# Paper Audit

> Unified paper audit for Chinese and English papers. Use when reviewing paper quality, pre-submission checks, or doing adversarial reviews.

- Skill: `jsgforever/paper-audit` (Agent Skill, multi-file: 16 files)
- Install (CLI): `npx skillmds@latest add jsgforever/paper-audit`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jsgforever/paper-audit/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: jsgforever (https://skillmd.com/u/jsgforever)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/jsgforever/paper-audit

---


# Paper Audit Skill

Unified academic paper auditing across formats and languages.

## Steps

1. Parse the paper path and mode from `$ARGUMENTS`. If missing, confirm the target `.tex`, `.typ`, or `.pdf` file.
2. Review evaluation criteria in `$SKILL_DIR/references/REVIEW_CRITERIA.md` and `$SKILL_DIR/references/CHECKLIST.md`.
3. Run the orchestrator: `python $SKILL_DIR/scripts/audit.py $ARGUMENTS`.
4. Present the MD report directly to the user. Distinguish between automated findings and LLM-judgment scores.
5. If in `review` mode, read `$SKILL_DIR/references/SCHOLAR_EVAL_GUIDE.md` and formulate LLM assessments for Novelty, Significance, Ethics, and Reproducibility.
6. If in `polish` mode, read `.polish-state/precheck.json` and spawn nested tasks for the Critic Agent and Mentor Agents as defined in the original workflow specifications.

## Examples

- Run `python $SKILL_DIR/scripts/audit.py $ARGUMENTS`.
- Run `python $SKILL_DIR/scripts/audit.py paper.pdf --mode review`.

## Troubleshooting

- Provide a valid `.tex`, `.typ`, or `.pdf` path when arguments are missing.
- Report command output and exit code when audit execution fails.