GitHub
multi-agent-orchestration
Multi-agent coordination and synthesis patterns. Use when orchestrating multiple specialized agents, implementing fan-out/fan-in workflows, or synthesizing outputs from parallel agents.
☆ 61查看技能
tools llm ai AI 技能
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。
分类目录: tools llm ai
tools llm ai 清除筛选
全部技能
GitHub
defense-in-depth
Use when building secure AI pipelines or hardening LLM integrations. Defense-in-depth implements 8 validation layers from edge to storage with no single point of failure.
☆ 61查看技能
GitHub
langgraph-supervisor
LangGraph supervisor-worker pattern. Use when building central coordinator agents that route to specialized workers, implementing round-robin or priority-based agent dispatch.
☆ 61查看技能
GitHub
explore
Deep codebase exploration with parallel specialized agents. Use when exploring a repo, finding files, or discovering architecture with the explore agent.
☆ 61查看技能
GitHub
agent-loops
Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.
☆ 61查看技能
GitHub
langgraph-functional
LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution, persistence, and human-in-the-loop.
☆ 61查看技能
GitHub
mcp-server-building
Building MCP (Model Context Protocol) servers for Claude extensibility. Use when creating MCP servers, building custom Claude tools, extending Claude with external integrations, or developing tool packages for...
☆ 61查看技能
GitHub
prompt-caching
Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.
☆ 61查看技能
GitHub
embeddings
Text embeddings for semantic search and similarity. Use when converting text to vectors, choosing embedding models, implementing chunking strategies, or building document similarity features.
☆ 61查看技能
GitHub
advanced-guardrails
LLM guardrails with NeMo, Guardrails AI, and OpenAI. Input/output rails, hallucination prevention, fact-checking, toxicity detection, red-teaming patterns. Use when building LLM guardrails, safety checks, or re...
☆ 61查看技能
GitHub
load-context
Auto-load relevant memories at session start from both mem0 and graph. Use when you need session context restored or preloaded.
☆ 61查看技能
GitHub
langgraph-checkpoints
LangGraph checkpointing and persistence. Use when implementing fault-tolerant workflows, resuming interrupted executions, debugging with state history, or avoiding re-running expensive operations.
☆ 61查看技能
GitHub
contextual-retrieval
Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.
☆ 61查看技能
GitHub
reranking-patterns
Reranking patterns for improving search precision. Use when implementing cross-encoder reranking, LLM-based relevance scoring, or improving retrieval quality in RAG pipelines.
☆ 61查看技能
GitHub
ollama-local
Local LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction. Covers model selection, LangChain integration, and performance tuning.
☆ 61查看技能
GitHub
recall
Search and retrieve decisions and patterns from knowledge graph. Use when recalling patterns, retrieving memories, finding past decisions.
☆ 61查看技能
GitHub
context-compression
Use when conversation context is too long, hitting token limits, or responses are degrading. Compresses history while preserving critical information using anchored summarization and probe-based validation.
☆ 61查看技能
GitHub
design-brief-generator
Generate comprehensive design briefs for design projects. Use this skill when designers ask to "create a design brief", "structure a design project", "define design requirements", or need help planning design w...
☆ 61查看技能
GitHub
anthropic-architect
Determine the best Anthropic architecture for your project by analyzing requirements and recommending the optimal combination of Skills, Agents, Prompts, and SDK primitives.
☆ 61查看技能
GitHub
openai-prompt-engineer
Generate and improve prompts using best practices for OpenAI GPT-5 and other LLMs. Apply advanced techniques like chain-of-thought, few-shot prompting, and progressive disclosure.
☆ 61查看技能
GitHub
git-worktrees
Manage Git worktrees for parallel Claude Code development. Use this skill when engineers ask to "create a worktree", "run parallel Claude sessions", "work on multiple features simultaneously", or need help with...
☆ 61查看技能
GitHub
content-brief-generator
Generate comprehensive content briefs for writers, ensuring clarity, alignment, and strategic content creation across all formats.
☆ 61查看技能
GitHub
anthropic-prompt-engineer
Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices for Claude AI models.
☆ 61查看技能
GitHub
query-expert
Master SQL and database queries across multiple systems. Generate optimized queries, analyze performance, design indexes, and troubleshoot slow queries for PostgreSQL, MySQL, MongoDB, and more.
☆ 61查看技能
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。