AI Skills Hub - Browse 180,000+ Agent Skills

Discover GCP infrastructure and save to JSON. Use when user asks to "discover GCP", "explore GCP project", "scan GCP infrastructure", or "create infrastructure JSON".

비개발자를 위한 AI 스킬 자동 생성기. 자연어 대화만으로 Claude Code 스킬을 만들고 GitHub에 배포하여 팀원들이 한 줄로 설치할 수 있게 합니다. 이 스킬 실행 시 플랜모드로 진입하여 사용자와 대화하며 기획을 구체화합니다. 다음과 같은 요청에 이 스킬을 사용하세요: - "create-tool" - "새 스킬 만들어줘" - "도구 만들고 싶어" - "자동화 스킬 만들어줘" - "팀에서 쓸 스킬 만들어줘" - "스킬 생성"

This skill should be used when the user asks to "create a note in Obsidian", "add to my vault", "search notes by tag", "find orphaned notes", "list recent notes", "analyze vault connections", "parse frontmatter", or needs to work with any Obsidian vault or markdown folder.

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.

Manage ~/.claude/ slash commands: create, analyze, edit, refactor, delete. AUTOMATIC TRIGGER - Invoke when user says ANY of: "создай команду", "проанализируй команду", "измени команду", "переделай команду", "удали команду" Do NOT use for: running commands (use SlashCommand tool)

Interact with Tender App backend APIs for construction tender management. Actions: global search (projects/packages/submissions/contractors), evaluate documents with AI, query price history with RAG, compare Excel files. Use when user asks to find/search/list projects, packages, submissions, contractors, or needs tender evaluation, price intelligence, document comparison.

Branch the current Claude Code or Codex session into a new tmux session. Creates a true fork with a new session ID while preserving conversation state. Use when you want to explore an alternative approach without losing your current context.

Refactor bloated skill.md files using progressive disclosure pattern. Moves detailed content to references/ while keeping skill.md focused and discoverable. Use when a skill is approaching 500 lines or needs better organization.

Send messages to other Claude Code or Codex sessions via tmux. Hand off complex debugging context, get second opinions, share detailed technical findings across sessions.

Use when repeated prompts, missing capability, or a blocked workflow indicate a new reusable skill is needed.

向游戏应用注册新游戏，需要更新 gameScanner.ts、dev-game.cjs 和 vite.config.ts。当用户需要添加新游戏到数学、英语或科学分类时使用，或当用户提到注册、添加、集成新游戏时使用。

Deploys infrastructure on Vultr with Cloud Compute instances, High-Frequency servers, and VPCs. Excellent value with Kubernetes autoscaling support and global data centers. Use when: setting up Vultr infrastructure, deploying cloud compute or high-frequency instances, configuring firewalls, needing good price/performance with global reach. Keywords: vultr, vultr-cli, VPS, cloud compute, high-frequency, firewall, VPC, kubernetes autoscale, infrastructure

MCP server management for Claude Desktop. Profile-aware - reads MCP server inventory from profile.mcp.servers{} and config path from profile.paths.claudeConfig. Use when: installing MCP servers, configuring Claude Desktop, troubleshooting MCP issues.

Native macOS and Linux administration (non-WSL). Profile-aware - reads preferences from ~/.admin/profiles/{hostname}.json. Use when: macOS system admin, Homebrew packages, native Linux admin, apt/dnf/pacman packages, systemd services, launchd/brew services, Python/Node on mac or linux. NOT for: WSL (use admin-wsl), Windows (use admin-windows). Keywords: macos, osx, darwin, homebrew, brew, linux, ubuntu, debian, fedora, apt, dnf, pacman, systemctl, launchd, brew services, python mac, node mac

Deploys infrastructure on DigitalOcean with Droplets (VMs), Firewalls, and VPCs. Includes Kasm Workspaces auto-scaling integration for dynamic agent provisioning. Use when: setting up DigitalOcean infrastructure, deploying Droplets, configuring firewalls, integrating with Kasm auto-scaling, looking for US/global cloud with good API. Keywords: digitalocean, doctl, droplet, VPS, firewall, VPC, kasm autoscale, cloud infrastructure

Third-party WordPress plugin integration patterns. Use when adding new integrations, debugging compatibility with other plugins, or working with existing integrations.

