mcpField
A
ai-llm-skills-guide

ai-llm-skills-guide

github.com/gmh5225Agent workflows9744 installsUpdated 5d ago
Repository

About ai-llm-skills-guide

ai-llm-skills-guide is a reference skill for organizing and exploring AI and LLM development topics. It outlines agent frameworks, RAG, observability, memory, context engineering, and multi-agent patterns.

Key features

  1. 01Survey agent framework categories
  2. 02Outline RAG components and techniques
  3. 03Catalog observability and tracing tools
  4. 04Describe memory system types
  5. 05Summarize context engineering and agent patterns

Use cases

  1. 01Find a skill category for an AI project
  2. 02Organize AI skills in a README
  3. 03Review common multi-agent architectures

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/gmh5225/awesome-skills --skill ai-llm-skills-guide

After installing, type/ai-llm-skills-guidein Claude Code to confirm it loaded.

Details

From the project README

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
FrameworkDescription
LangGraphStateful, multi-actor AI applications
CrewAIRole-based multi-agent orchestration
AutoGenMicrosoft's multi-agent framework
RAG (Retrieval-Augmented Generation)
ComponentSkills
EmbeddingsText embedding models, chunking strategies
Vector DBsPinecone, Weaviate, Chroma, Qdrant
RetrievalHybrid search, reranking, context optimization
Observability & Tracing
ToolPurpose
LangfuseOpen-source LLM observability
LangSmithLangChain tracing and debugging
Weights & BiasesML experiment tracking
Memory Systems
TypeDescription
Short-termConversation buffer, sliding window
Long-termVector store persistence, entity memory
EpisodicExperience-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 Development or Data & Analysis
  • Observability: AI Agents & LLM Development
  • Context engineering: Context Engineering

Key Repositories

sickn33/antigravity-awesome-skills/skills/
├── langgraph/
├── crewai/
├── langfuse/
├── rag-engineer/
├── prompt-engineer/
├── voice-agents/
├── agent-memory-systems/
└── autonomous-agents/

muratcankoylan/Agent-Skills-for-Context-Engineering/skills/
├── context-fundamentals/
├── context-degradation/
├── context-compression/
├── multi-agent-patterns/
└── memory-systems/

Best Practices

  1. Modular design: Separate retrieval, generation, and orchestration
  2. Evaluation: Include benchmarks and test cases
  3. Cost awareness: Document token usage and API costs
  4. Fallback strategies: Handle API failures gracefully
  5. 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.

Comments

Markdown supported