AI Skills Hub - Browse 180,000+ Agent Skills

Control Adobe Photoshop through LLM conversations by generating and executing JSX scripts. Use when users want to manipulate Photoshop documents, create new documents, edit images, manage layers, apply filters, or perform any Photoshop automation tasks through natural language commands. This skill bridges LLM instructions to Photoshop's JSX scripting API via a local HTTP service.

Comprehensive E2E testing for looplia CLI. Tests Docker deployments, published CLI versions, and local development. Verifies workflow execution, skill architecture (v0.6.9+), and command initialization (v0.6.10+). Use when testing looplia releases, CI validation, or verifying Docker builds.

Systematic debugging framework for any bug, test failure, or unexpected behavior. Use BEFORE proposing fixes. Triggers: "bug", "test failure", "flaky test", "debugging", "root cause", "investigate", "why is this failing", "unexpected behavior", "not working", "broken", "error", "fix this", "what's wrong".

Cloud CLI patterns for GCP and AWS. Use when running bq queries, gcloud commands, aws commands, or making decisions about cloud services. Covers BigQuery cost optimization and operational best practices.

Performs small structural code cleanups (tidyings). Use when preparing code changes, removing dead code, reducing nesting, or cleaning up before feature work.

Generates draw.io diagrams for visualization. Use when creating architecture, sequence, flowchart, or AWS infrastructure diagrams.

Diagnose and fix bugs using evidence-based investigation. Requires runtime evidence before fixes—never guess based on code alone. Covers hypothesis-driven debugging, instrumentation logging, Lua errors, taint issues, combat lockdown, and API failures. Triggers: error, bug, debug, fix, crash, taint, nil value, diagnose, hypothesis, runtime, evidence, instrumentation.

Fetches official documentation for external libraries and frameworks (React, Next.js, Prisma, FastAPI, Express, Tailwind, MongoDB, etc.) with 60-90% token savings via content-type filtering. Use this skill when implementing features using library APIs, debugging library-specific errors, troubleshooting configuration issues, installing or setting up frameworks, integrating third-party packages, upgrading between library versions, or looking up correct API patterns and best practices. Triggers automatically during coding work - fetch docs before writing library code to get correct patterns, not after guessing wrong.

Cross-platform disk space monitoring, analysis, and cleaning toolkit. Use when Claude needs to: (1) Analyze disk space usage and identify large files/directories consuming space, (2) Clean temporary files, caches, logs, and other junk files safely, (3) Monitor disk usage with configurable warning/critical thresholds, (4) Generate detailed reports on disk health and cleanup recommendations. Specializes in Windows C drive cleanup while maintaining full compatibility with Linux and macOS. Provides interactive CLI, automated scripts, and detailed reporting modes. All operations prioritize safety with built-in protection for system files.

Advanced Git repository helper that provides branch analysis, commit statistics, and automated workflow suggestions. Use this skill when you need to analyze repository state, generate insights about commit patterns, or get recommendations for Git workflows.

Crée une Pull Request en mode Continuous Delivery avec workflow complet : QA, labels version (major/minor/patch), feature flags, code review automatique.

Crée une Pull Request GitHub standard avec workflow complet : QA, commits, assignation milestone/projet, code review automatique.

Diagnose and fix rad-mem installation issues. Checks PM2 worker status, database integrity, service health, dependencies, and provides automated fixes for common problems.

Testing procedures. Invoke with /tzurot-testing for test execution, coverage audits, and debugging test failures.

Generate changelog from conventional commits with categorization (Features, Bug Fixes, Breaking Changes, Performance, Documentation) and formatted output for release notes.

Remote control tmux sessions for interactive CLIs (python, gdb, git add -p, etc.) by sending keystrokes and scraping pane output. Use when debugging applications, running interactive REPLs (Python, gdb, ipdb, psql, mysql, node), automating terminal workflows, interactive git commands (git add -p, git stash -p, git rebase -i), or when user mentions tmux, debugging, or interactive shells.

THOR Lens workflows for forensic timeline analysis. A web UI that imports THOR v11 audit trail JSONL logs for interactive exploration. Requires THOR v11 (audit trail not available in v10).

