# Retro · HiH-DimaN

> Self-proposing improvement cycle for the methodology itself — FACTS from the harness (itdretroscan.py aggregates VCR, regressions, active goals, SKILLBYPASS ledger, cost), PROPOSALS from the model (ranked, every one cites evidence from the scan; anti-Goodhart: external signals only), MERGE stays with the human via the ordinary release pipeline. Never edits the methodology itself; not a gate.

## Facts
- Page: https://tashan.sh/capability/skill-hih-diman-retro
- tashan id: skill:HiH-DimaN/retro
- Source: https://github.com/HiH-DimaN/idea-to-deploy
- Type: skill
- Category: other
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 62.0
- Freshness: 94.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: MIT
- Official: no

## Install

```sh
cp -r retro ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-14 by tashan (https://tashan.sh) from public evidence. Scorer s5.