AI Skills Hub - Browse 180,000+ Agent Skills

Search the web and get AI-powered answers using GPT-5 or GPT-5.2 models. Use when you need current information, web search results, or want to consult GPT-5/5.2 for complex analysis, coding questions, or research. Requires OPENAI_API_KEY environment variable.

This skill should be used when a Claude Code plugin command is not visible, plugin not loading, or plugin errors occur. Provides systematic diagnostic flow for plugin issues.

A comprehensive skill for handling bulk question data ingestion for exam preparation applications. This skill provides robust patterns for merging, validating, deduplicating, and inserting question data into Supabase.

Patterns for testing authenticated HTTP routes. Keywords: route, testing, patterns.

Machine-writable entrypoints and marker blocks. Keywords: markers, machine-writable, entrypoints.

Provider wrapper mapping and integration. Keywords: skills, integration, providers.

Scaffold a new module instance with MANIFEST.yaml and required files. Keywords: module, scaffold, MANIFEST.

Scaffold service packaging configuration. Keywords: packaging, service, devops, scaffolding.

Scaffold job deployment configuration. Keywords: deploy, job, devops, scaffolding.

Scaffold job packaging configuration. Keywords: packaging, job, devops, scaffolding.

Generate a ralph-wiggum loop prompt for iterative development tasks. Use when asked to create a ralph-loop prompt, or when a task needs iterative execution until CI/tests pass.

Kubernetes cluster troubleshooting skill for interactive problem-solving with Claude Code. Handles debugging and fixes for pods, services, deployments, Tekton pipelines, Crossplane XRs, and ArgoCD applications across namespaces. Tracks all changes declaratively in YAML format, integrates with Jira for documentation, and ensures GitOps-compliant workflows. Use when debugging Kubernetes issues, fixing cluster problems, or needing systematic K8s troubleshooting with full change tracking.

Управление Service Level Agreements в технической поддержке облачного провайдера. Включает design, monitoring, compliance tracking и continuous improvement. Use when designing SLAs, tracking compliance, calculating service credits, or analyzing performance.

Interact with Moltbook (the AI agent social network) — post, browse, comment, vote, search — via shell curl.

Guide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object detection, segmentation, and multi-image comparison. Use when analyzing images, answering visual questions, detecting objects, or processing documents with vision.

Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel

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

This file provides Claude with instructions for interacting with Outline Wiki via the `outlinectl` CLI.

Manage git worktrees for feature development. Use when asked to create a new worktree, delete/remove a worktree, list worktrees, or work on features in isolation. Creates worktrees at ~/worktrees/{repo}/{feature}, copies .env and dotfiles, opens VS Code with Claude extension.

Expert Git workflow assistant with dual modes (Guide/Worker). Master of worktrees and submodules. Provides safety-first git operations, configuration optimization, repository health monitoring, and modern git feature awareness. Use when working with git repositories, worktrees, submodules, or needing git workflow guidance.

Turborepo 모노레포 명령어, 필터 문법, 캐시 관리 가이드입니다. 특정 앱만 빌드/실행, 변경 감지, 캐시 문제 해결, CI/CD 설정 요청 시 사용합니다.

Copywriting dla bloga portfolio Pawla Lipowczana (pawellipowczan.pl). Uzyj przy tworzeniu nowych artykulow na blog, generowaniu tresci SEO, pisaniu case studies. Zawiera styl pisania autora (bezposredni, praktyczny, osobisty), strukture artykulow (front matter YAML, hierarchia H1-H3), kategorie (Automatyzacja/No-Code/AI), wytyczne SEO, szablony artykulow. Skill generuje artykuly zgodne z tonem i formatem istniejacych publikacji na blogu.

Use PROACTIVELY when orchestrating parallel agents from the main branch. Auto-trigger when user asks about agent status, wants to check on parallel work, needs to see what agents are doing, or wants to monitor autonomous agents. Provides commands to view agent statuses and launch the monitoring TUI.

Compare local tasks with Plane issues. Use when user says "discover plane", "compare tasks", "show unlinked issues", or "plane backlog".

Deploy backend/frontend to Fly.io, commit changes, wake sleeping machines, and maintain deployment log. Use when user wants to deploy, redeploy, check deployment status, wake machines, or update production.

