code", "daily at 6pm summarize what I accomplished", "every Monday at 10am check for security vulnerabilities", "every 4 hours check API health". Recognizes time formats like "at 9am", "at 1015am", "at 10:30pm", "at noon", relative times like "tomorrow", "tonight", "later", "next week", and dates like "January 15th". Use this skill instead of executing immediately whenever the user's request contains a time expression like "at Xam", "tomorrow", or any future time reference.

Build or upgrade OpenClaw plugins/extensions end-to-end from one request. Use when asked to create, modify, scaffold, debug, test, or enable OpenClaw plugins, including plugin commands, agent tools, gateway methods, services, channels, provider-auth flows, plugin manifests, plugin config schemas/uiHints, and plugin allowlist wiring.

Create modular capability packages that extend Claude's functionality through specialized knowledge, workflows, and tool integrations.

AI image generation with OpenAI and Google APIs. Supports text-to-image, reference images, aspect ratios, and parallel generation (recommended 4 concurrent subagents). Use when user asks to generate, create, or draw images.

認証・認可システム全般。JWT認証、セッション管理、権限チェック、IP Trust評価を提供。 【WHEN to use】 - 認証機能の実装・拡張時 - 権限チェックの実装時 - ログイン/ログアウトフロー修正時 - セキュリティ強化時 【WHEN NOT to use】 - 認証以外の機能開発 - 単なるコンポーネント確認（foundation-components使用） 【TRIGGER keywords】 認証、ログイン、JWT、セッション、権限、パーミッション、OAuth、RBAC

dashboard-acceleratorテンプレートが提供する統一エラーハンドリングシステム。 Backend (Encore.dev) と Frontend (SvelteKit) を統合したエラー処理を提供。 【WHEN to use】 - エラー処理実装時 - エラーコード追加時 - エラーフロー調査時 - Sentry統合時 【TRIGGER keywords】 エラー、エラーハンドリング、APIError、try-catch、Sentry、トースト、エラーコード

Java backend patterns for Opik. Use when working in apps/opik-backend, designing APIs, database operations, or services.

Local development environment setup and commands. Use when helping with dev server, Docker, or local testing.

Create and deploy single-page static websites to GitHub Pages with autonomous workflow. Use when building portfolio sites, CV pages, landing pages, or any static web project that needs GitHub Pages deployment. Handles complete workflow from project initialization to live deployment with GitHub Actions automation.

使用 Playwright 与本地 Web 应用交互与测试。支持验证前端功能、调试 UI、截图、查看浏览器日志。当需要测试本地 Web 应用时使用。

提供 React Native 性能优化指南，涵盖 FPS、TTI、打包体积、内存泄漏、重渲染与动画。适用于涉及 Hermes 优化、JS 线程阻塞、桥接开销、FlashList、原生模块或调试卡顿与掉帧的任务。

Create educational documents that build understanding progressively with citations

Build a variant using locally published kits for development validation

Add a new real-world agent case study to the awesome-agent-examples repository. Use when the user wants to add a new agent example, case study, or contribute an implementation to the repository. Handles research, file creation, git workflow, and PR creation. (project)

Configures Neon Serverless Driver for Next.js, Vercel Edge Functions, AWS Lambda, and other serverless environments. Installs @neondatabase/serverless, sets up environment variables, and creates working API route examples with TypeScript types. Use when users need to connect their application to Neon, fetch or query data from a Neon database, integrate Neon with Next.js or serverless frameworks, or set up database access in edge/serverless environments where traditional PostgreSQL clients don't work.

Create structured session logs documenting work done in a Claude Code conversation. Use at end of development sessions, when context is approaching limits, when switching focus areas, or when the user says "log session", "create session log", or "document this session". Captures decisions, learnings, files modified, and handoff documentation.

This skill should be used when you need to know what members, methods, or extensions are available on Kotlin types. It queries autocomplete metadata generated by the kotlin-autocomplete-gradle-plugin.

Submit and monitor .NET MAUI unit tests on Helix infrastructure. Supports running XAML, Resizetizer, Core, Essentials, and other unit test projects on distributed Helix queues.

Systematic workflow for AST-based mass edits in Python codebases. Use when editing 3+ files with structural changes (decorators, function signatures, imports, class definitions). Includes pre-surveying with grep/pyright, idempotent transformations, and validation protocol. NOT for simple string replacements or <5 instances.

