AI Skills Hub - Browse 180,000+ Agent Skills

查阅和使用《君主论》及相关研究的参考文献。当需要查找人名地名位置、查阅意大利文/英文/中译本版本信息，或进行马基雅维利研究时使用此技能。

分析马基雅维利政治哲学中的自由维持与权力巩固问题。当分析习惯君主制或腐败民族的自由维持、新君主的权力巩固、从卑微运道崛起者的策略，或应对机运（Fortuna）的方法时使用此技能。

Remove backgrounds from images using rembg. Use when user has images with backgrounds that need to be transparent, wants to batch process images, or needs PNGs with alpha channels.

Diagnose and fix oh-my-codex installation issues

This skill should be used when the user asks to "check my mattermost messages", "fetch DMs", "what did X say", "check messages from coworker", "read mattermost", or mentions mattermost conversations, chat history, or finding tasks mentioned in chat.

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

Fetches Zig language and standard library documentation via CLI. Activates when needing Zig API details, std lib function signatures, or language reference content that isn't covered in zig-best-practices.

Titanium Alloy CLI and configuration guide. Use when creating, reviewing, analyzing, or examining Alloy projects, running alloy commands (new, generate, compile), configuring alloy.jmk or config.json, debugging compilation errors, creating conditional views, using Backbone.Events for communication, or writing custom XML tags.

Titanium SDK native feature integration guide. Use when implementing, reviewing, analyzing, or examining Titanium location services, maps (Google Maps v2, Map Kit), push notifications (APNs, FCM), camera/gallery, media APIs, SQLite databases, HTTPClient networking, WKWebView, Android Intents, background services, iOS Keychain/iCloud, WatchKit/Siri integration, or CI/CD with Fastlane and Appium.

Titanium SDK UI/UX patterns and components expert. Use when working with, reviewing, analyzing, or examining Titanium layouts, ListView/TableView performance optimization, event handling and bubbling, gestures (swipe, pinch), animations, accessibility (VoiceOver/TalkBack), orientation changes, custom fonts/icons, app icons/splash screens, or platform-specific UI (Action Bar, Navigation Bar).

Titanium Alloy MVC official framework reference. Use when working with, reviewing, analyzing, or examining Alloy models, views, controllers, Backbone.js data binding, TSS styling, widgets, Alloy CLI, sync adapters, migrations, or MVC compilation. Explains how Backbone.js models and collections work in Alloy.

Titanium PurgeTSS utility-first styling toolkit. Use when styling, reviewing, analyzing, or examining Titanium UI with utility classes, configuring config.cjs, creating dynamic components with $.UI.create(), building animations, using grid layouts, setting up icon fonts, or working with TSS styles. Never suggest other CSS framework classes - verify in class-index.md first.

Comprehensive HWPX (Korean Hancom Office) document creation, editing, and analysis. When Claude needs to work with Korean word processor documents (.hwpx files) for: (1) Reading and extracting content, (2) Creating new documents, (3) Modifying or editing content, (4) Extracting tables to CSV, (5) Modifying tables or table cells, or any other HWPX document tasks. MANDATORY TRIGGERS: hwpx, hwp, 한글, 한컴, Hancom, Korean document

Integrate Outlit SDK for customer journey tracking and analytics. Triggers when users need to add Outlit to React, Next.js, Vue, Svelte, Angular, Astro, Node.js, Express, or Fastify apps. Covers SDK installation (@outlit/browser, @outlit/node), auth provider integration (Clerk, NextAuth, Supabase, Auth0, Firebase), GDPR consent management, event tracking, user lifecycle events (activate, engaged, inactive), customer billing status (trialing, paid, churned), and Stripe webhook integration.

Procedural CLI invocation details for the Codex agent

Traffic Light Protocol (TLP) file access control. This skill should be used when the user asks about TLP levels (RED, AMBER, GREEN, CLEAR), file classification, reading protected files, safe-read, blind-metadata, redacted reading, inline redaction markers, secret detection, .tlp configuration, file access policies, or frontmatter TLP overrides.

