AI Skills Hub - Browse 180,000+ Agent Skills

Generate lifecycle hooks (before-prompt, after-file-edit, after-build) with tsx runtime and <100ms performance. Use when creating hooks, implementing context injection, or setting up auto-activation. Provides hook-template.ts with graceful failure patterns and stdin/stdout handling.

Load and merge context from three-layer system (User > Team > Project). This skill should be used for personalized code generation, respecting user preferences, applying team conventions, or understanding project-specific patterns.

This skill should be used when implementing, debugging, or discussing WebSocket connections for Nostr relays. Provides comprehensive knowledge of RFC 6455 WebSocket protocol, production-ready implementation patterns in Go (khatru), C++ (strfry), and Rust (nostr-rs-relay), including connection lifecycle, message framing, subscription management, and performance optimization techniques specific to Nostr relay operations.

Review code, PRs, diffs, and changes in the Pebble codebase for correctness issues including resource leaks, concurrency bugs, iterator misuse, and lint violations. Use when asked to review code, a pull request, diff, or changes.

Systematically debug failed Omnistrate instance deployments using a progressive workflow that identifies root causes efficiently while avoiding token limits. Applies to deployment failures, probe issues, and helm-based resources.

当用户需要搜索npm包、下载npm包文档或精确修改文件时触发。支持通过registry.npmmirror.com搜索包，通过unpkg.com获取包文档，并使用Node.js脚本精确替换指定行内容，解决Claude Code自带编辑工具不稳定的问题。

Comprehensive Ansible automation skill with Context7 integration for real-time best practices, playbook generation, role management, inventory configuration, deployment workflows, testing with Docker targets, community module integration, and validation features. Automatically leverages Context7 for current documentation, best practices, and community patterns when available. Use when creating Ansible playbooks, roles, collections, linting, debugging, check mode, or deployment automation. Supports planning mode with dry-run capabilities for safe preview of operations.

Plan and execute CivicTheme upgrades in Drupal projects. Use when working with Drupal sites using CivicTheme that need version upgrades (e.g., 1.10→1.11, 1.11→1.12). Handles SDC migration, Twig syntax updates, build tooling changes, and customisation preservation. Triggers include "upgrade civictheme", "civictheme migration", "update civictheme version", or any CivicTheme-related Drupal theme upgrade work.

Archive a completed change and apply spec updates to the main specifications.

Manage torrents with qBittorrent. Use when the user asks to "list torrents", "add torrent", "pause torrent", "resume torrent", "delete torrent", "check download status", "torrent speed", "qBittorrent stats", or mentions qBittorrent/qbit torrent management.

Use when validating an implementation plan created by writing-plans - coordinates parallel checks for hallucinations, TDD violations, missing references, and architectural issues before execution.

Without PTY mode, command output will not be visible even though commands execute successfully.

Shared team playbook for multi-agent deep research operations. Defines communication protocols, source quality tiers, parallel safety rules, output formatting standards, and error handling conventions used by all agents (orchestrator, ExaAI specialist, Firecrawl specialist, NotebookLM specialist) in the agentic research system.

Search indexers and manage Prowlarr. Use when the user asks to "search for a torrent", "search indexers", "find a release", "check indexer status", "list indexers", "prowlarr search", "sync indexers", or mentions Prowlarr/indexer management.

Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.

Manage Usenet downloads with SABnzbd. Use when the user asks to "check SABnzbd", "list NZB queue", "add NZB", "pause downloads", "resume downloads", "SABnzbd status", "Usenet queue", "NZB history", or mentions SABnzbd/sab download management.

Request movies and TV shows via Overseerr, monitor request status, and manage media requests. Use when the user asks to "request a movie", "request a TV show", "check request status", "pending requests", "Overseerr status", "media request", or mentions Overseerr/Seerr media requesting.

Without PTY mode, command output will not be visible even though commands execute successfully.

Luo ja paivita runbookit Next.js SWC/lockfile -virheiden selvitykseen. Kayta, kun pyynto koskee SWC-binaarivirheita, lockfile-mismatchia tai runbookin/CodeX-startupin paivitysta.

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

Manage Confluence documentation with downloads, uploads, conversions, and diagrams. Use when asked to "download Confluence pages", "upload to Confluence", "convert Wiki Markup", "sync markdown to Confluence", "create Confluence page", or "handle Confluence images".

Use when executing dbt commands via CLI - running models, tests, builds, compiles, or show queries. Use when unsure which dbt executable to use or how to format command parameters.

