BigHugger

Agent skills that run typescript, in claude-code format

A skill is a Markdown file that tells a coding agent how to do one job. We parse every one we can find — the frontmatter, the outline, the languages in its code blocks — so you can look for the one that fits instead of reading through a repository to find out.

69,865 skills from 9,574 repositories, last read 11 September 2026.

Skills declare what they need inconsistently: 58.8% name the languages they run, 11.2% list the tools they ask for, and 4.6% give themselves a category. Filtering narrows to the ones that said so, never to the ones that are.

  1. AgentDB Vector Searchruvnet/ruflo

    Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search en

    claude-codebashtypescript
  2. V3 Deep Integrationruvnet/ruflo

    Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.

    claude-codebashtypescript
  3. ReasoningBank Intelligenceruvnet/ruflo

    Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workfl

    claude-codetypescript
  4. AgentDB Learning Pluginsruvnet/ruflo

    Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building

    claude-codebashjsontypescript
  5. V3 Core Implementationruvnet/ruflo

    Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing

    claude-codebashjsontypescript
  6. V3 Memory Unificationruvnet/ruflo

    Unify 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).

    claude-codebashtypescript
  7. worker-integrationruvnet/ruflo

    Worker-Agent integration for intelligent task dispatch and performance tracking

    claude-codebashjsontypescript
  8. V3 CLI Modernizationruvnet/ruflo

    CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow autom

    claude-codebashtypescript
  9. worker-benchmarksruvnet/ruflo

    Run comprehensive worker system benchmarks and performance analysis

    claude-codebashjsontypescript
  10. V3 Swarm Coordinationruvnet/ruflo

    15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timelin

    claude-codebashtypescript
  11. Swarm Orchestrationruvnet/ruflo

    Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing co

    claude-codebashtypescript
  12. V3 MCP Optimizationruvnet/ruflo

    MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring fo

    claude-codebashtypescript
  13. V3 Security Overhaulruvnet/ruflo

    Complete security architecture overhaul for claude-flow v3. Addresses critical CVEs (CVE-1, CVE-2, CVE-3) and implements secure-by-default patterns. Use for security-first v3 imple

    claude-codebashtypescript
  14. ReasoningBank with AgentDBruvnet/ruflo

    Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition.

    claude-codebashtypescript
  15. AgentDB Memory Patternsruvnet/ruflo

    Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful a

    claude-codebashtypescript
  16. AgentDB Performance Optimizationruvnet/ruflo

    Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improv

    claude-codebashtypescript
  17. V3 DDD Architectureruvnet/ruflo

    Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.

    claude-codebashtypescript
  18. AgentDB Advanced Featuresruvnet/ruflo

    Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when bu

    claude-codebashtypescript
  19. V3 Performance Optimizationruvnet/ruflo

    Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimizati

    claude-codebashtypescript
  20. fallowfallow-rs/fallow

    Codebase intelligence for TypeScript and JavaScript. Static analysis reports changed-code risk, cleanup opportunities, duplication, circular dependencies, complexity hotspots, arch

    claude-codebashjsontypescript+7 files
  21. hook-testchildrentime/reactuse

    Write and run jest tests for a hook in @reactuses/core, following the repo's conventions (co-located index.spec.ts, renderHook/act, fake timers, the .test/ helpers, and the SSR jes

    claude-codebashtypescript
  22. new-hookchildrentime/reactuse

    Scaffold a new React hook in @reactuses/core with the repo's real conventions (interface.ts + multilingual JSDoc, SSR-safe browser access, shared-util reuse, 3-part public export).

    claude-codetypescript+3 files
  23. add-mcp-toolsdecocms/studio

    Guide for adding new MCP tools with consistent patterns for schemas, tool definitions, registry updates, and Better Auth integration

    claude-codetypescript
  24. AgentDB Performance Optimizationruvnet/agentic-flow

    Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improv

    claude-codebashtypescript
  25. ReasoningBank Intelligenceruvnet/agentic-flow

    Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workfl

    claude-codetypescript
  26. V3 CLI Modernizationruvnet/agentic-flow

    CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow autom

    claude-codebashtypescript
  27. V3 Memory Unificationruvnet/agentic-flow

    Unify 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).

    claude-codebashtypescript
  28. AgentDB Vector Searchruvnet/agentic-flow

    Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search en

    claude-codebashtypescript
  29. V3 Swarm Coordinationruvnet/agentic-flow

    15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timelin

    claude-codebashtypescript
  30. ReasoningBank with AgentDBruvnet/agentic-flow

    Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition.

