AI Skills Hub - Browse 180,000+ Agent Skills

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.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

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

Core Tailscale concepts - tailnets, MagicDNS, device management, and basic setup

Edit images using AI on fal.ai. Style transfer, object removal, background changes, and more. Use when the user requests "Edit image", "Remove object", "Change background", "Apply style", or similar image editing tasks.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Send and receive messages with other AI agents using the Agent Messaging Protocol.

Create, sign (Ed25519), verify, and audit an AOS-style immutable constitution for OpenClaw. Use when implementing constitutional governance beneath SOUL.md, designing deny/confirm/allow policy evaluation, generating constitution.yaml + constitution.sig, validating GitTruth attestations, building tamper-evident tool-call logs, or preparing a reference implementation skill/plugin for OpenClaw.

Launch tokens on Base with instant Uniswap V4 liquidity. 80% trading fees to creator, LP locked forever, free to launch. Use when an agent wants to create their own token, launch a meme coin, or build token-gated experiences. Commands include create, list, buy, sell, claim fees, and more.

帮助生态学研究人员收集和整理学术文献，将现有数据转化为可发表的研究成果。当用户请求收集文献、需要查找生态学相关论文、或想要整理研究参考文献时使用。专为拥有数据但需要文献支持来发展成学术出版物的生态学专业人士设计。支持意图对齐、关键词识别、通过Semantic Scholar和Google Scholar进行文献检索，以及生成带中文翻译的格式化文献清单。

macOS app signing, notarization, and distribution expert. Guides developers through code signing with Developer ID, hardened runtime, notarization with notarytool, packaging as DMG/PKG/ZIP, and distribution via App Store, TestFlight, or direct download. Includes CI/CD automation for GitHub Actions and Xcode Cloud. Use when preparing a macOS app for release, debugging signing errors, setting up notarization pipelines, or troubleshooting Gatekeeper rejections.

Comprehensive security analysis for Claude Code skills with P0-P3 enhancements. Detects malicious code, obfuscation, YAML injection, typosquatting, time bombs, sandbox escapes, and 40+ attack patterns. Use for analyzing skills before installation or auditing existing skills.

System Specification Curator for SaaS systems enforcing "If it is not written, it does not exist." Use when reviewing PRs for specification completeness, creating or updating system specifications, ensuring documentation meets mandatory standards, or validating implementations have proper specification backing. Applies to systems serving external users, integrating with third parties, handling regulated data, or operating continuously.

Review websites for accessibility compliance with WCAG 2.2 Level AA and EU EAA requirements. Use when user asks to check, audit, review, or assess website accessibility, WCAG compliance, or EU accessibility standards. Identifies violations, provides remediation guidance, and generates compliance reports.

Generate comprehensive hierarchical wiki documentation from any code repository using LightRAG knowledge graphs. Supports repository indexing, intelligent querying, and automated wiki generation with multiple modes (base/extended).

This skill enables AI agents to browse, read, and submit papers to the Journal of AI Slop, a satirical academic journal publishing AI-generated research. Use when the agent needs to interact with the paper API.

在终端中显示图片。当用户需要在终端中查看图片时使用此技能。支持多种显示模式（Kitty/iTerm2图形协议、Unicode符号、ASCII艺术），自动检测最佳显示工具。

Use when executing an approved wish plan - dispatches implementor subagents per task with two-stage review (spec + quality) and fix loops.

严格变更控制下编辑、版本化并存储提示词。用于用户要求小改/局部优化/补丁式修订、修复提示词失败、添加或维护版本头、对比版本，或基于输入/思路/输出诊断问题时。强制版本控制、作者签名，并将版本保存到 /Users/wisewong/Documents/Developer/prompts。

Schema validation for JavaScript objects. Trigger: When creating Yup schemas, validating forms, or implementing validation.

TypeScript-first schema validation with type inference. Trigger: When creating schemas, parsing input, or ensuring type-safe validation.

Use when you need to safely inspect MySQL/PostgreSQL data or schema via the xsql CLI.

Converts documents into business stories and infographics using Gemini 3.0 Pro (Python SDK).

