retro-learn

Retro Learn Skill

[!IMPORTANT] Convert delivery findings into skill, eval, workflow, and documentation improvements.

Instructions

When the user asks to perform this workflow, execute the following steps:

Retro Learn Workflow

Goal: Turn defects, missed expectations, and delivery friction into durable standards improvements.

Steps

1. Gather evidence:

   • Review findings
   • Bugs found during verification
   • Security findings
   • User corrections
   • Failed or slow checks
   • Token or context pain
   • session-report artifacts, hallucination reports, and feedback logs

2. Classify:

   • Skill rule gap
   • Eval coverage gap
   • Workflow gap
   • Documentation gap
   • Tooling gap
   • Specialist gap
   • Environment-only issue

3. Decide action:

   • Existing skill should prevent it: update SKILL.md and evals/evals.json.
   • No skill covers it: propose a new skill.
   • Workflow caused drift: update .agents/workflows.
   • Specialist caused drift: add budget, tool fallback, or output-format rule.
   • Tooling can catch it: add or update an audit script.

4. Verify learning:

   • Run changed skill validation.
   • Run eval alignment.
   • Record remaining follow-ups.

Output Template

# Retro: [Name]

## Evidence

## Root Causes

| Finding | Category | Action |
| --- | --- | --- |
| [finding] | [category] | [action] |

## Skill Or Eval Updates

## Follow-Ups