Debug type errors in uv-managed Python projects by accessing true pyright diagnostics. Use when IDE shows type errors but standalone pyright reports 0 errors, or when systematic analysis of type errors is needed before mass edits. Critical for projects using pydantic models where Field() defaults may not be properly inferred.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

OpenClaw complete backup, restore, and update with automatic rollback support. Use when backing up OpenClaw configuration, workspace, and skills; restoring from backup; updating OpenClaw with rollback protection; or managing OpenClaw disaster recovery.

Default to local Supabase when a project has supabase/config.toml. Use when encountering Supabase-related work to detect local configuration and prefer it over remote MCP tools. Provides local-first decision tree with port discovery and environment variable extraction.

Use when generating Claude Code insights reports, usage analytics dashboards, or when the user runs /insights-ui command. Creates beautiful dark-themed HTML dashboards with charts and metrics.

This skill should be used when the user needs to automatically distribute tasks to team members based on skills/roles and update Feishu (Lark) bitable. It works together with the Feishu MCP server (@larksuiteoapi/lark-mcp) - the skill handles intelligent task assignment logic while MCP handles Feishu API interactions.

Manual invocation only; use only when the user explicitly requests `make-program-tutorial` by exact name, OR when the user asks to use a skill to create an SDK/API/library tutorial. Create a clear, reproducible, step-by-step tutorial for a specific API/SDK/library (or a set of functions/classes), with runnable examples, expected outputs, and basic troubleshooting.

Use when the user says "use pixi to install <some nvidia tool>" (or similar) and wants NVIDIA/CUDA/GPU packages installed via Pixi (no sudo/apt), e.g., CUDA toolkit pieces, cuDNN/NCCL, PyTorch CUDA builds, RAPIDS.

View changelog and recent updates since your installed version.

剪映 (JianYing) AI自动化剪辑的高级封装 API (JyWrapper)。提供开箱即用的 Python 接口，支持录屏、素材导入、字幕生成、Web 动效合成及项目导出。

Write BDD specifications using Gherkin for behavior-driven development

Activate for marketing analytics, KPI tracking, reporting dashboards, attribution analysis, and performance optimization. Use when analyzing campaign data, creating reports, or measuring marketing ROI.

通过E-utilities/Datasets API查询NCBI基因数据库。按基因符号/ID搜索，获取基因信息(RefSeqs、GO、位置、表型)，批量查找，用于基因注释和功能分析。

Create strategic HTML presentations with Chart.js, design tokens, and contextual decision system. Use for investor pitches, sales decks, product demos, QBRs, and conference talks. Features 15 deck strategies, 25 layouts, BM25 search, and Duarte Sparkline emotion arcs.

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.

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

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.

SEO audits, keyword research with ReviewWeb.site API (keyword ideas, difficulty, traffic, backlinks), on-page optimization, technical SEO, programmatic SEO (pSEO), JSON+LD schema, Google Search Console API integration. Activate for search optimization, meta tags, sitemap, Core Web Vitals. Used by seo-specialist, attraction-specialist, content-creator agents.

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.

使用 LaTeX（如 beamerposter、tikzposter 或 baposter）创建专业科研海报。支持会议展示、学术海报和科学传播。包含版式设计、配色方案、多栏布局、图形整合，以及面向海报视觉传达的最佳实践。

Claude Codeのカスタマイズを支援。「Claude Codeをカスタマイズしたい」「こういう挙動にしたい」「自動で〇〇したい」などのリクエストに対応し、適切な設定ファイルを作成・配置する。

Parse a contract document:

Create and refine prompt templates following Claude 4 conventions. Use when asked to build a new prompt template, improve an existing prompt, debug why a prompt isn't working, or develop reusable prompts for specific tasks. Triggers on "create a prompt", "build a template", "fix this prompt", "prompt isn't working", or requests to make prompts for specific use cases.

Generate constrained W/D/L predictions for each match by combining statistical models with research signals.

Automates mobile and simulator interactions for iOS and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, pinching, or extracting UI info on mobile devices or simulators.

AI-powered LuLu Firewall companion for macOS. Monitors firewall alerts, analyzes connections with AI, sends Telegram notifications with Allow/Block buttons. Use when setting up LuLu integration, handling firewall callbacks, or troubleshooting LuLu Monitor issues.

