ai-llm-skills-guide
Skill97 starsChanged 10 months agoMITView on GitHub
Guide for AI Agents and LLM development skills including RAG, multi-agent systems, prompt engineering, memory systems, and context engineering.
In this repository7 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this skill when:
- Distinctive: line 99
Cost awareness: Document token usage and API costs
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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/
├── 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
- 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.mdThe README.md contains the complete categorized resource list with all links.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