Workflows and commands for managing Alembic database migrations and schema changes in the letta-cloud core app, including using uv, just, LETTA_PG_URI, and switching between SQLite and Postgres.

Validates GAAC prerequisites and command arguments. Checks for required tools (gh, jq), validates gaac.md configuration, and validates input arguments for all GAAC slash commands. Use before starting any GAAC workflow.

Core GitHub integration skill for GAAC. Manages issues, PRs, project board integration, and PR comments. Provides templates and scripts for all GitHub operations. Use for any GitHub-related actions in GAAC workflows.

Document refactoring skill for splitting large markdown files and validating internal links. Use when documents exceed 1000-1500 lines or when checking documentation integrity. Ensures atomic document structure with proper cross-references.

Expert guidance for designing comprehensive software architectures following Spec-Driven Development methodology. Use when user requests to design architecture, create architectural plans, plan system design, or make technical approach decisions. Supports scope definition, interface design, NFR specification, data modeling, operational readiness planning, and intelligent ADR (Architecture Decision Record) suggestions for significant architectural decisions.

Choose the appropriate protocol based on the task:

Build and iterate US equities trading strategies using Backtrader plus machine learning. Use when asked to design, prototype, backtest, or tune algorithmic strategies for US stocks with Backtrader, walk-forward ML signals, feature engineering, and leakage-safe evaluation.

ALWAYS use for ANY C# operation: renaming (files/classes/methods/properties/namespaces), finding references/usages ("where is X used"), finding definitions ("where is X defined"), understanding code structure (hierarchies/dependencies/relationships). Roslyn-powered semantic analysis ensures all references are updated correctly across the entire solution.

Extract a small, high-signal context packet around ripgrep matches (bounded by hits/files/output budget) for fast LLM consumption.

This skill should be used when users need to discover Redpanda Connect components for their streaming pipelines. Trigger when users ask about finding inputs, outputs, processors, or other components, or when they mention specific technologies like "kafka consumer", "postgres output", "http server", or ask "which component should I use for X".

Multi-purpose utility for CRUX compression workflows. Provides token estimation and checksum calculation. Use when estimating tokens for compression, comparing file sizes, or getting checksums for sourceChecksum tracking.

Create, edit, and analyze professional documents with support for tracked changes, comments, formatting preservation, and text extraction. Use this skill when working with .docx files for creating new documents, modifying or editing content, working with tracked changes, adding comments, or performing any other document tasks.

Create, edit, and analyze spreadsheets with support for formulas, formatting, data analysis, and visualization. Use this skill when working with spreadsheets (.xlsx, .xlsm, .csv, .tsv files) for creating new spreadsheets with formulas, reading or analyzing data, modifying existing spreadsheets while preserving formulas, performing data analysis and visualization, or recalculating formulas.

This skill should be used when the user asks to send Slack messages, check notifications, get a Slack digest, or search message history. Supports multiple workspaces.

Reviews API design, REST conventions, and backend architecture. Use when junior builds API endpoints, Express routes, middleware, controllers, or asks "is this RESTful", "check my endpoint".

Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.

ALWAYS use for ANY C# operation: renaming (files/classes/methods/properties/namespaces), finding references/usages ("where is X used"), finding definitions ("where is X defined"), understanding code structure (hierarchies/dependencies/relationships). Roslyn-powered semantic analysis ensures all references are updated correctly across the entire solution.

The Nx Jest generator produces defaults that conflict with this workspace's standards. This skill ensures all mandatory post-generation fixes are applied.

Access Spotify podcast data through direct API calls using Python scripts. Search episodes, retrieve metadata, and analyze listening habits by invoking executable scripts.

Define WHO uses the feature and WHAT success looks like

Systematic approach to finding and fixing bugs

Evidence before claims - verify before asserting success

Manage Playwright (TypeScript) testing work through GitHub Issues/Projects; use for creating/updating test cases, bugs, and moving items across todo/in-progress/review/done while sharing Playwright run results between Test Manager and Automation agents.

Expert knowledge for using color-eyre in Rust applications for rich error handling with colored backtraces, contextual error chains, help text, and beautiful terminal output. Use for CLI tools, servers, and application-level error reporting with eyre::Report.

