paper-audit

これはレビュー時に保存された抜粋です。完全で最新の内容は外部ソースを確認してください。

---
name: paper-audit
description: Reviewer-style audit and submission gate for academic papers in .tex, .typ, or .pdf. Use for peer-review critique, readiness/gate decisions, blocker triage, revision roadmaps, journal-style reports, and re-audits. Do not use for source editing, sentence polishing, bibliography search, or compile repair.
when_to_use: >-
  Trigger on "review my paper", "act as a reviewer", "simulate peer review", "audit this paper",
  "审稿", "投稿门控", "投稿前体检", "把把关", "看看能不能投", "出审稿意见",
  "is this ready to submit", or requests for major/minor issues and revision priorities.
metadata:
  category: academic-writing
  tags: [audit, deep-review, paper, pdf, latex, typst, chinese, english, reviewer, gate, re-audit]
  version: "6.0.0"
  last_updated: "2026-08-09"
argument-hint: "[paper.tex|paper.typ|paper.pdf] [--mode quick-audit|deep-review|gate|re-audit|polish] [--report-style deep-review|peer-review] [--focus full|editor|theory|literature|methodology|logic] [--venue VENUE] [--lang en|zh] [--previous-report PATH] [--literature-search] [--tavily-key KEY] [--s2-key KEY] [--scholar-eval] [--regression] [--overwrite-workspace] [--format md|json]"
allowed-tools: Read, Glob, Grep, Bash(uv *), Task
---

# Paper Audit Skill v6.0

`paper-audit` is **deep-review-first**: behave like a serious reviewer — find
technical, methodological, claim-level, and cross-section issues; keep
script-backed findings separate from reviewer judgment; return a structured
issue bundle plus a revision roadmap. Use it for audit and review, not as the
first tool for source editing, sentence rewriting, or build fixing.

A script-backed `PRESUBMISSION` layer handles final-week mechanical checks
(em dashes, AI-tone term frequency, abstract completeness, LaTeX
citation/label/equation hygiene, paragraph-shape weak signals, concrete
captions). It plugs into existing modes and is not a separate public mode;
see `references/PRESUBMISSION_GUIDE.md`.

**Requirements**: `.tex`/`.typ` audit needs only the Python standard library.
**PDF mode needs `pip install pymupdf`** (the `enhanced` extraction path also
needs `pymupdf4llm`); both are optional and lazily imported — a `.pdf` input
without them fails with a clear install hint.

## What This Skill Produces

- `quick-audit`: fast submission-readiness screen with script-backed findings, incl. `PRESUBMISSION`
- `deep-review`: reviewer-style structured issue bundle with major/moderate/minor findings
- `gate`: PASS/FAIL calibrated for submission blockers; `PRESUBMISSION` Major/Minor stay advisory
- `re-audit`: compare current issue bundle against a previous audit, incl. mechanical regressions
- `polish`: precheck-only handoff into a polishing workflow

The primary product is no longer just a score: the `deep-review` workspace
root contains exactly four reader-facing files — `review_report.md`,
`revision_suggestions.md`, and their HTML twins — with everything else under
`artifacts/`. Full artifact map and the `--lang en|zh` report-language rules:
`references/output-layout.md`.

## Do Not Use

- direct source surgery on `.tex` / `.typ`
- compilation debugging as the main task
- free-form literature survey writing
- paragraph-level related-work rewriting
- cosmetic grammar cleanup without an audit goal
- cover letter generation / optimization / claim alignment — route to `cover-letter`

## Critical Rules

- Don't rewrite the paper source — `paper-audit` is a reviewer, not an editor; switch skills explicitly if the user wants prose changes, so review evidence stays separable from edits.
- Don't fabricate references, baselines, or reviewer evidence — invented citations and made-up reviewer voices undermine every other finding in the bundle.
- Distinguish `[Script]` from `[LLM]` findings — script-backed items have a deterministic anchor the user can rerun, while LLM findings need a quote or section to be falsifiable.
- Anchor every reviewer finding to a quote, section, or exact textual location — unanchored complaints become