AI Skills Hub - Browse 180,000+ Agent Skills

Creates Prowler security checks following SDK architecture patterns. Trigger: When creating or updating a Prowler SDK security check (implementation + metadata) for any provider (AWS, Azure, GCP, K8s, GitHub, etc.).

Creates MCP tools for Prowler MCP Server. Covers BaseTool pattern, model design, and API client usage. Trigger: When working in mcp_server/ on tools (BaseTool), models (MinimalSerializerMixin/from_api_response), or API client patterns.

Syncs skill metadata to AGENTS.md Auto-invoke sections. Trigger: When updating skill metadata (metadata.scope/metadata.auto_invoke), regenerating Auto-invoke tables, or running ./skills/skill-sync/assets/sync.sh (including --dry-run/--scope).

Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

Transform raw ideas and brain dumps into polished YouTube scripts through a structured checkpoint workflow. Use when the user wants to write a YouTube script, improve video retention, craft hooks, structure educational or entertainment content, or turn source material (transcripts, notes, research) into a compelling video script. Guides through research, hook writing, story structure, body content, and editing phases.

Fetch and display a trace from Tempo as a tree visualization. Use this when the user wants to view trace details, debug distributed operations, or analyze span hierarchies.

Implement development changes from a tagged Statement of Work (SOW) markdown file. Use when the user tags a .md file and asks to implement it, build it, or make the changes described in the document.

Toolkit for testing local web applications using Playwright. Use when asked to verify frontend functionality, debug UI behavior, capture browser screenshots, or view browser console logs. Supports Chrome, Firefox, and WebKit.

Validates that multiple systems work together correctly. Tests cross-system contracts, end-to-end workflows, and interface compatibility. Complements unit testing (test-generation) and code validation (code-validation) by focusing on system boundaries.

Implement robust error handling strategies for applications. Covers error classification, custom error hierarchies, propagation patterns, recovery mechanisms (retry, fallback, circuit breaker, bulkhead), logging and observability, user-facing messages, and boundary error handling across API, UI, and background job layers.

Semantic code analysis via Serena MCP + LSP (optional, requires uv)

Mandatory re-anchoring checklist before every ticket/task.

Update and rebuild spikectl or ctl packages in the monorepo

Renode practices for TMNL with tmux, UART sockets, telemetry, and guardrails.

Headless tmux launch workflow for Renode in TMNL. Invoke when starting or restarting Renode sessions, UART sockets, or monitor panes.

Use this to add models, decorations, and props to your game. Store AssetIds in Luau configs and load at runtime from Roblox CDN. Keeps your repo clean with version-controlled asset references instead of binary files.

Use this to upload images, sounds, and 3D models to Roblox. Uses Open Cloud API via rbxcloud CLI. Returns AssetIds for use in your game.

Create GitHub Issue knowledge entries. TRIGGERS - share knowledge, document solution, create how-to, add to knowledge base.

Writing PowerShell scripts for tasks and automations.

通过 ripgrep 在本地文件系统中精确定位代码、配置或文档，支持多轮迭代检索。

Create professional visual content using AI image generation. Use when designing social graphics, infographics, presentation slides, or learning materials that transform complex concepts into clear visuals.

Design and build AI-powered automation workflows. Use when creating integrations between systems, automating repetitive tasks, connecting APIs, or building workflows with Verdent, n8n, Make, or Zapier.

Classify, validate, generate, and audit documentation using the Diátaxis framework. Enforces quadrant purity across tutorials, how-to guides, reference, and explanation. Use when creating documentation, reviewing docs, auditing doc sets, restructuring existing content, or when the user mentions Diátaxis, documentation structure, or doc quality.

Generate labeled training examples for the BERT canonicalization classifier. Use to collect seed data from public APIs (OpenAPI specs), LLM tool-use datasets (ToolBench, API-Bank), or create synthetic variations. Outputs stratified JSONL with action, resource_type, and sensitivity labels.

Playwright-based testing for demo console errors and rendering

Validate and sync WorkAdventure maps to S3. Use when working with map files, syncing changes, checking for map errors, or setting up interactive zones (Jitsi rooms, silent areas). Covers JSON validation, TypeScript builds, S3 sync, and troubleshooting map loading issues.