Accessibility guidelines and patterns for building WCAG 2.2 AA compliant HTML. Use when creating base page structures, building reusable UI components, or implementing forms. Provides guidance on semantic HTML, ARIA labels, alt text, keyboard navigation, and contrast ratios. Triggers on requests for accessible forms, page layouts, navigation, or any UI component that needs accessibility support.

Quick reference for Hoon syntax fundamentals including rune forms, data types, gates, and common idioms. Use when needing fast syntax lookups, verifying rune usage, or resolving common gotchas for developers with working Hoon knowledge.

Systematic debugging workflow for troubleshooting Nock formula execution from error analysis to resolution.

Comprehensive backup strategies and recovery procedures for Urbit ships including automated backups, 3-2-1 backup rule, safe pier backup procedures, recovery testing, and business continuity planning. Use when implementing backups, planning disaster recovery, recovering from failures, or ensuring data protection.

Urbit L2 roller API and Azimuth point lookups. Use when querying Azimuth PKI state, looking up spawned planets, converting point numbers to @p, or interacting with the L2 roller JSON-RPC endpoint.

Expert guidance for designing, implementing, migrating, and debugging SwiftData persistence in Swift and SwiftUI apps. Use when working with @Model schemas, @Relationship/@Attribute rules, Query or FetchDescriptor data access, ModelContainer/ModelContext configuration, CloudKit sync, SchemaMigrationPlan/history APIs, ModelActor concurrency isolation, or Core Data to SwiftData adoption/coexistence.

Write tests and verify the implementation works. Includes build and biome verification. Use after implementing, or when the founder says "test", "verify", "check", "does it work?".

Comprehensive MQL4/MQL5 development for MetaTrader 4 and MetaTrader 5 platforms. Use when writing, reviewing, debugging, or architecting: Expert Advisors (EAs), custom indicators, scripts, libraries (.mqh), graphical panels, or any MQL code. Also use for: order/position management, risk management, backtesting strategies, communication with external APIs (WebRequest, REST, JSON), inter-program communication, code protection/licensing, and MQL4-to-MQL5 migration. Covers the full MQL ecosystem including trading automation, technical analysis, UI panels, and server integration.

Synthetic graph data generator with configurable topology, density, and AI-powered property generation. Use when the user needs to generate test graph data, create synthetic social networks, benchmark graph databases, produce realistic knowledge graphs, or generate graph datasets for ML training.

MCP server exposing 87+ neural trading tools for AI agent integration. Use when connecting trading capabilities to Claude or other AI agents via MCP, exposing market data and strategy tools through Model Context Protocol, or building agent-driven trading automation.

WASM graph database with Neo4j-inspired Cypher API for browser and edge runtimes. Use when the user needs a graph database in the browser, client-side Cypher queries, WASM-based graph traversals, edge-deployed knowledge graphs, or offline graph operations without server infrastructure.

Distributed compute network with WASM cryptographic security for edge AI coordination. Use when the user needs to build distributed peer-to-peer compute networks, coordinate edge AI nodes, implement secure mesh networking, or distribute workloads across browser and edge nodes.

RuVector-powered graph database CLI with Cypher queries, hyperedges, ACID persistence, and 150x faster vector search. Use when managing graph data stores, running Cypher queries, performing vector similarity search, managing database schemas, or building knowledge graphs for AI agents.

Data replication with vector clocks, conflict resolution, and multi-node synchronization. Use when the user needs multi-node data replication, eventual consistency, vector clock conflict resolution, CRDTs, or distributed data synchronization across RuVector instances.

Semantic router with HNSW SIMD-accelerated intent matching for AI agent task routing. Use when the user needs semantic intent routing, vector-based route matching, AI agent task dispatch, utterance classification, or building intent-based APIs with sub-millisecond routing decisions.

Raft consensus for distributed coordination with leader election, log replication, and fault tolerance. Use when the user needs distributed consensus, leader election, replicated state machines, fault-tolerant coordination, or building distributed systems that require strong consistency guarantees.

HTTP/gRPC server for RuVector with REST API, streaming, and authentication. Use when the user needs to deploy a vector database server, expose vector search over HTTP or gRPC, configure server authentication, manage collections via REST endpoints, or set up a production vector search service.

Native Node.js graph database bindings with hypergraph support, Cypher queries, and persistence. Use when the user needs a graph database in Node.js, Cypher query execution, vertex/edge CRUD operations, graph traversals, shortest path algorithms, or hypergraph data modeling.

Rust vector database with native NAPI bindings for Node.js, SIMD-accelerated HNSW search, and zero-copy operations. Use when the user needs maximum vector search performance in Node.js, SIMD-optimized distance calculations, native Rust bindings, or low-latency similarity search in server-side applications.