Recorder CLI skill that captures HTTP payloads during debugging sessions and allows to review and log recent requests quickly.

Datadog 日志/Trace/依赖查询工具集合，支持 Flex/Rehydrated 日志、Trace span 解析与服务依赖分析

Mobile browser automation via ATL (iOS Simulator). Navigate, click, screenshot, and automate web tasks on iPhone/iPad simulators.

Securely execute commands requiring API keys without exposing secrets in session logs

Ink CLI framework patterns for building React-based terminal UIs. Use when working with Ink framework for CLI development, building terminal interfaces with React, or need guidance on Ink components (Box, Text, Static), hooks (useInput, useFocus, useStdout), layout patterns, performance optimization, or understanding Ink's internal architecture.

Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.

Use nous-genai as an end user (not a contributor): run `genai` CLI for text/image/audio/video/embedding across providers (OpenAI/Gemini/Claude/DashScope/Doubao/Tuzi), save binary outputs, list available models, and start a local MCP server (Streamable HTTP/SSE) with auth. Use when setting up `.env.local` provider keys, choosing `{provider}:{model_id}`, or debugging common issues (auth/timeout/SSRF-download/MCP bearer-token rules). 中文: 用 nous-genai 调用多家大模型 + 启动 MCP 服务 + 排错。

Create OpenClaw plugins/extensions (TypeScript modules) from natural‑language requests. Use when the user asks to create a plugin/extension, add a new slash command, add plugin tools, or says “create plugin that does …” or “create OpenClaw plugin called NAME …”. Trigger for /create-plugin NAME WHAT-IT-DOES, /create-plugin GENERAL-PROMPT, “create extension that does ACTION”, or similar.

Dokploy 셀프호스팅 PaaS 플랫폼의 전체 관리 스킬. SSH 및 API를 통한 서버 관리, 애플리케이션 배포, Docker Compose/Swarm 관리, 데이터베이스(PostgreSQL, MySQL, MongoDB, Redis) 관리, Traefik 리버스 프록시 설정, SSL 인증서(Let's Encrypt, Cloudflare Origin CA), 도메인 설정, 볼륨 백업/복원, 컨테이너 모니터링, 서버 문제 해결 및 디버깅을 지원합니다. 이 스킬 사용 시점: (1) "Dokploy", "dokploy" 언급 시 (2) 애플리케이션 배포/재배포 요청 (3) Docker Compose 또는 Swarm 관련 작업 (4) 도메인 설정, SSL 인증서, HTTPS 설정 (5) Traefik 설정 확인/수정, 502 에러, 도메인 접속 문제 (6) 데이터베이스 생성, 백업, 복원 (7) 볼륨 백업/복원, S3 연동 (8) 컨테이너 로그 확인, 서버 상태 점검 (9) 서버 유지보수, Dokploy 업데이트 (10) 빌드 타입 선택 (Nixpacks, Dockerfile, Buildpack) (11) 와일드카드 도메인(SAN 인증서)에서 특정 서브도메인을 별도 컨테이너로 라우팅 (12) pgAdmin4 설치, 설정, 도메인 연결

Understand the Flavorful cookbook file structure, recipe markdown format, and user preferences in COOK.md. Use when you need to read, interpret, or work with cookbook files but no specific action like find, save, or start is needed.

Search the user's Flavorful recipe collection by ingredients, cuisine, technique, or dietary needs. Use when the user asks what they can cook, searches for recipes, or mentions available ingredients.

OpenSpec usage guide and workflow reference. Triggers when users ask about OpenSpec, including: (1) how to use /opsx commands, (2) OpenSpec workflow explanations, (3) Spec-Driven Development (SDD) best practices, (4) purpose and format of proposal, specs, design, and tasks files, (5) delta specs concepts and usage.