Generate AI videos using varg SDK React engine. Use when creating videos, animations, talking characters, slideshows, or social media content. Always run onboarding first to check API keys.

Create Claude Code hooks for static analysis and code quality. Provides pre-built linting, formatting, and type-checking hooks. Use when setting up project quality gates, enforcing code standards, or adding pre-commit style checks.

Claude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging.

Python asyncio patterns for concurrent programming. Triggers on: asyncio, async, await, coroutine, gather, semaphore, TaskGroup, event loop, aiohttp, concurrent.

Creates Claude Code hooks for static analysis and code quality. Provides pre-built linting, formatting, and type-checking hooks. Use when setting up project quality gates, enforcing code standards, or adding pre-commit style checks.

Slackチャンネルにフォーマット済みメッセージを送信するSkill。 「Slackに通知して」「チームに連絡して」「#channelに投稿して」 などのリクエストで自動発火する。 MCP連携（フルAPI）とWebhookフォールバック（送信のみ）の両方に対応。

Posts content to WeChat Official Account (微信公众号) via Chrome CDP automation. Supports article posting (文章) with full markdown formatting 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".

Scrape webpage content, extract metadata, download images, and prepare for import/migration to AEM Edge Delivery Services. Returns analysis JSON with paths, metadata, cleaned HTML, and local images.

This skill should be used when scanning container images, filesystems, or repositories for vulnerabilities using Trivy. Use for CVE detection, security analysis, vulnerability comparison across image versions, understanding scan output (severity levels, status fields), and batch scanning multiple images.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Helps users generate, edit, and validate mirrord.json configuration files for mirrord (MetalBear). Use when the user wants to connect their local process to a Kubernetes environment, configure features (env/fs/network), or needs feedback on an existing mirrord.json. Always ensures output JSON is valid and schema-conformant.

PR review and merge automation for OpenClaw maintainers. Review with opus, prep and merge with a gpt subagent. Use when asked to review, prep, or merge a PR.

google, gmail, email, google docs, sheets, calendar, drive.

Manage Google Tasks and task lists. Load when user mentions 'google tasks', 'tasks', 'todo list', 'create task', 'complete task', or references task/todo management.

Read, write, and manage Google Docs. Load when user mentions 'google docs', 'google document', 'create doc', 'read doc', 'write doc', 'edit document', or references creating/editing text documents in Google Drive.

Read and write Google Sheets data. Load when user mentions 'google sheets', 'spreadsheet', 'update sheet', 'read sheet', 'append to sheet', or references extracting data to update a tracking sheet.

Shared resource library for Google integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by gmail, google-docs, google-sheets, google-calendar, and future Google skills.

Shared resource library for Airtable integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, field types) and scripts used by airtable-connect, airtable-query, and airtable-sync.

heyreach, linkedin outreach, linkedin campaigns, add leads.

Internal resource library for HeyReach integration. Contains shared API client, operation scripts, and reference documentation.

heyreach, linkedin outreach, linkedin campaigns.

notebooklm, create notebook, audio overview, podcast.

Shared resource library for NotebookLM Enterprise integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by notebooklm-connect and individual NotebookLM skills.

Simple text-to-speech skill using MiniMax Voice API. Converts text to audio with customizable voice selection. Use for generating speech audio from text.

Find, install, and configure MCP servers. Use proactively for MCP discovery, OAuth setup, env vars, stdio vs SSE transport, or troubleshooting MCP connections. Examples: - user: "Add the filesystem MCP server" → read server file, add to mcpServers in opencode.json, verify transport type - user: "How do I use MCP with GitHub?" → check catalog, install @modelcontextprotocol/server-github, configure OAuth token - user: "MCP not connecting" → check transport type (stdio/SSE), verify args/command, check env vars are passed - user: "What MCPs are available?" → run list_mcps.py, show catalog with auth types and install commands

Find, install, and configure OpenCode plugins from the catalog or community. Use proactively when user asks about plugins, requests new capabilities, or mentions extending OpenCode functionality. Examples: - user: "Is there a plugin for Tailwind CSS?" → list catalog, read tailwind plugin details, install if available - user: "How do I add a custom slash command?" → suggest command-creator skill or guide through opencode.json setup - user: "What plugins are available for database work?" → list catalog, filter for database-related plugins - user: "Install the playwright plugin" → read plugin file, add to opencode.json, verify installation