Use this skill when the user asks to "get contract source code", "show verified contract", "fetch source from etherscan", "view smart contract code", or mentions viewing verified source code on EVM chains (Ethereum, Polygon, Arbitrum, etc.). Requires a contract address and optional chain parameter.

Use Qwen (DashScope/百炼) for speech tasks: (1) ASR speech-to-text transcription of user audio/voice messages (Telegram .ogg opus, wav, mp3) using qwen3-asr-flash, optionally with coarse timestamps via chunking; (2) TTS text-to-speech voice reply using qwen3-tts-flash with selectable voice (default Cherry) and output as .ogg voice note for Telegram.

Query Strava for activities, performance stats, segments, and social data.

指导在前端项目中按团队规范创建和维护 HTTP 接口，包括类型定义、请求封装、命名约定与错误处理。当前端需要新增或调整 API 时使用本技能。

指导在前端项目中按团队规范创建和维护路由，包括目录结构、Page 与 Loader 职责划分及懒加载用法。当前端需要新增或重构页面路由时使用本技能。

Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search

Automate Zed extension releases for this repo. Use when bumping the extension version, updating CHANGELOG/README/PUBLISHING, rebuilding extension.wasm, running tests, committing/tagging, and pushing a vX.Y.Z tag to trigger the Zed extensions registry update workflow.

Allows you to debug the game with LLDB step debugging and breakpoints utilizing pexpect

PowerShell 5.1 validation script operations including asset validation, lint checking, smoke tests, and token budget reporting. Use for pre-PR validation and conductor pause point checks.

Provide a multi-select UI for browsing and installing packs from the Loa Constructs Registry. Enables composable skill installation per-repo.

本地提醒调度技能。用于用户说“提醒我多久之后/在某个时间做什么”等新增提醒需求，尤其适合非技术用户。负责检查服务、自动启动、安装依赖并调用提醒脚本。

This skill should be used when checking Hugo content for consistency issues, validating internal references, detecting duplicate content, verifying frontmatter completeness, and ensuring proper naming conventions. Use this skill to audit content quality, fix broken links, and maintain consistency across a Hugo site.

Summarizes how to use the Anima animation engine (Scene, Mobjects, Fluent API, Pro API, camera, timeline, rendering, and CLI). Use when authoring or explaining Anima animations.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

See and interact with the macOS desktop through a vision-action loop. Captures screenshots, analyzes them with Claude vision, and executes mouse clicks, keyboard input, and app navigation via cliclick and AppleScript. Use when the user asks to interact with GUI applications, click buttons, open or navigate native macOS apps (Figma, Finder, System Settings, etc.), export files from visual interfaces, fill forms in desktop apps, or perform any task requiring seeing and acting on the screen. Triggers: 'look at my screen', 'click on X', 'open app Y and do Z', 'export from Figma', 'navigate to settings', or any multi-step desktop GUI workflow.

Commander.js CLI development patterns for ARI

EventBus communication patterns for ARI's six-layer architecture

Create, export, and manage Canva designs via the Connect API. Generate social posts, carousels, and graphics programmatically.

Runs Software Composition Analysis (SCA) to detect vulnerable dependencies. Wraps npm audit and Trivy fs. Use when user asks to "scan dependencies", "check npm vulnerabilities", "SCA scan", "dependency audit", "依存関係スキャン", "脆弱性チェック".

Scans git repositories for hardcoded secrets, credentials, and API keys using Gitleaks. Returns findings with severity, location, and remediation steps. Use when user asks to "scan for secrets", "detect credentials", "find API keys", "check for leaks", "シークレット検出", "認証情報スキャン".

Runs Static Application Security Testing (SAST) using Semgrep. Scans source code for vulnerabilities, security anti-patterns, and OWASP Top 10 issues. Use when user asks to "run SAST", "scan for vulnerabilities", "static analysis", "code security scan", "静的解析", "脆弱性スキャン".

Runs Google Lighthouse audits using Playwright for SEO, Performance, Accessibility, and Best Practices scoring. Supports both URLs and local HTML files. Use when user mentions "Lighthouse", "page speed", "performance audit", "Core Web Vitals", "CWV", or needs comprehensive web performance analysis.