Standardizes testing and validation for rsyslog using the diag.sh framework.

Handles environment setup and high-performance incremental building for rsyslog.

Comprehensive development support for Circle's stablecoin ecosystem including USDC/EURC integration, wallet solutions (Developer-Controlled, User-Controlled, Modular), cross-chain transfers (CCTP, Bridge Kit, Gateway), smart contracts, and payment APIs. Use when building applications with Circle for - (1) Stablecoin payments and transfers, (2) Wallet creation and management, (3) Cross-chain USDC/EURC transfers, (4) Smart contract deployment and management, (5) Gas fee sponsorship and optimization, (6) Circle Mint integration, (7) Global payment settlement, (8) FX operations with stablecoins. Covers SDK usage (TypeScript/JavaScript), API integration (REST), smart contract development (Solidity), and Circle-specific features like programmable wallets, native cross-chain transfers, and gasless transactions.

Comprehensive development support for LI.FI DEX aggregator including SDK, Widget, and API integration for cross-chain swaps and bridging. Use when building applications with LI.FI for - (1) Cross-chain token swaps and bridges, (2) Multi-chain liquidity aggregation, (3) Trading widget integration, (4) Custom DEX aggregation UI, (5) Gas subsidy implementation, (6) Revenue monetization with integrator fees, (7) Route optimization across 60+ chains, (8) Intent-based trading systems. Covers SDK usage (TypeScript/JavaScript), Widget customization (React/Vue/Svelte), API integration (REST), and LI.FI-specific features like cross-chain routing, gas subsidies (LI.Fuel), and multi-protocol aggregation across Uniswap, 1inch, Stargate, Across, and 800+ protocols.

Comprehensive development support for ENS (Ethereum Name Service) including name registration, resolution, subdomains, smart contracts, and multichain integration. Use when building applications with ENS for - (1) Domain name registration and management (.eth names), (2) Name resolution (ENS to address, address to ENS), (3) Subdomain creation and management, (4) Avatar and profile records, (5) Smart contract integration with ENS, (6) Multichain resolution (L2s, sidechains), (7) Name Wrapper and permission management (fuses), (8) DNS integration (traditional domains on ENS), (9) Reverse resolution (address to name). Covers library usage (viem, ethers, wagmi), smart contract development (Solidity), ENS protocol architecture (Registry, Resolver, Registrar), and ENS-specific features like wrapped names, CCIP Read, and programmable fuses.

Unlink a project from experimental skills. Removes the local .claude/skills shortcut. Skills remain safe in experimental folder. Use when: user wants to disconnect, unlink, stop using experimental skills, or done experimenting.

Sync experimental skills to stable/production. Commits changes in experimental and merges to stable branch. Use when: user wants to promote skills, sync to stable, publish skills, or move experimental to production.

Link a project to the experimental skills environment. Creates a local .claude/skills shortcut so the project can use experimental skills. Use when: user wants to connect project to lab, use experimental skills, or test skills in a project.

Manage GitHub Projects V2 with full CRUD operations. This skill should be used when users want to: create issues with sub-issues, add issues to organization projects, set custom project fields (like Priority, Status, Issue Type), query project structure, or perform bulk issue operations. Covers the critical distinction between personal and org projects, proper sub-issue linking via GraphQL, and field value mutations.

Generate and submit Salesforce time log entries from Claude Echo activity data and Calendar events. Use when the user wants to log hours worked on customer opportunities, fill out SFDC time tracking forms, or calculate how much time was spent on different accounts/projects. Requires Echo MCP and Salesforce MCP servers. Optional Calendar MCP for meeting time capture.

Interact with Tlon/Urbit beyond the channel plugin. Use for contacts (get/update profiles, nicknames, avatars), listing channels/groups, fetching message history, and ship lookups. Complements the Tlon channel - use this skill for read operations and profile management.