Fast DAG library with Rust/WASM for topological sort, critical path, task scheduling, and dependency resolution. Use when the user needs directed acyclic graph operations, topological sorting, critical path analysis, dependency resolution, task scheduling, or workflow DAG management.

High-performance vector database for Node.js with native Rust NAPI and automatic WASM fallback. Use when the user needs to run vector similarity search, manage HNSW indexes, insert embeddings, or use the ruvector CLI for database operations, benchmarking, or ecosystem package management.

RuVector CLI with self-learning hooks, HNSW vector search, and agent routing. Use when the user needs to manage vector databases from the command line, configure self-learning hooks, route tasks to agents, run benchmarks, or orchestrate RuVector operations via terminal commands.

Standalone vector database with SQL, SPARQL, and Cypher query support powered by RuVector WASM. Use when the user needs a lightweight embedded vector database, multi-language query support (SQL/SPARQL/Cypher), standalone vector search without external dependencies, or a portable vector store for applications.

High-performance HNSW vector database core built in Rust with N-API bindings - 50k+ inserts/sec, sub-ms search. Use when building vector search applications, adding nearest-neighbor indexing to Node.js projects, or needing a fast embedded vector store with metadata filtering.

WebAssembly vector database bindings for browser and edge runtimes with HNSW search. Use when the user needs client-side vector search in the browser, edge-deployed similarity search, WASM-based embeddings, or portable vector operations without a server.

Add or create a UI component following project conventions (shadcn/ui v4, Base UI primitives, no asChild)

CLI reference and workflows for memories.sh — the persistent memory layer for AI agents. Use when: (1) Running memories CLI commands to add, search, edit, or manage memories, (2) Setting up memories.sh in a new project (memories init), (3) Generating AI tool config files (CLAUDE.md, .cursor/rules, etc.), (4) Importing existing rules from AI tools (memories ingest), (5) Managing cloud sync, embeddings, or git hooks, (6) Troubleshooting with memories doctor, (7) Working with memory templates, links, history, or tags.

MCP server integration for memories.sh — the persistent memory layer for AI agents. Use when: (1) Configuring the memories.sh MCP server for any client (Claude Code, Cursor, Windsurf, VS Code, v0, Claude Desktop, OpenCode, Factory), (2) Using MCP tools to store, search, or retrieve memories programmatically, (3) Understanding get_context vs search_memories vs list_memories, (4) Working with streaming memory tools for SSE content, (5) Troubleshooting MCP connection issues, (6) Choosing between cloud MCP (HTTP) and local MCP (stdio) transports.

Developer guide for contributing to and extending the memories.sh codebase. Use when: (1) Understanding the memories.sh architecture and how packages connect, (2) Adding new CLI commands or MCP tools, (3) Modifying the memory storage layer (SQLite/libSQL), (4) Working on the web dashboard (Next.js/Supabase), (5) Adding new generation targets for AI tools, (6) Extending cloud sync or embeddings functionality, (7) Debugging build, test, or deployment issues in the monorepo.

Designs and implements pytest test suites for Python libraries with fixtures, parametrization, mocking, Hypothesis property-based testing, and CI configuration. Use when creating tests, improving coverage, setting up testing infrastructure, or implementing property-based testing.

Guide for installing and setting up the cursor_workflow system in a Cursor project. Use when the user wants to install cursor_workflow, set up MCP tools, add workflow modules, or when they ask about installing the cursor workflow system.

Debug runtime bugs using HTTP logpoints that capture variable state without breakpoints. Use when the user describes a bug involving wrong values, race conditions, unexpected state, timing issues, or says "debug this", "why is this value wrong", "trace this", or "instrument this code". Works with JavaScript, TypeScript, Python, Go, Ruby, Shell, Java, C#, PHP, Rust, and Kotlin.

Spawn cloud code agents with specialized skills and execute tasks remotely. Use when: - User needs to list available skills from a skill store - User wants to spawn a cloud agent with specific skills installed - User needs to run tasks on a deployed cloud agent - User wants to manage cloud agent lifecycle (list, info, terminate) - User needs to track task status with polling Requires an API key from the skill service provider.

Integrate MercadoPago Checkout Pro (redirect-based) into Next.js applications with any PostgreSQL database (Supabase, AWS RDS, Neon, PlanetScale, self-hosted, Prisma, Drizzle, or raw pg). Use when the user needs to: (1) Add MercadoPago payment processing to a Next.js app, (2) Create a checkout flow with MercadoPago, (3) Set up payment webhooks for MercadoPago, (4) Build payment success/failure pages, (5) Create a shopping cart with payment integration, (6) Troubleshoot MercadoPago integration issues (auto_return errors, webhook failures, hydration mismatches, double submissions). Triggers on requests mentioning MercadoPago, Mercado Pago, payment integration with MP, Argentine/Latin American payment processing, or checkout with MercadoPago. Supports all MercadoPago countries: Argentina (ARS), Brazil (BRL), Mexico (MXN), Colombia (COP), Chile (CLP), Peru (PEN), Uruguay (UYU).