LLMが適切に設計されたツールを通じて外部サービスと連携できる、高品質なMCP（Model Context Protocol）サーバーを作成するためのガイド。外部APIやサービスを統合するMCPサーバーを構築する場合に使用（Python（FastMCP）またはNode/TypeScript（MCP SDK）対応）。

Bookmark management CLI for searching, organizing, and syncing bookmarks with tagging, import/export, and browser integration. Use when helping end users manage bookmarks via CLI: (1) Adding and searching bookmarks, (2) Organizing with tags, (3) Importing from browsers or files, (4) Exporting and backing up, (5) Bulk operations and migrations.

Comprehensive Kubernetes cluster health diagnostics using dynamic API discovery. Use when checking cluster health, troubleshooting K8s issues, or running health assessments.

This skill enables interaction with BitBucket Server REST API for Pull Request management. Use when the user wants to create, review, comment on, merge, list pull requests, read comments, or manage tasks on BitBucket Server.

アプリケーションコードでの自動脆弱性検出のための静的アプリケーションセキュリティテスト（SAST）ツールを設定します。セキュリティスキャンの設定、DevSecOps実践の実装、またはコード脆弱性検出の自動化時に使用してください。

Helps developers author and debug Clix personalization templates

Comprehensive frontend testing strategy encompassing component tests, visual regression, accessibility, and E2E testing for modern web applications using Vitest, React Testing Library, Playwright, and Storybook.

API仕様に整合したリクエスト/レスポンス例とエラーレスポンス例を作成するスキル。 cURLとSDKサンプルを含め、実行可能で説明的な例示を短時間で整備する。

Model Context Protocol (MCP) 仕様と実装パターン。サーバー設定、ツール定義、LLM統合向けJSONスキーマ設計を提供。

Playwrightによるブラウザ自動化テストの実装技術。 安定した待機戦略、適切なセレクタ選択、効率的なテスト設計を提供します。

Inject Doc Detective test specs into documentation source files as inline comments. Use when (1) you have a valid test spec (JSON/YAML) with steps and need to embed them in a source file, (2) the user asks to add inline tests to documentation, (3) converting separate test files to inline format, or (4) placing test steps close to their associated content in Markdown, MDX, HTML, AsciiDoc, or XML/DITA files.

Generate a new rule with proper schema and OpenGrep patterns

Update an existing rule based on user intent

Create, validate, and publish Agent Skills following the official open standard from agentskills.io. Use when (1) creating new skills for AI agents, (2) validating skill structure and metadata, (3) understanding the Agent Skills specification, (4) converting existing documentation into portable skills, or (5) ensuring cross-platform compatibility with Claude Code, Cursor, GitHub Copilot, and other tools.

Agent Skill: DDEV setup for TYPO3 extension development. Use when setting up local dev environment or multi-version testing (11.5/12.4/13.4/14.0). By Netresearch.

This skill should be used by plugin authors who need to access wicked-search graph data for symbol dependencies, file references, definitions, or call chains. Triggered by queries about "graph data", "symbol dependencies", "cross-plugin search", "file references", "call chain", "blast radius from cache", or "cached graph". Enables other plugins to query the code graph without direct wicked-search coupling, using wicked-cache for efficient data sharing.

Extracts generated mockup images from Google Stitch project pages. Use when user provides a Stitch project URL (stitch.withgoogle.com/projects/...), mentions extracting/downloading Stitch mockups, saving Stitch designs, or wants to archive generated design assets. Requires authenticated Chrome browser profile.

Generate comprehensive model cards and upload fine-tuned models to Hugging Face Hub with professional documentation

Training manager for local GPU training - validate CUDA, manage GPU selection, monitor progress, handle checkpoints

Training manager for Hugging Face Jobs - launch fine-tuning on HF cloud GPUs with optional WandB monitoring

Component description

Use this skill when the user asks to read, understand, or modify USD shader graph structure in .usda/.usdz files, analyze material networks, modify shader parameters, or validate file integrity for RealityKit.