Z.ai API integration for building applications with GLM models. Use when working with Z.ai/ZhipuAI APIs for: (1) Chat completions with GLM-4.7/4.6/4.5 models, (2) Vision/multimodal tasks with GLM-4.6V, (3) Image generation with GLM-Image or CogView-4, (4) Video generation with CogVideoX-3 or Vidu models, (5) Audio transcription with GLM-ASR-2512, (6) Function calling and tool use, (7) Web search integration, (8) Translation, slide/poster generation agents. Triggers: Z.ai, ZhipuAI, GLM, BigModel, Zhipu, CogVideoX, CogView, Vidu.

Comprehensive Next.js v16 development with Cache Components, feature-based architecture, and best practices. Use for ANY Next.js 16 task to know - (1) Project structure with features folder pattern, (2) Where to fetch data with use cache, (3) Server vs Client component decisions, (4) One file per query/type/schema/hook pattern, (5) Cache invalidation with updateTag/revalidateTag, (6) Proper component organization within features. Apply to all Next.js 16 development tasks.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation 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

Initialize orchestrated 5-phase workflow using multi-agent execution

将英文编写的skill翻译成中文版本。当用户需要将现有的英文skill（包括SKILL.md和相关文档）翻译成中文，同时保持核心内容、代码、路径、技术细节不变时使用此skill。适用于创建skill的中文本地化版本。

Use this skill when the user asks about creating videos with React, Remotion framework, programmatic video generation, video animations, or needs help with Remotion projects

Kurocoとフロントエンドフレームワークの統合パターン。使用キーワード：「Kuroco Nuxt」「Kuroco Next.js」「フロントエンド連携」「Nuxt3」「Nuxt2」「App Router」「Pages Router」「SSG」「SSR」「静的生成」「コンテンツ表示」「ログイン実装」「会員登録」「signup」「KurocoPages」「フロントエンド環境構築」「Vue」「React」「useAsyncData」「$fetch」「asyncData」「composable」「useAuth」「認証状態」「プロフィール取得」「profile」「generateStaticParams」「動的ルート」「v-html」「dangerouslySetInnerHTML」「XSS対策」「サードパーティCookie」「credentials include」。Nuxt/Next.jsでのKuroco連携、認証実装、SSG/SSR設定に関する質問で使用。

Kurocoコンテンツ管理（CRUD操作）のベストプラクティス。使用キーワード：「コンテンツ定義」「記事管理」「Topics」「TopicsGroup」「カテゴリ」「WYSIWYG」「ファイルアップロード」「CSVインポート」「コンテンツAPI」「拡張項目」「ext_col」「topics_id」「subject」「contents」「ymd」「topics_flg」「フィルター」「filter」「order_by」「一覧取得」「詳細取得」「list」「details」「insert」「update」「delete」「bulk_upsert」「一括更新」「タグ」「tag」「予約投稿」「open_ymd」「close_ymd」「公開設定」「閲覧制限」「関連コンテンツ」「pageID」「cnt」。コンテンツの作成・取得・更新・削除・フィルタリングに関する質問で使用。

Kuroco Webhook・バッチ処理・自動化のベストプラクティス。使用キーワード：「Webhook」「バッチ処理」「定期実行」「スケジュール実行」「cron」「15分毎」「1時間毎」「外部連携」「GitHub Actions」「repository_dispatch」「workflow_dispatch」「Slack通知」「slack_send」「Chatwork」「chatwork_send」「メール通知」「send_mail」「SendGrid」「sendgrid_send」「自動処理」「Smarty」「Smarty構文」「assign」「foreach」「if」「api_internal」「api_request」「外部API」「トリガー」「前処理」「後処理」「Function」「カスタム処理」「CSV出力」「write_file」「put_file」「json_encode」「date_format」「topics変数」「inquiry変数」。定期実行、外部通知、Smartyテンプレート、トリガー処理に関する質問で使用。

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

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task.

Enforces Effect-TS patterns for services, errors, layers, and atoms. Use when writing code with Effect.Service, Schema.TaggedError, Layer composition, or effect-atom React components.

