agentic-ai-engineering/skills/individual/feynman/SKILL.md

45 lines
1.2 KiB
Markdown

---
name: feynman
description: Feynman Technique for deep learning. Explain a concept simply, identify gaps, fill them, then refine. Compatible with neurofoo/agent-skills.
user-invocable: true
---
# Feynman Technique
Apply the full Feynman learning technique to deeply understand any agentic engineering concept.
## Steps
### Step 1: Explain It Simply
Explain as if teaching someone with no background in this field.
### Step 2: Identify Gaps
Where did the explanation get fuzzy or require jargon?
### Step 3: Fill the Gaps
Research or think through each gap.
### Step 4: Refined Explanation
Rewrite with gaps filled and simpler language.
## Course Concepts to Apply To
| Concept | Module | Invoke |
|---------|--------|--------|
| What is an agent? | M1 | `/feynman agent` |
| Security ladder | M3 | `/feynman security` |
| Verifier pattern | M3 | `/feynman verifier` |
| Orchestration | M4 | `/feynman orchestration` |
| Cascade routing | M6 | `/feynman cascade` |
| Autoresearch | M7 | `/feynman autoresearch` |
## Usage
```
/feynman What is an AI agent?
/feynman How does the verifier pattern work?
/feynman Explain cascade routing to a non-technical stakeholder
```
$ARGUMENTS