(CryptoView - Skill) 加密货币与贵金属市场数据分析。获取 OKX 交易所的 K线、资金费率、持仓量、多空比等实时数据, 并且进行技术分析的脚本。MUST USE for any crypto/market data queries.

Manages SOPS-encrypted Kubernetes secrets for Flux GitOps deployments using age encryption

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

Add new equipment to the fleet configuration via natural language

This skill should be used when working with Dockerfile, docker-compose.yml, compose.yml, docker-bake.hcl, .dockerignore, or any container image development. Covers Dockerfile best practices, CI testing patterns, and Docker Compose orchestration. By Netresearch.

Show status of all active tasks across repos. Use when user asks "what's the status", "what am I working on", or to get overview of active work.

Resume a task using fuzzy matching across all repos. Use when user wants to continue previous work, says "resume", "continue", or references a past task.

Show all projects with current status. Manager-specific skill for cross-project visibility.

Turn PowerPoint files (.pptx/.ppt) into a structured knowledge document (Markdown + JSON). Use when you need to extract slide text, speaker notes, and images; OCR text inside screenshots/diagrams; and generate an executive summary, key points, glossary, and slide-by-slide notes.

Master Laravel queues and job processing with queue drivers, job batching, chaining, failure handling, Horizon monitoring, and advanced queue patterns. Use when implementing background job processing, async tasks, scheduled work, or building scalable job pipelines.

SolidWorks API patterns for C#. Use when writing SW API code.

Analyze timing data from QA runs to identify performance bottlenecks and track regressions. Run after /qa to see what's slow.

Guide for setting up the TL;DR Buccaneer bot on Leviathan News

Pyron is the asset productivity layer of Fogo - overcollateralized lending and borrowing protocol.

Get current machine context (OS, frontmost app, clipboard, battery, network, calendar, reminders) via the os-context CLI. Use when the user asks what they're doing, what's on screen, battery status, calendar, reminders, or when you need local context to tailor your response.

This skill should be used when executing Bankr requests, submitting prompts to Bankr API, polling for job status, checking job progress, using Bankr MCP tools, or understanding the submit-poll-complete workflow pattern. Provides the core asynchronous job pattern for all Bankr API operations.

This skill should be used when the user asks about "Bankr API", "Bankr Agent API", "how does Bankr work", "Bankr job status", "Bankr response format", or "building on Bankr". Provides endpoint documentation, job patterns, and TypeScript interfaces.

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

Design PROSE-compliant AI-native code in Markdown. Use when (1) Writing prompts, instructions, or agent definitions (2) Designing multi-primitive AI systems from requirements (3) Decomposing mega-prompts into composable primitives (4) Auditing prompts/instructions for reliability issues. PROSE = Progressive Disclosure, Reduced Scope, Orchestrated Composition, Scoped Boundaries, Explicit Hierarchy

Build RAG pipelines with Exa.ai for real-time web retrieval. Use when building retrieval-augmented generation, integrating Exa with LangChain, LlamaIndex, Vercel AI SDK, or implementing AI agents with web search capabilities. Triggers on: RAG pipeline, retrieval augmented generation, Exa LangChain, Exa LlamaIndex, ExaSearchRetriever, ExaSearchResults, Exa MCP, Exa tool calling, Claude tool use, AI agent web search, grounded generation, citation generation, fact checking, hallucination detection, OpenAI compatibility, chat completions.

Exa.ai deep research and answer generation with citations. Use when building research automation, implementing Answer API for Q&A with sources, creating research reports, or using deep search with summaries. Triggers on: Exa Answer, answer endpoint, exa.answer, deep search, research API, Exa Research, async research, research report, citation extraction, summarization with sources, fact verification, streaming answers, research tasks.

Exa.ai company and people search for lead generation, competitive intelligence, and data enrichment. Use when searching for companies, finding people profiles, building lead gen tools, or implementing Websets for data collection at scale. Triggers on: Exa company search, Exa people search, category company, lead generation, company research, profile search, LinkedIn profiles, Websets API, data enrichment, company lookup, find companies, competitive intelligence, recruiting, talent search, 1B profiles.

