ai-llm-skills-guide
4
总安装量
4
周安装量
#52437
全站排名
安装命令
npx skills add https://github.com/gmh5225/awesome-skills --skill ai-llm-skills-guide
Agent 安装分布
opencode
4
gemini-cli
4
antigravity
4
junie
4
claude-code
4
github-copilot
4
Skill 文档
AI Agents & LLM Development Skills
Scope
Use this skill when:
- Finding or adding AI/LLM related skills
- Understanding agent architecture patterns
- Working with RAG, embeddings, or vector databases
- Implementing multi-agent systems
Key Skill Categories
Agent Frameworks
| Framework | Description |
|---|---|
| LangGraph | Stateful, multi-actor AI applications |
| CrewAI | Role-based multi-agent orchestration |
| AutoGen | Microsoft’s multi-agent framework |
RAG (Retrieval-Augmented Generation)
| Component | Skills |
|---|---|
| Embeddings | Text embedding models, chunking strategies |
| Vector DBs | Pinecone, Weaviate, Chroma, Qdrant |
| Retrieval | Hybrid search, reranking, context optimization |
Observability & Tracing
| Tool | Purpose |
|---|---|
| Langfuse | Open-source LLM observability |
| LangSmith | LangChain tracing and debugging |
| Weights & Biases | ML experiment tracking |
Memory Systems
| Type | Description |
|---|---|
| Short-term | Conversation buffer, sliding window |
| Long-term | Vector store persistence, entity memory |
| Episodic | Experience-based memory recall |
Context Engineering Skills
Core Concepts
- Context fundamentals: What context is and why it matters
- Context degradation: Lost-in-middle, poisoning, distraction patterns
- Context compression: Summarization, trimming strategies
- Context optimization: Caching, masking, compaction
Multi-Agent Patterns
- Orchestrator pattern
- Peer-to-peer collaboration
- Hierarchical delegation
- Tool-using agents
Where to Add in README
- Agent frameworks:
AI Agents & LLM Development - RAG tools:
AI Agents & LLM DevelopmentorData & Analysis - Observability:
AI Agents & LLM Development - Context engineering:
Context Engineering
Key Repositories
sickn33/antigravity-awesome-skills/skills/
âââ langgraph/
âââ crewai/
âââ langfuse/
âââ rag-engineer/
âââ prompt-engineer/
âââ voice-agents/
âââ agent-memory-systems/
âââ autonomous-agents/
muratcankoylan/Agent-Skills-for-Context-Engineering/skills/
âââ context-fundamentals/
âââ context-degradation/
âââ context-compression/
âââ multi-agent-patterns/
âââ memory-systems/
Best Practices
- Modular design: Separate retrieval, generation, and orchestration
- Evaluation: Include benchmarks and test cases
- Cost awareness: Document token usage and API costs
- Fallback strategies: Handle API failures gracefully
- Streaming: Support streaming responses where possible
Full Resource List
For more detailed skill resources, complete link lists, or the latest information, use WebFetch to retrieve the full README.md:
https://raw.githubusercontent.com/gmh5225/awesome-skills/refs/heads/main/README.md
The README.md contains the complete categorized resource list with all links.