When the user wants to check monitoring status, manage alerts, view dashboards, or troubleshoot monitoring scripts. Also use when the user mentions "monitoring," "alerts," "ntfy," "dashboard," "uptime," "host availability," "backup monitor," or "daily readiness." For service-specific management, see homelab-services.

When the user wants to use Ansible for automation -- playbook development, inventory management, patching, configuration management, or vault secrets. Also use when the user mentions "Ansible," "playbook," "inventory," "patching," "patch all," "Ansible vault," or "configuration management." For CI/CD pipelines, see github-actions.

Generate content for TRMNL e-ink display devices using the TRMNL CSS framework and send via the trmnl CLI. Use when the user wants to display information on their TRMNL device, send messages to an e-ink display, create dashboard content, show notifications, or update their terminal display. Supports rich layouts with the TRMNL framework (flexbox, grid, tables, progress bars, typography utilities).

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.

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.

Interactive issue creation optimized for LLM agent teams. Guides users through type-specific question flows (bug, feature, epic, refactor, new project, chore, research spike) and produces structured, machine-parseable GitHub issues that AI coding agents can execute autonomously. Triggers: create issue, plan work, new task, project manager, write ticket, draft issue, plan feature, plan project, start project, create ticket, pm.

PDFファイルから問題データを抽出し、TypeScriptコードとして出力する

Manage i18n translations for Note Sage plugin. Use when: (1) Adding new translation keys, (2) Updating existing translations, (3) Maintaining consistency across 11 languages (en, ko, ja, es, fr, de, pt, zh, ar, ru, hi), (4) Finding missing translations

Use when [specific triggers, symptoms, error messages user will see] - [what this skill does and how it helps, in third person]

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.

Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you’re designing a CLI spec (before implementation) or refactoring an existing CLI’s surface area for consistency, composability, and discoverability.

Real-time monitoring dashboard for PAI multi-agent activity. USE WHEN user says 'start observability', 'stop dashboard', 'restart observability', 'monitor agents', 'show agent activity', or needs to debug multi-agent workflows.

現在のブランチをリモートのデフォルトブランチ（main/master/develop等）と同期し、 コンフリクトを自動解決する。"mainと同期して"、"最新にして"、"originと同期"、 "sync with origin"、"pull main"、"rebase on main"、"update from main" などで起動。

Track and list files modified in the current workspace within the last week, ordered by most recent modification date. Use when you need to see recent file changes, track development progress, or identify files that have been worked on recently in a git repository.

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.

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.

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Write high-quality automated tests for JavaScript/TypeScript applications. Use when: (1) writing unit, integration, or component tests, (2) testing React/Vue components, (3) working with Vitest or similar test runners, (4) mocking APIs or dependencies, (5) debugging flaky tests, (6) improving test reliability. Provides patterns for assertions, async testing, mocking, and test structure.

Operate Railway for the GradeOS project via CLI and web console (browser MCP): monitor logs, detect deploy/build/runtime errors, update environment variables, clear build cache, and redeploy. Use when the user asks to watch Railway logs, fix Railway deployment failures, or perform Railway console operations for GradeOS.

Analyze llm-compact-logger test output and configure enhancements. Use when user shares debug-compact.json or debug-report.json files.

This skill should be used when you need to import tasks from another Claude Code session's TaskList into your current session, enabling coordination across sessions without restarting.

OpenClaw 페르소나용 Slack App을 생성하고 .env 파일까지 완성하는 단계별 가이드. "/slack-app-setup", "Slack App 만들어줘", "슬랙 앱 설정", "페르소나 Slack 연결" 요청 시 사용한다.

Set up fast file suggestions for Claude Code using ripgrep, jq, and fzf. Use this skill when users want to improve file autocomplete performance or add custom file suggestion behavior.

Enforce Viet K-Connect non-negotiables (no Server Actions, API Routes only, Drizzle/Supabase patterns, TanStack Query repo layer, i18n ko/en/vi key parity). Use before/after code changes and for PR review checklists.

Create or modify evaluations for MCP Server(s). Use whenever you are tasked with changed MCP evals.

Comprehensive Adobe InDesign IDML creation, editing, and analysis. Use when working with .idml files to unpack, inspect, modify stories or spreads, preserve layout structure, validate packages, or generate IDML from InDesign exports.