learn-eval

/learn-eval - Extract, Evaluate, then Save

Extends /learn with a quality gate, save-location decision, and knowledge-placement awareness before writing any skill file.

What to Extract

Look for:

1. Error Resolution Patterns — root cause + fix + reusability
2. Debugging Techniques — non-obvious steps, tool combinations
3. Workarounds — library quirks, API limitations, version-specific fixes
4. Project-Specific Patterns — conventions, architecture decisions, integration patterns

Process

1. Review the session for extractable patterns

2. Identify the most valuable/reusable insight

3. Determine save location:

   • Ask: "Would this pattern be useful in a different project?"
   • Global (~/.codex/skills/learned/): Generic patterns usable across 2+ projects (bash compatibility, LLM API behavior, debugging techniques, etc.)
   • Project (.codex/skills/learned/ in current project): Project-specific knowledge (quirks of a particular config file, project-specific architecture decisions, etc.)
   • When in doubt, choose Global (moving Global → Project is easier than the reverse)

4. Draft the skill file using this format:

---
name: pattern-name
description: "Under 130 characters"
user-invocable: false
origin: auto-extracted
---

# [Descriptive Pattern Name]

**Extracted:** [Date]
**Context:** [Brief description of when this applies]

## Problem
[What problem this solves - be specific]

## Solution
[The pattern/technique/workaround - with code examples]

## When to Use
[Trigger conditions]

1. Quality gate — Checklist + Holistic verdict

   5a. Required checklist (verify by actually reading files)

   Execute all of the following before evaluating the draft:

   • Grep ~/.codex/skills/ and relevant project .codex/skills/ files by keyword to check for content overlap
   • Check MEMORY.md (both project and global) for overlap
   • Consider whether appending to an existing skill would suffice
   • Confirm this is a reusable pattern, not a one-off fix