Runs automated HTML linting using @axe-core/playwright (WCAG accessibility) and markuplint (HTML standards). Use when user asks to "lint HTML", "run automated checks", "validate HTML", "check accessibility", or mentions "axe-core", "markuplint", "automated audit".

Scans Infrastructure as Code for security misconfigurations. Wraps tfsec for Terraform and Checkov for multi-cloud IaC. Use when user asks to "scan Terraform", "IaC security", "infrastructure scan", "tfsec", "checkov", "Terraformセキュリティ", "インフラスキャン".

Analyzes HTML/JSX/TSX files for SEO and accessibility issues including WCAG 2.1 AA compliance, color contrast (4.5:1), heading hierarchy, meta tags, image alt text, and ARIA attributes. Use when checking web pages for SEO, accessibility, WCAG compliance, or when user mentions "a11y", "contrast", "alt text", "meta tags", "heading structure", or "accessibility audit".

Scans containers and Dockerfiles for security issues. Wraps Hadolint for Dockerfile linting and Trivy for container image scanning. Use when user asks to "scan Dockerfile", "lint Dockerfile", "container security", "image scan", "Dockerセキュリティ", "コンテナスキャン".

Technical reference for TaskMan/Vikunja infrastructure. Provides MCP tool documentation, database query methods, and troubleshooting guides. This skill does NOT activate on user queries - use the 'taskman' skill instead for all user-facing task management requests.

Use this when installing dependencies, running scripts, filtering packages, or migrating this monorepo from pnpm to Bun (bun.lock, workspaces, bun ci) while keeping Cloudflare Workers + Wrangler workflows working.

This skill is for routine monorepo work *after* the repo uses Bun. For pnpm → Bun migration steps, use the `bun-monorepo-workflows` skill.

Install Tacodex skills into $TACODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Production-grade skill for API documentation creation including OpenAPI/Swagger specifications, REST endpoint documentation, authentication flows, and error handling guides.

Production-grade skill for generating clear, well-documented code examples, implementation patterns, configuration files, and integration samples with multi-language support.

Analyze and generate idiomatic Common Lisp libraries following patterns from Edi Weitz, Marijn Haverbeke, and Eitaro Fukamachi

Analyze Common Lisp libraries to extract patterns, conventions, and design decisions.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Use Git worktrees for isolated work environments. Creates separate working directories for parallel development on different branches.

Test web applications comprehensively for quality. Performs functional, integration, and user experience testing of web applications.

Process and manipulate spreadsheet documents. Creates, edits, analyzes, and transforms Excel files with formula and formatting support.

Comprehensive word document processing with full format support. Handles creation, editing, formatting preservation, tracked changes, and metadata management.

This skill should be used when agents need to log into websites, retrieve passwords, or access credentials. CRITICAL - always use find_credential with the website URL, never guess item names.

This skill should be used when the user asks about "AIR", "algebraic intermediate representation", "ZK constraints", "trace design", "constraint soundness", "polynomial commitments", "FRI", "STARK", "lookup arguments", "permutation arguments", "memory consistency", "transition constraints", "boundary constraints", "vanishing polynomial", "quotient polynomial", "Fiat-Shamir", or needs expert-level cryptographic review of constraint systems.

Modern growth hacking: loops + product-led growth + disciplined experimentation, under privacy and deliverability constraints.

Finalize development branches for integration. Prepares branches for merging with cleanup, rebasing, and verification steps.

Extract data from websites efficiently using uv scripts. Never bloat context by reading raw HTML/JSON into conversation.

Generate TRELLIS distillation data with automatic restart handling for memory leaks

Upload training data, models, and scripts to cloud instance

Run automated hyperparameter search using Optuna with Bayesian optimization

Train consistency view synthesis model for multi-view novel view generation

This skill should be used for browser automation tasks using Chrome DevTools Protocol (CDP). Triggers when users need to launch Chrome with remote debugging, navigate pages, execute JavaScript in browser context, capture screenshots, or interactively select DOM elements. No MCP server required.

