# Peter Zhou Mistake Bank

> Store, validate, review, confirm, and query Peter Zhou mistake-bank records. Use for RawMistakeRecord persistence, SourceDocument status, is_wrong review, id allocation, crop refs, and script-owned JSON writes.

- Skill: `szsip239/peter-zhou-mistake-bank` (Agent Skill)
- Install (CLI): `npx skillmds@latest add szsip239/peter-zhou-mistake-bank`
- Raw SKILL.md: https://api.skillmd.com/api/skills/szsip239/peter-zhou-mistake-bank/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: szsip239 (https://skillmd.com/u/szsip239)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/szsip239/peter-zhou-mistake-bank

---


# Mistake Bank

Use this subskill when a recognized result must become canonical local data.

Core contract:

- Persist one JSON file per subject under the mistake bank.
- Keep `SourceDocument` state separate from subject mistake records.
- Keep `is_wrong=false` records for audit, but exclude them from final stats and practice by default.
- Generate review reports from canonical data; do not persist separate long-lived review tables.
- Allocate ids and write JSON only through `scripts/allocate_id.py` and `scripts/json_store.py`; see `references/schema.md`.
- After every successful `scripts/intake_recognition.py ingest`, present the returned `review_report` as the next skill step for user review. Focus the user on `needs_review=true`, low-confidence answers, ambiguous teacher marks, and crop screenshots. If the user does not review, leave the source status as `processed`; only `apply-review --confirm` moves it to `confirmed`.
- Use `scripts/intake_recognition.py review-report` to regenerate the same derived report, `apply-review` for user corrections/confirmation, and `repair-crops` for script-owned screenshot bbox fixes.