Search, retrieve, and analyze data from a MemoryLake Streamable HTTP MCP Server — the memory layer for AI Agents that provides intelligent unstructured file content retrieval and data analysis. Access the server directly via HTTP/curl (not via pre-configured MCP tools). Use this skill when the user wants to: (1) search for information across uploaded files in MemoryLake, (2) retrieve specific documents or data from MemoryLake, (3) analyze data stored in MemoryLake using Python code execution, (4) explore what's available in a MemoryLake memorylake, (5) ask natural-language questions about their files, or (6) perform data analysis, aggregation, or comparison across MemoryLake documents. Trigger phrases include: "search my files", "find in memorylake", "analyze my data", "what files do I have", "look up", "summarize my documents", "compare data across files", "run analysis on my data".

Apply billing and security best practices for payment/auth integrations. Invoke when: setting up Stripe/Clerk/auth, debugging payment issues, configuring webhooks, before prod deployment, after billing incidents.

Stripe integration patterns, parameter constraints, and debugging. Auto-invoke when: file contains stripe/payment/checkout/webhook, imports stripe package, references STRIPE_* env vars. Use for checkout mode selection, webhook signature verification, env var hygiene, subscription debugging.

Expert code review specialist. Reviews for quality and intent alignment. Use immediately after writing or modifying code, or when user requests code review. Handles both uncommitted changes and targeted file reviews.

Comprehensive guide for building, testing, and distributing Claude Code plugins including slash commands, Agent Skills, subagents, MCP servers, and hooks. Use this when the user asks about creating plugins, writing slash commands, implementing skills, building MCP tools, configuring hooks, plugin architecture, marketplace distribution, or debugging plugin components. Covers 2025 schema with tool permissions, version tracking, and activation triggers.

Automate chill.institute torrent/magnet ingestion into put.io. Use when asked to search, scan, or fetch torrent/magnet links from chill.institute and add them to put.io, or when troubleshooting the chill/put.io ingestion pipeline (cookies, profiles, put.io token).

从 GitHub Issue 或 Linear Issue 自动创建 Git 分支 + git worktree（含规范化分支名/目录名），用于 GitHub Flow 开发。用户提到“从 issue 创建 worktree/分支/开发目录”、给出 GitHub issue URL/#123/owner/repo#123，或给出 Linear issue URL/ABC-123 时使用；也适用于“为某个 issue 开一个独立工作区/隔离目录”的需求。

Structured output patterns with ensure_keys, ordering, and instant streaming.

This skill should be used when the user asks to "create a task in Things", "add a todo to Things 3", "manage Things projects", "schedule a task", "complete a todo", "delete a task from Things", "move task to Today", "add to Things inbox", "create a project in Things", "manage Things areas", or mentions Things 3 task management.

Uses shared scripts from [openapi-toolkit](../../../../../.claude/shared/openapi-toolkit/README.md).

Frontend website debugging toolkit using Chrome DevTools Protocol with Playwright/WebKit fallbacks. Use this skill when: (1) Debugging CSS, HTML, or JavaScript issues on a webpage, (2) Taking screenshots to verify visual changes, (3) Inspecting DOM structure or console errors, (4) Testing responsive layouts, (5) Extracting selectors for automation, (6) Self-debugging frontend work Claude has created, (7) User says "debug this page", "check my site", "why doesn't this look right", or "fix the frontend". Supports Chrome (primary) and Safari/WebKit (via Playwright). Designed for agent-driven debugging loops.

Generates Claude Code skills from user descriptions. Use when creating new skills, converting documentation to skills, or scaffolding skill structure.

Google APIs made easy — Gmail, Drive, Calendar, Tasks. Unified library and gateway CLIs (go-gmail, go-drive, go-calendar, go-tasks) for AI agents. Use when user needs to work with Gmail, Google Drive, Google Calendar, or Google Tasks. Replaces gmcli, gdcli, gccli.

Google Sign-In and Apple Sign-In with Supabase or custom backend. OAuth setup, platform config, PKCE/nonce security, sealed Failures, mock repository. Use when adding social login or troubleshooting OAuth.

