delegate
Delegate tasks to specialized subagents. Analyzes requirements, selects appropriate agents, and launches them with proper context while enforcing the max-2-parallel rule.
发现 tools llm ai 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Delegate tasks to specialized subagents. Analyzes requirements, selects appropriate agents, and launches them with proper context while enforcing the max-2-parallel rule.
Backend Architect Agent. 시스템 설계, 아키텍처 결정, 기술 선택을 담당합니다. 설계, 아키텍처, 구조, 패턴, 기술 선택 관련 요청 시 사용됩니다.
Docs API Agent. OpenAPI 스펙, API 레퍼런스 문서 작성을 담당합니다.
Data Scientist Agent. ML 모델 개발, 실험, 분석을 담당합니다.
Backend Developer Agent. 코드 개발, 디버깅, 기능 구현을 담당합니다. 개발, 코딩, 디버그(debug), 버그 수정, 기능 구현 관련 요청 시 사용됩니다.
PM Manager Agent. 프로젝트 관리, 일정 조율, 리소스 관리를 담당합니다. 일정, 스케줄, 마일스톤, 프로젝트 관리 관련 요청 시 사용됩니다.
API Contract Agent. OpenAPI 스펙 정의, Mock Server 생성, Contract-First 개발을 담당합니다. Frontend/Backend 간 API 계약을 관리합니다.
Claude Code CLI and development environment. Use for Claude Code features, tools, workflows, MCP integration, configuration, and AI-assisted development.
Use when creating new Claude Code skills, setting up marketplace repositories, or packaging skills for distribution - complete workflow from skill creation to marketplace publication
Externalize detailed memory to Memory Bank before conversation summarization to prevent context loss. Triggers: CP, checkpoint, save, 存檔, 記一下, 保存, sync memory, dump, 先記著, 備份, backup, snapshot, 快照,...
Handle vision/image tasks (read, describe, analyze images) by calling Gemini CLI or Qwen Code CLI from the shell. Use for requests to interpret or describe images, extract visible text, or summarize visual cont...
Use when building Retrieval-Augmented Generation systems. Covers document chunking, embedding generation, vector indexing, semantic search, context building, and integration of retrieval with LLM completion for...
Use when integrating OpenAI GPT models for conversational AI. Covers chat completions, streaming responses, function calling, system prompts, token management, cost optimization, error handling, and building sp...
Use when working with Qdrant vector database for semantic search and RAG. Covers collection setup, embedding generation, vector upsert/search, HNSW indexing, filtering, and integration with OpenAI embeddings fo...
Expert CRO advisor that analyzes landing pages, product funnels, UI/UX friction, and provides data-driven A/B test ideas to maximize conversions, sign-ups, trials, and retention. Use when optimizing conversion...
Comprehensive UX research assistant that analyzes user feedback from surveys, reviews, and interviews to identify trends, cluster themes, surface friction points, and generate actionable product roadmaps. Use w...
Expert guidance for designing, integrating, and maintaining third-party APIs with best practices for authentication, error handling, rate limiting, security, and data transformation. Use when integrating extern...
Transform vague requests into production-ready, hallucination-free prompts optimized for Claude 4.x. Applies investigation-first protocols, anti-hallucination guards, extended thinking patterns, and multishot e...
Use when creating new Claude Code skills, setting up marketplace repositories, or packaging skills for distribution - complete workflow from skill creation to marketplace publication
Use when user explicitly requests Telegram bot development, Mini App integration, webhook/polling setup, or debugging Telegram-specific issues. Handles Telegraf-based bots, AI chatbot integration via Telegram,...
Self-improving metacognitive recipe tools that learn from execution feedback and extract patterns to provide recommendations
Use when [specific triggers, symptoms, error messages user will see] - [what this skill does and how it helps, in third person]
Expert guidance for Azure Functions (Node.js v4) in the 5BulletMethod app.
Access local/LAN URLs that cloud AI agents cannot reach. Fetch HTML content, take screenshots, interact with page elements, crawl sites, and list UI elements for private network addresses (192.168.x.x, localhos...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。