Native Fabric pattern execution for Claude Code. USE WHEN processing content with Fabric patterns (extract_wisdom, summarize, analyze_claims, threat modeling, etc.). Patterns run natively in Claude's context - no CLI spawning needed. Only use fabric CLI for YouTube transcripts (-y) or pattern updates (-U).

Find similar companies using Exa.ai's neural search API

Get yesterday's code changes from a GitHub repository

Specification-driven development workflow for AI agents. Use when tasks are too large for a single session, require multi-step implementation, span multiple files/features, or need persistent requirements tracking.

PostgreSQL database exploration and debugging. Use when user asks to explore database schemas, tables, columns, or run queries. Requires a `.pgtool.json` file in the project directory.

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

Generate AGENTS.md files with progressive context loading for any folder. Analyzes folder contents, extracts context, and creates vendor-neutral context files following AGENTS.md best practices.

Work with Beads issue tracker for AI agent memory. Use when managing tasks, tracking dependencies, filing issues, or maintaining context across coding sessions. Handles bd commands, issue graphs, and persistent agent memory.

Onboards new Windows users by adapting the system prompt to their machine. Use when setting up a new user on Windows, when someone needs their Claude assistant customized for their specific Windows paths and preferences, or when migrating the skills system to a new Windows machine. Collects user information (name, username, Google Drive preferences) and generates a personalized system prompt with correct Windows paths.

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

Run the WorkerVless2sub cfst_hosts.sh workflow to refresh result_hosts.txt and nowip_hosts.txt, then stage and commit those updates in git. Use when asked to update CloudflareST hosts/IPs, run the speed test, or auto-commit the refreshed results for this repo.

Polibaseのプロジェクト規約とベストプラクティスを説明します。Pre-commit hooks遵守、CI/CD運用、中間ファイル管理、知識蓄積層の活用など、開発時に守るべきルールとガイドラインをカバーします。

Guides test creation for Polibase following strict testing standards. Activates when writing tests or creating test files. Enforces external service mocking (no real API calls), async/await patterns, test independence, and proper use of pytest-asyncio to prevent CI failures and API costs.

Streamlit UIの動作確認手順を提供します。Google認証スキップでの起動方法、ブラウザでの確認手順、Playwrightによる自動確認をカバー。UIの変更・修正後に動作確認する時にアクティベートします。

Assists in creating database migrations for Sagebase using Alembic. Activates when creating migration files, modifying database schema, or adding tables/columns/indexes. Ensures proper migration structure, rollback support, and Alembic best practices.

> Generate professional documents from templates using Carbone's JSON-to-document engine.

Working with model instances and fields

Technology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, evaluating technology stacks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.

Writing controller handler functions

Before claiming phase completion, spawn an independent review agent to verify your implementation. This catches issues you may have missed.

Create command aliases for skills with arguments

Inngest workflow patterns for OCR Chandra. Step functions, retry logic, event handling, and pipeline orchestration.

Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (图文) with multiple images. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "图文/文章".

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".

Use when creating hooks, configuring hook events, debugging hooks not firing, choosing hook types (command vs prompt), or understanding exit codes. Triggers: create hook, hook not working, PreToolUse, PostToolUse, Stop, settings.json hooks

Use when auditing Claude Code configurations, finding what skills/agents/hooks exist, checking for integration gaps, or optimizing plugin architecture. Triggers: audit config, what exists, list components, find gaps, integration check

Use this skill to query your Google NotebookLM notebooks directly from your AI agent for source-grounded, citation-backed answers from Gemini.

Migration between GCP Projects (DB, Storage, Container Images, Terraform)

Quality assurance specialist for security, performance, accessibility, and comprehensive testing

Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs.

Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest.

Acts as the Trader agent, turning the research manager’s investment plan and analyst reports into a concrete trade plan with a final BUY/HOLD/SELL proposal. Use for execution-focused trade decisions.

Acts as the Aggressive Risk Analyst, arguing for high-reward, high-risk interpretations of the trader’s plan in the risk debate. Use when you need a pro-risk critique of conservative views.

Analyzes company fundamentals using financial statements and profile-style data. Use when the user wants deep fundamental analysis, balance sheet/cash flow/income statement review, or long-term investment context.