Processes cold email copy with spintax, checks for spam triggers and grammar issues. Use when creating email variants, applying spintax, validating copy for deliverability, checking spam scores, or verifying grammar. REQUIRES control message anchoring - spintax must be variations OF the control, not rewrites.

Planejar e implementar mudanças no indexador Python (chunking, embeddings, indexação full/incremental, IDs de chunk e payload rico); usar quando o pedido tocar `apps/indexer` ou pipeline RAG de ingestão e não usar para handlers MCP, schema Qdrant, infra ou documentação.

Planejar e implementar mudanças na camada vetorial Qdrant (collections, distance metric, vector size, payload filters, upsert/delete e migração de schema); usar quando o pedido tocar modelagem ou operação de vetor e não usar para lógica do indexador, handlers MCP, infra geral ou documentação.

Planejar e implementar mudanças de infraestrutura local e operacional (docker-compose, env vars, make targets, bootstrap, logs e métricas) para o Code Compass; usar quando o pedido tocar execução/observabilidade e não usar para lógica de MCP, indexação, modelagem vetorial ou documentação editorial.

Governar qualidade técnica transversal do Code Compass (gates de entrega, política de testes/contratos, lint, typecheck, cobertura e estabilidade de CI) quando o objetivo principal for elevar confiabilidade sistêmica entre módulos; não usar para bugfix com repro antes/depois, regressão localizada de mudança pontual ou smoke e2e de alteração específica (usar `developer-tester`) nem para implementação de feature de domínio.

Planejar e implementar mudanças no servidor MCP em Node/NestJS (tools, handlers, validação, allowlist, contratos de retorno com evidência e performance P95); usar quando o pedido tocar `apps/mcp-server` ou integração MCP e não usar para indexação Python, schema Qdrant, infra ou documentação.

自动化将本地内容发布为微信公众号图文。用于将 Markdown/HTML 转草稿并提交发布（draft+freepublish），当你需要把文章自动发布到公众号时触发。

Retrieve current weather conditions for a specific city. Use when the user asks for weather updates, temperature, or current conditions.

Professional instruction-set manual drafting and maintenance for the Linx ISA. Use when creating or editing ISA spec content (instruction entries, encoding diagrams/tables, precise pseudocode semantics, exceptions/interrupts, CSRs/privileged behavior, memory model), or when linting/reviewing the spec for ambiguity and internal consistency.

pyCircuit + MLIR development for Linx CPU bring-up. Use when modifying the PYC MLIR dialect, passes, or tools (pyc-opt/pyc-compile), adding ops/types/lowerings, or regenerating golden outputs and regressions for the Linx CPU examples in pyCircuit.

LLVM backend bring-up and maintenance for the Linx ISA. Use when implementing or changing Linx codegen/MC support (TableGen, registers, instruction selection, asm/disasm, object emission, ABI/calling convention), debugging miscompiles, or adding LLVM lit/FileCheck tests for Linx.

Analyze pi session transcripts to discover patterns that could become AGENTS.md rules, skills, or prompt templates. Mines your usage history for automation opportunities.

Build PR-focused context packs (PR description + git diff + full changed files + related files via Scribe), then token-check with o200k-base against a budget.

Compress videos to a target file size using ffmpeg two-pass encoding. Useful for Discord/Slack upload limits.

Compress images to a target file size using macOS sips. No dependencies required.

Use after a Concept Brief (S1) is approved and before requirements gathering (S3). Use when an initiative needs a go/no-go investment decision, feasibility evaluation, change impact analysis, or ROM estimate. Triggers include steering committee preparation, investment board submissions, or when someone asks 'is this feasible?' or 'how big is this?'.

Use when starting a new initiative, project, or feature concept — the entry point to the SDLC skill chain. Use before feasibility assessment, requirements gathering, or solution architecture. Triggers include new project ideas, strategic mandates, incident-driven initiatives, or when someone says 'I want to build...' or 'we need to...'.

Comprehensive Google Ads account health analysis detecting wasted spend, search term leaks, negative keyword gaps, bid strategy issues, and Quality Score problems. Use when analyzing campaign data, pasting Google Ads exports, reviewing account performance, or requesting a full diagnostic of advertising spend efficiency.