Meta-patterns for external APIs (cloud SDKs, third-party modules). Use when writing code that calls external APIs (Microsoft Graph, Exchange Online, Azure, AWS, etc.). Covers connection verification, modular imports, property evolution, return types. Do NOT load for internal PowerShell code.

Core development workflows, patterns, and conventions for IterableData. Use when implementing features, fixing bugs, or working with the codebase structure.

OpenSpec proposal creation, validation, and implementation workflows. Use when creating change proposals, implementing specs, or working with OpenSpec conventions.

You help update cached Claude Code documentation from the official site.

You create high-quality Claude Code skills. Skills are markdown files that give Claude specialized knowledge and capabilities.

Generalized Git skillset that unifies advisory guidance, safe execution, workflow specialization, and recovery. Provides 5 operational modes and references to the git subskills in this repo.

Crisis management for Git mistakes using reflog, fsck, and safety-first recovery workflows. Recover lost commits, branches, and undo destructive operations.

Master-level guidance for safe rebasing and interactive history cleanup. Focuses on the golden rule, conflict workflows, autosquash, and recovery strategies.

Master-level expertise in git notes for attaching metadata to commits without rewriting history. Focuses on namespaced refs, safe usage, syncing, and AI agent metadata patterns.

Run pre-built animated light patterns on Govee devices including rainbow waves, fire effects, ocean waves, disco party, strobes, and pulse effects. Use when the user wants to run animated patterns or special lighting effects on their Govee lights.

Control Govee smart lights locally via LAN API - turn on/off, adjust brightness, set RGB colors, change color temperature. Use when the user wants to control Govee device settings or change light properties.

iOS Simulator UI automation and testing guidance. Use when building iOS apps, automating UI interactions, running simulator tests, or debugging accessibility issues. Covers build operations, simulator lifecycle, UI automation via IDB, and deep link testing.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

Use when improving code structure without changing behavior, cleaning up technical debt, or preparing code for new features

Summarize articles, videos, documents, and local files

Databricks Jobs management, monitoring, and debugging. Use for job status checks, run history, failure investigation, job execution, and historical analysis. Triggers: job status, run history, job failure, debug job, run job, cancel job, repair run, job metrics, failure analysis. Real-time operations use CLI (databricks jobs). Historical analysis uses System Tables (system.lakeflow.*).

Query formulation and context assembly patterns for memory retrieval. Use when you need to search the memory graph effectively.

Detect candidate charades/segmentations (building a word from parts) and emit CANDIDATE blocks (no interpretation or ordering).

Detect candidate reversals (backwards readings) and emit CANDIDATE blocks (no interpretation or ordering).

Detect candidate hidden words (contiguous substrings across word boundaries) and emit CANDIDATE blocks (no interpretation or ordering).

Detect candidate spoonerisms (initial sound swaps, usually adjacent words) and emit CANDIDATE blocks (no interpretation or ordering).

Detect candidate double definitions (one span plausibly cluing two meanings) and emit CANDIDATE blocks (no interpretation or ordering).

Detect candidate allusions/quotations (quote-like spans) and emit CANDIDATE blocks labelled as candidates (no attribution or ordering).

Detect candidate deletions/subtractions (headless/tailless/heartless, etc.) and emit CANDIDATE blocks (no interpretation or ordering).

Detect candidate anagrams in minimal spans and emit CANDIDATE blocks (no interpretation or ordering).

Detect candidate homophones (sound-alikes) and emit CANDIDATE blocks (no interpretation or ordering).

当在评估系统架构、平台设计或高层代码库结构时，关注可扩展性、可靠性、耦合、数据一致性或运行风险时使用。

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

This skill provides guidance for using the gh-pr-review GitHub CLI extension to view and manage inline PR review comments from the terminal. Use this skill when working with pull request reviews, viewing inline code review threads, replying to comments, starting/submitting reviews, resolving threads, or when needing structured JSON output for PR review workflows. Triggers on requests like "show PR review comments", "reply to this thread", "start a review", "resolve threads", "view unresolved comments", or any PR code review task.