Analyzes market data and technical indicators for a given ticker using the project’s indicator set. Use when the user asks for technical analysis, price/volume trends, or indicator-driven market commentary.

Install svelte-adapter-bun into a SvelteKit project by copy-pasting source code

Run dotnet test, capture failed test cases, and generate a rerun filter plus a markdown failure summary. Use when test runs fail and you need a focused rerun command or a compact failure report.

Validate work in a task worktree, commit safely, push the branch, and open a pull request to main using GitHub CLI. Use when wrapping up implementation and preparing review.

Manages cross-session knowledge persistence. Triggers on "remember", "recall", "what did we", "save this decision", "todo", or session handoff.

Create pages and write content to Roam Research via API. Use when the user wants to create pages, write content to today's daily notes, write to a specific page, or perform bulk operations in their Roam Research graph.

Deploy Apache Superset on Azure. Use when deploying Superset for BI/data visualization with PostgreSQL backend.

Generate Azure Bicep infrastructure code. Use when creating Container Apps, PostgreSQL, Log Analytics, or other Azure resources.

n8n workflow automation configuration for Azure. Use when deploying n8n specifically to Azure Container Apps.

一句话验收当前 worktree：review gate →（可选）merge main → 删除 worktree（纯 git，不依赖 dev panel）。

Use `agent-browser` CLI for browser automation in trade_canvas (可替代/补充 Playwright)：跑网页 E2E 流程、登录/表单交互、等待/断言、抓取页面信息、截图/PDF；优先用 `snapshot` + ref（@e1/@e2）+ 可选 `--json` 以便 LLM 稳定定位元素。

vibe-commander의 4-레이어 아키텍처 규칙에 따라 코드를 작성합니다. 새 함수, 모듈, 파일 생성, 리팩토링, 의존성 방향 검토 요청 시 사용합니다.

vibe-commander의 MCP 서버 도구를 구현합니다. MCP tool 정의, 핸들러 작성, MCP SDK 사용, 도구 스키마 설계 요청 시 사용합니다.

마크다운 계획서, 로드맵, 커맨드 파일의 파싱 및 섹션 교체 로직을 구현합니다. 파서 작성, 정규식 파싱, 마크다운 처리, Fallback 체인, 섹션 교체 요청 시 사용합니다.

Work with Linear project management via MCP tools. Use when creating issues, updating projects, managing initiatives, or querying Linear data.

This skill should be used when the user asks to "store a memory", "remember this", "save this insight", "search memories", "find related insights", "what do I know about", "connect these concepts", "add a relationship", "traverse the knowledge graph", or when working with the sem-mem MCP tools. Also activates when storing learnings, debugging knowledge, or building on prior insights.

Find and fix MongoDB ObjectId handling issues in hola-server router code.

Hide specific fields from the search form while keeping server-side filtering. Use when entity fields need search:true for server-side filtering (via filter prop) but should not appear in the user-facing search form UI.

Use secure Entity find methods with attribute filtering for data privacy. Use when querying MongoDB via Entity class - always specify attrs parameter to limit returned fields instead of exposing entire documents.

Add customized types to the Hola meta-programming framework. Use when the user says "add a meta programming type", "create custom type", "add type validation", or needs to define entity field types for server/client validation. See references/type_guide.md for comprehensive documentation.

CRUD data table components (CrudTable, DataTable) in Hola web framework. Use when building entity list/search views, implementing create/update/delete operations, customizing table actions/toolbars, handling pagination/infinite scroll, or integrating with server metadata. See references/ for detailed documentation.

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

Debug, edit, and fix billing endpoints. Covers legacy endpoints (attach/checkout/cancel) and the new v2 4-layer architecture (setup, compute, evaluate, execute). Use when working on billing, subscription, invoicing, or Stripe integration code.

def check_containers(self): """Verify Docker containers are healthy""" result = subprocess.run( ["docker-compose", "ps"], capture_output=True ) return "healthy" in result.stdout.decode()

def scan_file(self, filepath): if self.is_test_file(filepath): return [] # Mocks allowed in tests

Generate and edit images using Google Gemini API (Nano Banana). Use when the user wants to create images, edit photos, generate illustrations for articles, or create visual content. Trigger phrases include "generate an image", "create a picture", "make an illustration", "edit this photo", or when visual content is needed for a project.