NestJS 11+ best practices for enterprise Node.js applications with TypeScript. Use when writing, reviewing, or refactoring NestJS controllers, services, modules, or APIs. Triggers on: NestJS modules, controllers, providers, dependency injection, @Injectable, @Controller, @Module, middleware, guards, interceptors, pipes, exception filters, ValidationPipe, class-validator, class-transformer, DTOs, JWT authentication, Passport strategies, @nestjs/passport, TypeORM entities, Prisma client, Drizzle ORM, repository pattern, circular dependencies, forwardRef, @nestjs/swagger, OpenAPI decorators, GraphQL resolvers, @nestjs/graphql, microservices, TCP transport, Redis transport, NATS, Kafka, NestJS 11 breaking changes, Express v5 migration, custom decorators, ConfigService, @nestjs/config, health checks, or NestJS testing patterns.

Vue 3 and Vue.js best practices for TypeScript, vue-tsc, Volar, and component patterns. Use when writing, reviewing, or refactoring Vue 3 components with TypeScript, configuring Volar/vueCompilerOptions, extracting component types, working with defineModel/withDefaults, setting up Pinia store tests, or debugging Vue tooling issues. Triggers on Vue components, props extraction, wrapper components, template type checking, strictTemplates, vueCompilerOptions, Volar 3, CSS modules, fallthrough attributes, defineModel, withDefaults, deep watch, vue-router typed params, Pinia mocking, HMR SSR, moduleResolution bundler, useTemplateRef, onWatcherCleanup, useId, generic components, reactive props destructure.

Test GitHub Actions workflows locally before pushing to GitHub using Docker and the 'act' CLI tool. Use this skill when users want to run CI locally, debug workflow failures, or validate GitHub Actions changes without pushing commits.

Merges a Pull Request using GitHub CLI after verifying CI passes. Handles squash merge, remote branch cleanup, and local sync. Local branch is ALWAYS preserved (never auto-deleted). Use when user wants to merge a PR or asks to complete/finish a feature.

Look up Microsoft API references, find working code samples, and verify SDK code is correct. Use when working with Azure SDKs, .NET libraries, or Microsoft APIs—to find the right method, check parameters, get working examples, or troubleshoot errors. Catches hallucinated methods, wrong signatures, and deprecated patterns by querying official docs.

プロジェクトドキュメント（仕様書・レトロ）の新規作成

既存ドキュメントの更新・修正（仕様変更反映、情報追加など）

Annotate a Spec/PRD with Feature IDs and generate a Coverage Index. Use when user wants to add spec tags to a vision document, create F-nnn identifiers, set up traceability, or initialize a PRD framework for phased development.

Implement reactive state management with Jotai atoms in Electron renderer. Use when creating atoms with real-time IPC updates or hybrid stream + HTTP patterns.

Run code quality checks for Laravel Spectrum (PHPStan, Laravel Pint, PHPUnit). Use when user mentions "lint", "format", "code quality", "PR準備", "コミット前チェック", or before creating commits/PRs. Also use after writing significant code changes.

Delegate simple, fast tasks to GPT-5-mini Quick-Helper agent. Use when (1) Simple file operations needed (finding files, listing directories, basic grep), (2) Quick validations required (file existence, JSON validation, simple tests), (3) Fast transformations (string manipulation, format conversions), (4) Repetitive tasks (batch operations, loops), (5) Speed matters and task is straightforward. DO NOT use for complex code implementation, user perspective reviews, test writing, or deep analysis - Main Claude handles those.