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

Split development into multiple features with tmux, git worktrees, and Claude Code instances

全面的文档创建、编辑和分析，支持修订跟踪、评论、格式保留和文本提取。当 Claude 需要处理专业文档（.docx 文件）时用于：(1) 创建新文档，(2) 修改或编辑内容，(3) 处理修订跟踪，(4) 添加评论，或任何其他文档任务

用于创建高质量 MCP（模型上下文协议）服务器的指南，使 LLM 能够通过设计良好的工具与外部服务交互。当构建 MCP 服务器以集成外部 API 或服务时使用，无论是在 Python（FastMCP）还是 Node/TypeScript（MCP SDK）中。

Capture screenshots from iOS Simulator or Android Emulator using the bundled simulator-screenshot.sh script. Use when asked to take simulator/emulator screenshots, list available devices, select a specific simulator or emulator by ID/name, or return JSON output for automation.

Видалення ознак AI-генерованого тексту з української мови. Використовуй для редагування або перевірки тексту, щоб він звучав природно по-українськи. Виявляє та виправляє: русизми, англіцизми, канцеляризми, плеоназми, AI-лексику, надмірне підкреслення значущості, промоційну мову, приховані Unicode watermarks, статистичні AI-патерни (низька perplexity, низька burstiness). Triggers: humanize Ukrainian text, зробити текст українським, прибрати AI, виправити суржик, редагувати українською, nature Ukrainian, remove AI patterns from Ukrainian, fix Russian calques, виправити русизми, канцелярит.

Auto-suggested when working on src/content/reference/**/*.md files. Provides Reference page structure and tone guidance.

Query Polymarket prediction markets - check odds, trending markets, search events, track prices and momentum.

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.

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 Gimli to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

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

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

Check Syncthing sync status between devices. Use when asked about sync status, Syncthing issues, or file synchronization.

Comprehensive status report for Startup multi-agent system. Shows bd stats, active tmux sessions, blocked issues, Decision Ledger history, and agent activity.

Build and upload releases to GitHub Releases using standardized build scripts. Automates version tagging, portable package creation, and release publishing. Use when releasing new versions or creating distribution packages.

Create and edit Obsidian .canvas files using the JSON Canvas format. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, project boards, knowledge graphs, or when the user wants to organize notes/content spatially. Triggers on requests for infinite canvas layouts, visual diagrams, node-and-edge visualizations, or Obsidian Canvas files.

Task management CLI for tracking and managing feature subtasks with status, dependencies, and validation

The reference framework to generate, compile, and lint greenfield prompts that conform to the Agnostic Prompt Standard (APS) v1.0.

Use the Opper Python Agent SDK (opper-agents) to build AI agents with think-act reasoning loops, tool use via @tool decorator, multi-agent composition, MCP integration, persistent memory, hooks for observability, and Pydantic schema validation. Activate when building Python AI agents, autonomous systems, or tool-using reasoning loops with the Opper platform.

Use the Opper Node/TypeScript SDK (opperai) for AI task completion, structured output with JSON Schema or Zod, knowledge base semantic search, streaming responses, and tracing. Activate when building TypeScript or JavaScript applications that need LLM-powered task completion, RAG pipelines, or AI function orchestration with the Opper platform.

Search for people and properties using Whitepages APIs via x402.

Use when feature branch is complete and reviewed, ready to merge to main - squashes multiple commits into single clean commit in main using git merge --squash

Use when generating branded QR codes for ProductTank SF events - speaker LinkedIn profiles, sponsor websites, or Slack join links. Handles single/bulk generation, correct logo mapping, GDrive upload, and mandatory test-scanning.

Use when creating or editing Mermaid flowchart diagrams, encountering parse errors, or unsure about node shapes, connection syntax, or styling - provides syntax guardrails using modern shape syntax for Obsidian-compatible diagrams

Use when creating, viewing, or labeling GitHub issues - enforces project label conventions (component:Name, priority:level, type:category) and proper title format before any issue creation

Use when creating or editing slash commands - applies TDD to slash command documentation by testing with SlashCommand tool and subagents before deployment, preventing inverted logic and untested conditionals

Taskfile conventions (balance direct commands vs shell scripts, sub-task imports). Use when creating or modifying Taskfile.yaml and sub-task files in tasks/.

