| name | context-engineering |
| description | Context engineering knowledge base for designing context stacks, memory, retrieval, orchestration, and AI system reliability in a Codex-compatible way. |
| user-invocable | false |
Context Engineering
Use this skill when designing or reviewing how context is assembled for AI systems.
Use Cases
- Context stack design
- Retrieval and RAG planning
- Memory design
- Multi-step orchestration
- AI system reliability reviews
Core Principle
Deliver the smallest high-signal context that makes the task solvable and safe.
Layers
Think in layers:
- System policy
- Developer instructions
- Tool contracts
- Runtime state
- Retrieved knowledge
- Memory
- Examples
- Output contract
Repository Mapping
- Root and scoped
AGENTS.md -> developer instructions and runtime context
.agents/skills/* -> reusable task workflows and knowledge
- Project files and retrieved docs -> knowledge context
- Structured outputs or explicit response formats -> output contract
Companion Resources
context-stack-model.md
memory-engineering.md
agent-harness-patterns.md
rag-engineering.md
multi-agent-patterns.md
production-checklists.md
reference-templates.md
privacy-compliance-ai.md