    claude-codebashtypescript
  31. Swarm Orchestrationruvnet/agentic-flow

    Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing co

    claude-codebashtypescript
  32. V3 Deep Integrationruvnet/agentic-flow

    Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.

    claude-codebashtypescript
  33. V3 Performance Optimizationruvnet/agentic-flow

    Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimizati

    claude-codebashtypescript
  34. AgentDB Memory Patternsruvnet/agentic-flow

    Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful a

    claude-codebashtypescript
  35. V3 Core Implementationruvnet/agentic-flow

    Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing

    claude-codebashjsontypescript
  36. AgentDB Advanced Featuresruvnet/agentic-flow

    Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when bu

    claude-codebashtypescript
  37. V3 MCP Optimizationruvnet/agentic-flow

    MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring fo

    claude-codebashtypescript
  38. V3 DDD Architectureruvnet/agentic-flow

    Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.

    claude-codebashtypescript
  39. V3 Security Overhaulruvnet/agentic-flow

    Complete security architecture overhaul for claude-flow v3. Addresses critical CVEs (CVE-1, CVE-2, CVE-3) and implements secure-by-default patterns. Use for security-first v3 imple

    claude-codebashtypescript
  40. AgentDB Learning Pluginsruvnet/agentic-flow

    Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building

    claude-codebashjsontypescript
  41. zcf-add-sponsorUfoMiao/zcf

    Quickly add a new corporate sponsor to ZCF — sponsor list by default, with optional API preset and documentation ad placements

    claude-codebashhtmltypescriptRead(**)Write(**)Edit(**)
  42. V3 Security Overhaulruvnet/ruv-FANN

    Complete security architecture overhaul for claude-flow v3. Addresses critical CVEs (CVE-1, CVE-2, CVE-3) and implements secure-by-default patterns. Use for security-first v3 imple

    claude-codebashtypescript
  43. AgentDB Memory Patternsruvnet/ruv-FANN

    Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful a

    claude-codebashtypescript
  44. V3 Swarm Coordinationruvnet/ruv-FANN

    15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timelin

    claude-codebashtypescript
  45. V3 MCP Optimizationruvnet/ruv-FANN

    MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring fo

    claude-codebashtypescript
  46. V3 Deep Integrationruvnet/ruv-FANN

    Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.

    claude-codebashtypescript
  47. ReasoningBank with AgentDBruvnet/ruv-FANN

    Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition.

    claude-codebashtypescript
  48. V3 Core Implementationruvnet/ruv-FANN

    Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing

    claude-codebashjsontypescript
  49. AgentDB Vector Searchruvnet/ruv-FANN

    Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search en

    claude-codebashtypescript
  50. ReasoningBank Intelligenceruvnet/ruv-FANN

    Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workfl

    claude-codetypescript
  51. AgentDB Learning Pluginsruvnet/ruv-FANN

    Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building

    claude-codebashjsontypescript
  52. V3 DDD Architectureruvnet/ruv-FANN

    Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.

    claude-codebashtypescript
  53. V3 CLI Modernizationruvnet/ruv-FANN

    CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow autom

    claude-codebashtypescript
  54. AgentDB Performance Optimizationruvnet/ruv-FANN

    Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improv

    claude-codebashtypescript
  55. V3 Memory Unificationruvnet/ruv-FANN

    Unify 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).

    claude-codebashtypescript
  56. AgentDB Advanced Featuresruvnet/ruv-FANN

    Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when bu

    claude-codebashtypescript
  57. Swarm Orchestrationruvnet/ruv-FANN

    Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing co

    claude-codebashtypescript
  58. V3 Performance Optimizationruvnet/ruv-FANN

    Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimizati

    claude-codebashtypescript
  59. architecturektnyt/cclsp

    Guides the design of safely disposable code through contracts (traits/interfaces) and dependency inversion. Use when designing new modules, refactoring existing code, or making arc

    claude-codegorusttypescript
  60. write-frontend-testsSignificant-Gravitas/AutoGPT

    Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write them. TRIGGER when user asks to write frontend tests, add test

    claude-codebashtypescript

Browse all 69,865 skills200 at a time, grouped by owner. The list above is the skills with the highest standing; this is every one of them.

The whole corpus is one call away through the search API, or ask a question of it on the index itself.