CI/CD workflow patterns (reusable workflows, shell scripts, caching, codecov). Use when creating or modifying GitHub Actions workflows.

AI-powered crypto trading agent via natural language. Use when the user wants to trade crypto (buy/sell/swap tokens), check portfolio balances, view token prices, transfer crypto, manage NFTs, use leverage, bet on Polymarket, deploy tokens, or set up automated trading strategies. Supports Base, Ethereum, Polygon, Solana, and Unichain. Comprehensive capabilities include trading, portfolio management, market research, NFT operations, prediction markets, leverage trading, DeFi operations, and automation.

Batch convert directories of audio files or documents to markdown. Use when converting all files in a folder, multiple recordings, or bulk document processing.

Build Claude Code skills from documentation websites. Scrapes Mintlify, ReadTheDocs/Sphinx, Docusaurus, GitBook, and static HTML sites. Generates properly formatted skills with SKILL.md and reference files. Use when: creating skills from docs, scraping documentation, generating reference materials from URLs.

Generate Go test coverage report with package breakdown.

Create a new release with version bump, git tag, and GitHub release with binary builds. Use when releasing a new version.

Generate app icons, splash screens, and adaptive icons for iOS, Android, and Web. Use when creating or updating visual assets.

Initialize new economics research projects with standardized structure. Use when starting a new research project to create folder structure, configuration files, and boilerplate code. Sets up git, rix environment, Makefile, and connects to Dropbox/Overleaf.

Compile Unity project via uloop CLI. Use when you need to: (1) Verify C# code compiles successfully after editing scripts, (2) Check for compile errors or warnings, (3) Validate script changes before running tests.

Initialize a Roblox game project with professional tooling. Creates folder structure, config files (Rojo, Wally, Selene, StyLua), starter code, VS Code settings, and CLAUDE.md. Use when starting a new Roblox game or setting up Rojo workflow.

Configure, deploy, and troubleshoot Model Context Protocol (MCP) servers for AI agent workflows. Use when setting up MCP servers, debugging connection issues, managing multi-server configurations, integrating with Claude Desktop/Code/Cowork, or designing custom tool servers. Triggers on MCP configuration, tool server development, Claude integration issues, or agent infrastructure setup.

Scaffold and build interactive 3D visualizations using Three.js with emphasis on algorithmic art, sacred geometry, temporal animations, and modular architecture. Use when creating WebGL visualizations, generative art pieces, interactive 3D experiences, particle systems, flow fields, or projects like gravitational spirals, temporal perspective pieces, or illuminated visual narratives. Triggers on requests for Three.js projects, 3D web graphics, algorithmic visualizations, or sacred geometry renders.

Optimize Google Cloud Platform resource allocation and manage cloud credits efficiently. Use when planning GCP deployments, analyzing cloud spend, maximizing value from expiring credits, right-sizing instances, or designing cost-effective architectures. Triggers on GCP cost optimization, credit management, resource allocation planning, or cloud budget concerns.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Create DevTrail documentation. Analyzes context to suggest document type or accepts explicit type parameter. Always confirms before creating.

Show DevTrail documentation status. Use to verify if AI agents properly documented their changes.

Manages the Claude Code Config Manager development servers (backend on port 8420, frontend on port 5173). Claude and subagents should use this skill before running tests, after modifying backend code, or when server issues occur. Triggers on server operations, test preparation, backend restarts, health checks, or when encountering connection errors to localhost:8420.

Generate professional resumes that conform to the Reactive Resume schema. Use when the user wants to create, build, or generate a resume through conversational AI, or asks about resume structure, sections, or content. This skill guides the agent to ask clarifying questions, avoid hallucination, and produce valid JSON output for https://rxresume.org.

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.

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

DDD architecture knowledge base. Provides patterns, antipatterns, and PHP-specific guidelines for Domain-Driven Design audits.

CQRS architecture knowledge base. Provides patterns, antipatterns, and PHP-specific guidelines for Command Query Responsibility Segregation audits.