Monitor and analyze narrative API logs from Google Cloud Run. Use when (1) Investigating Cloud Run API errors or failures, (2) Analyzing API usage costs and optimizing spend, (3) Measuring scenario generation performance (duration, citations), (4) Reviewing custom scenario generation requests, (5) Understanding user/IP access patterns, (6) Debugging production issues. DO NOT use for local Docker debugging (use docker logs), real-time monitoring (Cloud Logging has 1-2min delay), or Vite dev server logs (use browser console).

PixelLab MCP for generating pixel art game assets. TRIGGERS: pixel art, sprite, character sprite, tileset, Wang tiles, isometric, top-down tiles, sidescroller tiles, map objects, game assets, character animation, walk cycle, idle animation, attack animation, PixelLab MCP, create_character, animate_character, create_topdown_tileset, create_map_object USE WHEN: Generating pixel art characters, creating tilesets for maps, making game objects (collectibles, props, furniture), animating characters, building consistent visual asset sets, or setting up asset production pipeline. TOKEN BUDGET: ~520 tokens (SKILL.md only), ~1800 with references NOTE: Non-blocking workflow - queue jobs and check status later (2-5 min processing)

Blender MCP for 3D game asset creation and scene building. TRIGGERS: 3D model, Blender, mesh, material, texture, HDRI, lighting, fbx export, gltf export, glb, Poly Haven, Sketchfab, Hyper3D, 3D scene, low-poly, game-ready model, UV mapping, Blender MCP, execute_blender_code, 3D character, 3D prop, 3D environment, rigging, armature, keyframe USE WHEN: Creating 3D models, setting up game scenes, applying materials, importing assets from Poly Haven/Sketchfab, generating models with Hyper3D, rigging characters, creating animations, exporting to Unity/Godot formats. TOKEN BUDGET: ~520 tokens (SKILL.md only), ~2200 with references NOTE: Blender must be running with addon installed. Code execution is powerful but requires caution - always save before complex operations. COMPATIBILITY: Blender 3.0+ recommended. Some operators (triangulate, decimate) have slight API changes between versions.

This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style. It applies when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals, Basecamp, HEY, or Campfire style. Embodies REST purity, fat models, thin controllers, Current attributes, Hotwire patterns, and the "clarity over cleverness" philosophy.

Capture solved problems as categorized documentation with YAML frontmatter for fast lookup

This skill provides expert guidance for creating, writing, building, and refining Claude Code Skills. It should be used when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

CRM and automation integration patterns for lead gen sites. Webhooks, Zapier, Make, HubSpot, Pipedrive. Use for connecting forms to business systems.

Design system foundation. Colors, typography, spacing. Single source of truth. No raw values.

Internationalization patterns for Astro sites. Multi-language routing, content translation, locale switching, RTL support. Use for multi-market lead generation.

Accessibility patterns for Astro lead generation sites. WCAG 2.1 AA compliance, screen readers, keyboard navigation, focus management, ARIA. Use for all accessibility implementation.

Social proof patterns for lead generation sites. Testimonials, reviews, trust badges, stats, logos. Use for building trust and credibility.

Analytics and conversion tracking for lead generation websites. Use when implementing GTM, GA4, or any measurement. Works with astro-architecture for GTM setup. No CRO mérés nélkül vakrepülés.

A/B testing patterns for lead generation sites. Client-side experiments, Google Optimize alternative, analytics integration. Use for conversion optimization.

Testing and QA gate for Astro lead gen sites. Manual + E2E + A11y + Performance. FAIL = no deploy.

Width-based responsive image patterns for Astro. Aspect ratio independent.

Generate CLAUDE.md project files. Execution contracts that eliminate ambiguity.

Schema.org structured data patterns for lead gen sites. LocalBusiness, FAQ, HowTo, Service, Review, BreadcrumbList. Rich snippets for better SERP visibility.

Generates Astro component skeleton with slots. Stateless, deterministic. No content.

Keyword research for UK local service businesses. Generates silo-compatible keyword map. Binding input for heading-tree and internal-linking skills.

Project handover process for lead generation websites. Documentation, training, credentials, maintenance. Use when project complete.

Extract text from cardiology research paper PDFs - **FREE, runs locally**.

Or use in Claude Code: ``` "Create a carousel about statins myth-busting" "Generate Instagram slides for GLP-1 benefits" "Turn this newsletter into carousel slides: [paste content]" ```

Instagram carousel generator. Creates 1080x1080px branded slides from text/markdown input. Use this skill when you need to generate Instagram carousel slides with Dr. Shailesh Singh's brand colors, typography, and footer. Supports both @heartdocshailesh and @dr.shailesh.singh accounts.

Transform AI-sounding writing into natural, human prose. Use when creating or editing any written content—articles, essays, reports, emails, social posts, scripts, or marketing copy—to avoid patterns that signal AI authorship. Triggers on requests to "make it sound human," "less AI," "more natural," improve voice/tone, or any writing task where authentic style matters.

Comprehensive estate planning assistant that guides users through document preparation with state-specific intelligence, educational guidance, and professional boundaries. Auto-invokes when users mention wills, trusts, estate planning, power of attorney, healthcare directives, beneficiary designations, or related topics.

RF signal scanning, IoT discovery, and spectrum monitoring. Use when user mentions SDR, radio, signal, frequency, spectrum, FM, IoT, 433 MHz, antenna.

Facilitate brainstorming sessions as a thinking partner. Use when users want to brainstorm, generate ideas, explore possibilities, or need help thinking through options. This skill positions AI as a FACILITATOR that extracts and expands the user's own ideas rather than just generating ideas for them. Triggers on requests like "help me brainstorm", "I need ideas for", "let's think through", "what are my options for".

Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before releasing openai-agents-python.

Integrate Mol* (MolStar) with MolViewSpec into Jupyter notebooks, Marimo notebooks, or custom webapps for visualizing molecules (PDB, SDF, MMCIF, and more) or trajectories (XTC), and for customizing layout and appearance using selectors and primitives.

Use when a task needs headless browser automation (navigate, click, fill forms, extract text, take screenshots) and Playwright-based tooling should be avoided; prefer the agent-browser CLI.

Provides expertise for analyzing DWARF debug files and understanding the DWARF debug format/standard (v3-v5). Triggers when understanding DWARF information, interacting with DWARF files, answering DWARF-related questions, or working with code that parses DWARF data.

Scans Cosmos SDK blockchains for 9 consensus-critical vulnerabilities including non-determinism, incorrect signers, ABCI panics, and rounding errors. Use when auditing Cosmos chains or CosmWasm contracts. (project, gitignored)

Scans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithmetic overflow, panic DoS, incorrect weights, and bad origin checks. Use when auditing Substrate runtimes or FRAME pallets. (project, gitignored)

Meta-skill that analyzes the Trail of Bits Testing Handbook (appsec.guide) and generates Claude Code skills for security testing tools and techniques. Use when creating new skills based on handbook content.

Use Windows Chrome from WSL via Chrome DevTools Protocol with a stable CDP profile.

当需要查询或分析高熵合金(HEA)描述符数据时使用。 适用场景： - 根据6种元素组合查询对应的描述符数据表 - 按描述符条件筛选满足特定性质的合金成分 - 关联描述符与成分比例(con_index JOIN hea_con_6) - 跨多个元素组合批量搜索符合条件的成分 - 导出特定系统的全部描述符数据用于ML训练 数据范围：15个元素中任选6个组成的5005种高熵合金系统。

Operations and troubleshooting workflows for lidx. Use when debugging indexing issues, MCP server problems, or managing releases.

Use when developing Lua plugins for Neovim, including user commands, keymaps, lazy loading, health checks, or help documentation. Apply best practices for <Plug> mappings, deferred require, proper structure, even when user requests shortcuts or quick solutions.

Vercel MCP 伺服器管理技能。用於設定 Vercel MCP、管理專案、部署、環境變數、domains 等 Vercel 操作。