PRD-first feature development workflow that generates a PRD file from a reference template, captures requirements, business flow, clarification questions, and test plans, then waits for user confirmation before implementation. Use when users ask to design or implement new features, change product behavior, request a PRD-driven process, or ask for a greenfield feature that is complex and has no existing base (plan before action).

Use beads (bd) for persistent task tracking in coding projects. A git-backed issue tracker designed for AI agents with dependency graphs, hierarchical tasks, and multi-agent coordination.

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Display HTML content on connected StarforgeOS nodes (Mac app, iOS, Android).

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.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks StarforgeOS to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

Merge a GitHub PR via squash after /preparepr. Use when asked to merge a ready PR. Do not push to main or modify code. Ensure the PR ends in MERGED state and clean up worktrees after success.

Org-mode formatting and org-roam note management via emacsclient. Never use Read/Write/Edit on roam notes directly. Triggers: roam note, org-roam, org-mode, .org files, Zettelkasten, backlinks

This skill lets you create AI voice agents with custom personalities that can make outbound phone calls. Perfect for sales outreach, appointment setting, customer follow-ups, or any scenario where you need a voice agent.

Working with OpenBench data layer - vector stores, chunking, embeddings, and RAG patterns. Use when implementing PineconeStore, chunking documents, generating embeddings, or building RAG workflows.

Attempt automated verification of criteria before falling back to manual. Parses criterion text for automation hints and executes appropriate tool (curl, browser, file check). Invoked by verify-task and phase-checkpoint for MANUAL criteria.

Get a second opinion from OpenAI Codex on documents, specs, or plans. Use for cross-AI consultation on any content, not just code diffs.

Apply dotfiles changes with GNU Stow. Use when editing files in ~/dotfiles to ensure changes are properly symlinked to home directory. Handles stow conflicts with adopt workflow.

Use when user needs to set up Milvus locally. Triggers on: local setup, install milvus, docker, docker-compose, dev environment, milvus standalone, milvus lite.

High-performance PDF document processing with text extraction, image extraction, table recognition, and NLP analysis. Use when you need to extract content from PDF files, analyze document structure, or process PDF content in any way (text extraction, image extraction, table extraction, entity recognition, summarization, keyword extraction, document classification, language detection, or advanced text analysis).

Complete workflow for creating Agent Skills following the open standard. Use when building new capabilities, setting up skill directories, or designing progressive loading workflows for VSCode Copilot customization.

Unity Editor scripting and extension development for Unity 6.3 LTS. Use when creating custom inspectors, property drawers, editor windows, asset importers, build pipeline extensions, gizmos, handles, or any Unity Editor customization. Covers EditorWindow, CustomEditor, PropertyDrawer, ScriptedImporter, menu items, and UI Toolkit for editor UI.

Clone any webpage into pixel-perfect, production-ready code. Extracts complete page structure using Playwright, intelligently chunks content following three core principles (mutual exclusivity, complete coverage, size control), and generates React/Next.js/Vue components in parallel using subagents. Use when user wants to clone a website, replicate a page design, convert URL to code, rebuild a webpage, or copy a website's layout.

Documentation synchronization using Mem0 for tracking relationships between specs, architecture, ADRs, and roadmap

Generate feature-by-feature implementation workflows that map features from `roadmap/features.json` to tech-specific commands from the project's tech stack.

Templates and scripts for generating layered BUILD-GUIDE.json/md from Airtable plugin index - shows available commands organized by infrastructure layers

Intelligent Word document restructuring and refinement expert that transforms messy .docx files containing images, formulas, and scattered notes into well-organized Markdown documents compatible with Feishu. Use when Codex needs to extract and preserve all content from Word documents including images and formulas, reorganize scattered content by topic rather than chronological order, maintain the author's personal voice and style while improving clarity, convert documents to Markdown format with proper image links and formula representations, or process Chinese technical documents with mixed media content.

> **Purpose:** Build Clay enrichment tables, signal detection systems, and API integrations for GTM operations. Implement waterfall enrichment logic, credit-conscious workflows, and CRM sync patterns.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Search Granola meeting transcripts by folder tags, title, and content keywords. This skill should be used when the user wants to find or search through Granola meeting notes — whether by person, category, meeting title, or topic.