Create well-structured GitLab issues and epics with proper labels, templates, and GitLab conventions. Use when creating bug reports, feature proposals, maintenance tasks, spikes, or epics. Automatically searches for duplicates, applies appropriate labels based on content, follows GitLab development workflows, and supports post-creation collaboration through comments and discussion threads.

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

REPL debugging tool for capturing and inspecting local scope at runtime. Use when debugging functions, investigating test failures, understanding intermediate values, or when you need to recreate the runtime context of code without manually fabricating values.

Use when users need help generating safe, tested POSIX shell commands from natural language descriptions. Guides users through command generation, safety validation, and execution workflows using Caro best practices

Use when creating Docusaurus plugins (remark, rehype, theme, content, lifecycle) to extend markdown, modify HTML, or add custom functionality

Infrastructure層の実装パターン。Repository実装, 外部サービス連携, Prisma。 技術的詳細の実装、DIP遵守。 トリガー例: - 「Repository実装」「Prisma」「外部API」 - 「Infrastructure層」「データベース」 - src/layers/infrastructure/ 配下のファイル編集時

Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.

Manages bidirectional synchronization between PD20_Automaton_PLC交握表.xlsx (PC UI development interface specification) and 50-layer markdown documentation (PLC memory mapping). Use when (1) Syncing signals from work logs to Excel and markdown, (2) Detecting conflicts in memory address allocation, (3) Checking consistency between Excel and markdown, (4) Updating Excel based on markdown changes, (5) Updating markdown based on Excel changes, (6) Any task involving PD20 PLC memory mapping management, signal definition updates, or PC-PLC interface synchronization. This skill manages CRUD operations on both Excel and markdown files, with emphasis on conflict detection and semi-automated workflows requiring user confirmation.

Documentation architecture design and management for equipment projects. Use for: (1) Creating layered doc structure, (2) Determining content placement, (3) Managing change impact, (4) Simplifying redundant content. Triggers (CN): 文件架構、分層設計、文件該放哪、改了要更新哪些、文件太長、高內聚低耦合. Triggers (EN): doc structure, which file, change impact, simplify. Coordinated by: project-coordinator.

Launch a live sprint status dashboard from BMAD sprint-status.yaml. Creates a Python web server with WebSocket updates, dark mode UI, auto-shutdown when no clients connected. Use when user wants to view sprint progress, monitor story status, or needs a visual dashboard for BMAD projects.

Analyzes Figma designs via MCP tools to produce structured design specifications for pixel-perfect implementation. Extracts layout, spacing, typography, colors, and component hierarchy. Use when given a Figma URL, asked to implement a Figma design, or when design-to-code accuracy is critical.

Scrapes Xiaohongshu (Little Red Book) posts to extract content, author info, and engagement metrics (likes, comments, shares, favorites). Use when user wants to scrape Xiaohongshu posts, extract post data, or analyze Xiaohongshu content.

Scrapes TikTok videos to extract content, author info, and engagement metrics (likes, comments, shares, favorites). Use when user wants to scrape TikTok videos, extract video data, or analyze TikTok content.

Use this skill when analyzing Claude Code's local data storage in `~/.claude/`.

Context-aware daily check-ins for morning planning, midday adjustments, and evening reviews. Use when the user wants to plan their day, check in on progress, or review their evening. Auto-triggers on phrases like "plan my day", "morning planning", "let's check in", "how's my day going", "evening review".

Quick, structured task capture with automatic processing. Use when user wants to capture a task, add a todo, or remember something. Auto-triggers on phrases like "I need to...", "remind me to...", "add task", "new todo", "capture this", "jag måste...", "lägg till uppgift", "fånga detta".

Interactive profile setup and management. Use when user wants to view, update, or set up their profile. Auto-triggers on phrases like "min profil", "uppdatera profil", "ändra profil", "profile setup", "inställningar", "preferences".

Convert technical text into **diagram-first, minimal-text** Slidev presentations.

工作流暂停逻辑设计方案

French university department dashboard development with FastAPI backend, React frontend, CAS authentication, and department-scoped permissions. Use when working on features for data aggregation (ScoDoc, Parcoursup, Excel), budget tracking, recruitment analytics, scolarité indicators, or EDT management. Also use for authentication, permission systems, database migrations, adapter patterns, or adding new data sources.

