# Codify Corrections

> Process $GOVERNANCESTATEDIR/user-corrections.jsonl — the Stop-hook-harvested signals of user corrections ("不是" / "不對" / "應該" / "糾正" etc.). Dedup by session + keyword, cluster by topic, and apply edits to the canonical owner(ds-canonical rule / repository memory / canonical skill reference / spec.md rationale) under the shared authority classifier. Engineering/governance clusters auto-execute with evidence; only genuine product/UI/UX SSOT tradeoffs stop. After codification archive processed entries in the same Git-owned runtime state root. Invoke when user-corrections.jsonl exceeds 20 entries(sessionstart soft reminder)or exceeds 40 entries(hard threshold), OR quarterly.

## Facts
- Page: https://tashan.sh/capability/skill-ajenchen-codify-corrections
- tashan id: skill:ajenchen/codify-corrections
- Source: https://github.com/ajenchen/design-system
- Type: skill
- Category: design
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 96.0
- Freshness: 92.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- Official: no

## Install

```sh
cp -r codify-corrections ~/.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 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.