Configure environment flavors (dev, staging, prod) for Flutter apps. Sets up compile-time variables via --dart-define-from-file, Gradle productFlavors, Xcode schemes, and per-environment configuration. Use when adding multi-environment support or separating dev/staging/prod builds.

Master YARAL query language for low-maintenance threat hunting and detection in Google SecOps. Build behavioral detections without magic strings or IOC lists. Use when writing YARAL queries, creating custom detections based on network/process behavior, debugging failing queries, or learning YARAL syntax and best practices.

Git operations with conventional commits. Use for staging, committing, pushing, PRs, merges. Auto-splits commits by type/scope. Security scans for secrets.

Prompt testing, metrics, and A/B testing frameworks

Download Claude Code templates from aitmpl.com (GitHub API). Use PROACTIVELY to search and install agents, commands, skills, mcps, settings, hooks, and plugins.

Shared resource library for Airtable integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, field types) and scripts used by airtable-connect, airtable-query, and airtable-sync.

Internal resource library for HeyReach integration. Contains shared API client, operation scripts, and reference documentation.

This skill should be used when managing documentation files in an Obsidian vault, including creating session artifacts, moving planning documents from project directories to the vault, updating document lifecycle states (active → processed → archived), searching for documents by tags or content, and automating archival of old documents. Integrates with task-startup/task-wrapup workflows for any coding project.

Operate Atlassian Jira through the official jira CLI; trigger this skill to list, inspect, create, update, triage, or report on Jira work using deterministic shell commands aligned with Jira MCP workflows.

.NET 코드에서 정적 분석(Static analysis), 보안 스캔(Security scan) 및 종속성 체크(Dependency check)를 수행합니다. 코드 품질, 보안 감사 또는 취약점 탐지가 포함된 작업에서 사용합니다.

dotnet format, prettier 및 기타 포맷팅 도구를 사용하여 코드를 정리합니다. 코드 스타일 수정, 포맷 일관성 유지 또는 커밋 전 코드 준비가 필요한 작업에서 사용합니다.

Discovers, validates, and integrates Model Context Protocol (MCP) tools into Claude Code skills. Searches MCP catalogs, scores candidates, generates tool configurations, and optionally sets up Docker runtimes. Use when creating skills that need external MCP tool integration.

Use PROACTIVELY when creating new Claude Code skills from scratch. Automated generation tool following Claudex marketplace standards with intelligent templates, pattern detection, and quality validation. Supports guided creation, quick start templates, clone-and-modify, and validation-only modes. Not for modifying existing skills or non-skill Claude Code configurations.

Expert code reviewer. Use after code changes.

Use PROACTIVELY when creating new Claude Code skills from scratch. Automated generation tool following Claudex marketplace standards with intelligent templates, pattern detection, and quality validation. Supports guided creation, quick start templates, clone-and-modify, and validation-only modes. Not for modifying existing skills or non-skill Claude Code configurations.

Converts documents to markdown (PDFs, Word docs, PowerPoint, Confluence exports) with Windows/WSL path handling. Activates when converting .doc/.docx/PDF/PPTX files to markdown, processing Confluence exports, handling Windows/WSL path conversions, or working with markitdown utility.

Execute external CLI AIs as isolated sub-agents for task delegation, parallel processing, and context separation. Use when delegating complex multi-step tasks, running parallel investigations, needing fresh context without current conversation history, or leveraging specialized agent definitions. Returns structured JSON with agent output, exit code, and execution status.

Decomposes vague, high-level project requirements into well-scoped planning units for /deep-plan. Use when starting a new project that needs to be broken into manageable pieces.

Define Neon Postgres schema and migration workflow for chatbot sessions, messages, users, and optional onboarding profile fields. Use when setting up database persistence for RAG chatbots, adding authentication/onboarding tables, or creating new migrations for message metadata (selected text, citations, document IDs). Supports init scripts, Alembic, Prisma, and raw SQL workflows.

Convert legacy agent resources to the unified [Agent Skills](https://agentskills.io) format.

Generate audio tracks from text using ElevenLabs eleven_v3 model. Presents available voices, allows language selection, and lets you review/modify text before generating. Requires ELEVENLABS_API_KEY environment variable.