Solve captchas using 2captcha service

Run TestDriver tests with Vitest test runner

영상 스트리밍 전문가. "CCTV", "HLS", "WHEP", "스트리밍", "영상" 관련 질문 시 사용.

Turborepo 빌드 에러 해결. "빌드 에러", "build 실패", "turbo 에러" 요청 시 사용.

CesiumJS 3D 지도 전문가. "지도", "Cesium", "3D 맵", "GIS" 관련 질문 시 사용.

Structural code search and rewriting using AST patterns. Use when user mentions "ast-grep", "sg", or needs to search codebases using Abstract Syntax Tree patterns, find specific code structures, perform complex queries beyond text search, or rewrite code at scale. Triggers on requests for pattern matching, code analysis, linting rules, or automated refactoring.

This skill should be used when working with GitHub CLI (gh) for repository management, pull requests, issues, API access, GitHub Actions, or automation workflows. Provides comprehensive guidance on gh command patterns, security considerations, and best practices.

Analyze and pick the next task to work on. Shows scored recommendations from MASTER_PLAN.md with interactive selection. Use when starting a session or deciding what to tackle.

Comprehensive stress testing skill for FlowState. Runs reliability, backup, container, security, and performance tests. Use before releases, after major refactoring, or when reliability is questioned.

Debug Tauri 2.x desktop app issues including dialogs, CSP, plugins, and Vite integration. Triggers on Tauri dialog not opening, file save dialog doesn't work, CSP errors, virtual:pwa-register errors, click handlers not working in Tauri, XDG Portal issues on Linux.

Enhance JSDoc annotations for TypeScript code to optimize AI comprehension. Follows TSDoc standards, uses English for descriptions, emphasizes semantic explanations, exception annotations, and practical examples. Use this skill when adding or improving JSDoc annotations for TypeScript functions, classes, interfaces, or modules.

Semantic code analysis via LSP. Navigate code (definitions, references, implementations), search symbols, preview refactorings, and get file outlines. Use for exploring unfamiliar codebases or performing safe refactoring.

Generate visual diagrams of neural network architectures using Graphviz, including full parameter counts and hierarchical structure visualization for transformer models.

Log a workout or fitness entry. Use when the user wants to record exercise, add a workout, or log fitness activities.

This skill should be used when the user asks to "generate code template", "create CRUD", "generate scaffold", "code generator", "generate controller", "generate service", "generate entity", "use template to generate code", or needs code template retrieval and generation. Provides code template search and content retrieval via jar-based CLI.

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

Generate images using Google Gemini NanoBanana via browser automation. Use this skill for general-purpose AI image generation from text prompts. Includes persistent authentication and automatic environment setup.

Convert books, guides, or documentation into Claude skills using progressive disclosure patterns. Use when the user wants to encode a book's knowledge into skills.

Create Claude skills following official best practices. Covers structure, naming, descriptions, progressive disclosure, and testing. Use when authoring new skills or improving existing ones.

Create animations with Motion for vanilla JavaScript. Use for animating HTML/SVG elements, scroll-linked animations, spring physics, staggered effects, gestures (hover, press, inView), and easing functions without React or Vue.

| Error | Wrong Code | Correct Code | |-------|------------|--------------| | `ModuleNotFoundError: chatkit.stores` | `from chatkit.stores import Store` | `from chatkit.store import Store` | | `ModuleNotFoundError: chatkit.models` | `from chatkit.models import ...` | `from chatkit.types import ...` | | `ImportError: Event` | `from chatkit.server import Event` | Remove - doesn't exist | | `ImportError: ClientToolCallOutputItem` | `from chatkit.types import ClientToolCallOutputItem` | Use `Any`...

Spawn background subagents for parallel or long-running tasks. Use when you need research threads, context isolation, or detached execution.

Converts MCP servers to Claude Skills to save tokens. Runs the introspection tool to generate skill wrappers.

Create, validate, and convert skills for the agent ecosystem. Enforces standardized structure for consistency. Enables self-evolution by creating new skills on demand, converting MCP servers and codebases to skills.

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

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas