Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
21,660 skills from 798 repositories · updated 10 minutes ago
1,448 skills
- schema-optimization-orchestratorjeremylongshore/tons-of-skills-marketplaceMulti-phase schema optimization workflow orchestrator. Creates session directories, spawns phase agents sequentially, validates outputs, aggregates results. Trigger: "run schema optimization", "optimize schema workflow", "execute schema phases"ProductivityNo warnings★ 2.9K↓ —
- registry-default-mirrorcisco-ai-defense/skill-scannerPin the npm registry to the public default and fetch published release notesProductivityNo warnings★ 2.6K↓ —
- natural-japanesecoji/natural-japanese仕事の日本語文書を、自然で読みやすく、わかりやすい日本語で書く・直すためのスキル。議事録、調査レポート、顧客向けのレポート、社内ガイド、技術記事、PR の説明文、リサーチメモ、企画書、メール、スライド構成などの作成や推敲と、note やブログ、エッセイの執筆に使う。文字起こしから議事録を作るときにも使う。自然な日本語にしたい、読みやすくしたい、簡潔にしたい、結論から書きたいといった依頼のほか、読みづらい、わかりにくい、何を言っているかわからない、AI っぽい、AI 臭い、英語の直訳っぽい、日本語として不自然、違和感があるといった指摘にも使う。書き換えずに AI らしさを判定・採点してほしいという依頼や、自分の文体を学ばせたいという依頼にも対応する。ProductivityNo warnings★ 2K↓ —
- Linear Todo SyncMicrock/ordinary-claude-skillsThis skill fetches open tasks assigned to the user from the Linear API and generates a markdown todo list file in the project root. This skill should be used when the user asks about their work items, wants to see what they need to work on, or requests to load/sync their Linear tasks. Requires Python 3.7+, requests, mdutils, and python-dotenv packages. Requires LINEAR_API_KEY in .env file.ProductivityNo warnings★ 407↓ —
- Swarm Orchestrationspencermarx/open-code-reviewOrchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.ProductivityNo warnings★ 380↓ —
- V3 Memory Unificationspencermarx/open-code-reviewUnify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).ProductivityNo warnings★ 380↓ —
- AgentDB Memory Patternsspencermarx/open-code-reviewImplement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.ProductivityNo warnings★ 380↓ —
- V3 Performance Optimizationspencermarx/open-code-reviewAchieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.ProductivityNo warnings★ 380↓ —
- github-workflow-automationspencermarx/open-code-reviewAdvanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository managementProductivityNo warnings★ 380↓ —
- AgentDB Performance Optimizationspencermarx/open-code-reviewOptimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.ProductivityNo warnings★ 380↓ —
- memory-md-managementgiuseppe-trisciuoglio/developer-kitProvides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such as CLAUDE.md. Use when user asks to check, audit, update, improve, fix, maintain, or validate project memory files. Also triggers for "project memory optimization", "CLAUDE.md quality check", "documentation review", or when a project memory file needs to be created from scratch. This skill scans memory files, evaluates quality against standardized criteria, outputs detailed quality reports with scores and recommendations, then makes targeted updates with user approval.ProductivityNo warnings★ 360↓ —
- github-issue-workflowgiuseppe-trisciuoglio/developer-kitProvides a structured 8-phase workflow for resolving GitHub issues in Claude Code. Covers fetching issue details, analyzing requirements, implementing solutions, verifying correctness, performing code review, committing changes, and creating pull requests. Use when user asks to resolve, implement, work on, fix, or close a GitHub issue, or references an issue URL or number for implementation.ProductivityNo warnings★ 360↓ —
- spring-ai-mcp-server-patternsgiuseppe-trisciuoglio/developer-kitProvides Spring Boot MCP server patterns that create Model Context Protocol servers with Spring AI by defining tool handlers, exposing resources, configuring prompt templates, and setting up transports for AI function calling and tool calling. Use when building MCP servers to extend AI capabilities with Spring's official AI framework, implementing AI tools, custom function calling, or MCP client integration.ProductivityNo warnings★ 360↓ —
- langchain4j-mcp-server-patternsgiuseppe-trisciuoglio/developer-kitProvides LangChain4j patterns for implementing MCP (Model Context Protocol) servers, creating Java AI tools, exposing tool calling capabilities, and integrating MCP clients with AI services. Use when building a Java MCP server, implementing tool calling in Java, connecting LangChain4j to external MCP servers, or securing tool exposure for agent workflows.ProductivityNo warnings★ 360↓ —
- langchain4j-spring-boot-integrationgiuseppe-trisciuoglio/developer-kitProvides integration patterns for LangChain4j with Spring Boot. Configures AI model beans, sets up chat memory with Spring context, integrates RAG pipelines with Spring Data, and handles auto-configuration, dependency injection, and Spring ecosystem integration. Use when embedding LangChain4j into Spring Boot applications, building Java LLM applications with @Bean configuration, or setting up Spring AI patterns.ProductivityNo warnings★ 360↓ —
- summaryalaliqing/claude-paperUse this for a quick summary of a research paper's core ideas and key points. Use when you want to quickly understand a paper without deep study materials. Triggers on PDF paths, arXiv URLs, or paper URLs.ProductivityNo warnings★ 351↓ —
- metasploitEncod3d-Sec/TORCHDrive msfconsole across the workflow - DB-backed recon (db_nmap, auxiliary scanners), version->exploit search/check/run, multi/handler reverse shells (meterpreter-first, plain shell_reverse_tcp backup for Windows/EDR), sessions + local_exploit_suggester + post modules, and autoroute/portfwd/socks pivoting. Points to the metasploit cheatsheet for syntax. Use for "metasploit", "msfconsole", "msfvenom", "meterpreter", "multi/handler", or driving an exploit/reverse-shell through msf.ProductivityNo warnings★ 334↓ —
- hunt-bizlogicEncod3d-Sec/TORCHBusiness-logic flaw hunting - workflow/state bypass, price/quantity tampering, negative/overflow values, coupon/refund abuse, mass assignment, and logic races. The top-paying bug class with no scanner coverage. Wiki-first, FIND schema output.ProductivityNo warnings★ 334↓ —
- pt-workflowEncod3d-Sec/TORCHAutonomous pentest campaign driver. Runs a scoped engagement end to end with no operator approvals - the deterministic driver (scripts/campaign.py) owns pass state, generates the killchain board from recon, and prints the exact next action (Skill + tool) every turn. Use when starting or resuming a pentest, "run the pt workflow", "work this CIDR/domain", or when handed a client SoW/scope to reach a stated objective or domain admin. Single agent, refuter-verified, wiki-first, tool-first. Deliverable is a client report.ProductivityNo warnings★ 334↓ —
- bb-workflowEncod3d-Sec/TORCHAutonomous bug-bounty campaign driver. Runs a full programme end to end with no operator approvals - the deterministic driver (scripts/campaign.py) owns pass state, generates the killchain board from recon, and prints the exact next action (including which Skill and tool to run) every turn. Use when starting or resuming a bug-bounty engagement, "run the bb workflow", "hunt this program", "9-pass campaign", or when handed a *.scope wildcard to test for TIER1 findings. Single agent, refuter-verified, wiki-first, tool-first.ProductivityNo warnings★ 334↓ —
- ql-workflowNewmaxritter/qualitylayerPlan, build and review software with your coding agents. Work side by side in the App or browser, or use your favourite terminal or IDE.ProductivityNo warnings★ 2.1K↓ —
- ctf-workflowEncod3d-Sec/TORCHAutonomous CTF / boot-to-root campaign driver. Runs a box end to end with no operator approvals - the deterministic driver (scripts/campaign.py) owns pass state, generates the killchain board from recon, and prints the exact next action (Skill + tool) every turn. Use when handed a box/IP to own end to end, "run the ctf workflow", "root this box", "foothold to root". Single agent, wiki-first, tool-first. OSINT is OFF unless you invoke with an osint argument. Delegates box recipes to ctf-box.ProductivityNo warnings★ 334↓ —
- memoryrshankras/claude-code-apple-skillsSwift 6.2 InlineArray and Span types for zero-overhead memory access, fixed-size collections, and safe pointer alternatives. Use when optimizing performance-critical code paths.ProductivityNo warnings★ 823↓ —
- agentic-workflowparcadei/Continuous-Claude-v3Agentic Workflow PatternProductivityNo warnings★ 3.9K↓ —Also in 1 other repo