Statistical significance calculator for A/B test results with sample size requirements, segment breakdowns, and hypothesis generation. Use when feeding test results, checking statistical significance, calculating sample sizes, analyzing experiment outcomes, or generating next test ideas based on results.

自動辨識定檢資訊並回填至不同廠商格式的表單文件

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

Config-driven PyTorch Lightning wrapper with type-safe configs and registries. Use when building training pipelines with nshtrainer, configuring TrainerConfig or callbacks, creating LightningModuleBase subclasses, or setting up optimizers/schedulers/loggers via registry configs.

Initialize a Claude Code skill for a Python package using nshskill. Use when setting up a new skill for a library, creating SKILL.md for a package, wiring CLI install/uninstall commands, or adding nshskill integration to a Python project.

Local-first RAG cache: distill docs into structured Markdown, then index/query with Chroma (vector) + ripgrep (keyword).

Kotlin Coroutines review and remediation for Android. Use when asked to review concurrency usage, fix coroutine-related bugs, improve thread safety, or resolve lifecycle issues in Kotlin/Android code.

Authoritative rules and patterns for production-quality Kotlin Coroutines onto Android. Covers structured concurrency, lifecycle integration, and reactive streams.

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

.claude.env 파일에서 Git 설정을 읽어 git config를 자동 설정하는 스킬

작업 완료 후 결과 보고서를 생성하고, history.md를 갱신하고 CLAUDE.md를 필요시 갱신하며, 완료 알림을 전송하는 스킬. 사용 시점: (1) /report 명령어로 명시적 호출, (2) 작업 완료 후 결과 정리 요청 시, (3) 보고서, 리포트, report 키워드 포함 요청 시. 마크다운(.md), CSV, 엑셀(.xlsx) 등 다양한 형식으로 출력하며, 다이어그램 스킬과 연동하여 시각화 가능.

TDD(Test-Driven Development) 원칙 위반을 PreToolUse 훅으로 모니터링하고, 테스트 없이 소스 파일을 수정하려는 시도를 경고하는 가드

Use this agent to configure the user's Claude Code status line setting. Triggers - "statusline 설정", "상태줄 설정", "statusline 수정", "status line 변경", "init:statusLine".

rm -rf, git reset --hard, git push --force 등 위험한 명령어를 PreToolUse 훅으로 차단하는 안전 가드

Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage.

Build, test, and deploy n8n workflows via REST API with incremental testing. Expert automation for n8n. USE THIS SKILL WHEN: - User says "create workflow", "build automation", "deploy to n8n", "activate workflow" - User needs to list, update, delete, or test workflows - User mentions webhook execution, checking executions, debugging workflow runs - User asks about n8n nodes, expressions, credentials, or Code nodes - User needs JavaScript or Python code for n8n Code nodes - User mentions {{ }} expressions, $json, $input, or $node references - User asks about AI Agent, OpenAI, Anthropic, Google Sheets, Airtable, Slack, or other n8n nodes

This skill should be used when the user asks to "deploy to Coolify", "manage Coolify applications", "check Coolify status", "create database on Coolify", "manage Coolify servers", "diagnose Coolify issues", "update environment variables on Coolify", or mentions Coolify deployment, infrastructure management, or self-hosted PaaS operations.

Guide for fetching cryptocurrency market data from CoinGecko API using curl. Use this when asked to retrieve live crypto prices or market data.

Guide for creating data visualizations with Python Matplotlib. Use this when asked to generate charts, graphs, or visual reports from crypto data.

DART CI/CD troubleshooting - GitHub Actions, cache debugging, platform-specific failures

Help users improve their English vocabulary through clear explanations, practical examples, and effective memory techniques.

Convert online documentation into Claude Code skills with working scripts. Crawls docs, analyzes patterns, generates SKILL.md, reference files, and executable code examples.

Use this skill when the user wants to compare two data files, find differences between datasets, validate data consistency, check if files have matching records, or reconcile data between sources. Triggers include "compare these files", "diff the datasets", "are these the same", "find differences", "validate data matches", "reconcile", "data comparison", or when doing data quality validation between two files.

This skill should be used when the user asks to "create CARLA scenario in Python", "write Python CARLA script", "implement scenario with Python API", "use CARLA Python API", or mentions "carla python", "pythonでシナリオ", "python実装". Supports CARLA Python API scenario development with reference to official documentation.

This skill should be used when the user asks to "register to FiftyOne", "create FiftyOne dataset", "compute video embeddings", "add to FiftyOne", "FiftyOneに登録", "embedding計算". Automates FiftyOne dataset registration and video embedding computation for CARLA scenarios.