# Research Paper Integrity

Standards and audits for writing academic papers, especially ML/NLP submissions to...

- Repository: https://github.com/Leanmcp/gateway-skills (2122 stars)
- Category: Data and ML
- License: MIT
- Last updated: 2026-10-07
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add Leanmcp/gateway-skills --skill research-paper-integrity -g -a claude-code -y`
Codex: `npx skills add Leanmcp/gateway-skills --skill research-paper-integrity -g -a codex -y`
Cursor: `npx skills add Leanmcp/gateway-skills --skill research-paper-integrity -g -a cursor -y`
Gemini CLI: `npx skills add Leanmcp/gateway-skills --skill research-paper-integrity -g -a gemini-cli -y`

## Description

Standards and audits for writing academic papers, especially ML/NLP submissions to NeurIPS, ICML, ICLR, ACL, EMNLP, NAACL. Covers the author's house prose rules (zero em dashes, zero fluff, every sentence earns its place), verification of hallucinated claims and hallucinated or malformed bibliography entries, the ACL policy on AI writing assistance and what must be disclosed, and best practices for paper structure, experiments, reproducibility checklists, and rebuttals. Use this skill whenever the user is drafting, editing, polishing, restructuring, or reviewing a paper, abstract, intro, related work, rebuttal, or camera-ready; whenever they ask to "clean up" or "tighten" academic writing; whenever citations or a .bib file need checking; and whenever they ask what has to be disclosed about AI assistance. Reach for it even when the user only says "make this section better", "check my references", or "is this ready to submit".

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Research paper integrity

This skill is the index. Each area below lives in its own reference file so you only
load what the current task needs. Read the file before acting on that area, not after,
because these rules change what you write rather than how you check it afterwards.

## What lives where

| Area | File | Read it when |
|---|---|---|
| Prose rules: no em dashes, no fluff, necessity test | `references/writing-style.md` | Writing or editing any prose the user will submit |
| Hallucination audit: unsupported claims, fake or wrong citations, bib hygiene | `references/hallucination-audit.md` | Any draft has claims or references that were not hand-verified |
| AI assistance disclosure (ACL 2023 policy and its logic) | `references/ai-writing-policy.md` | The user asks what to disclose, fills a responsible-NLP checklist, or used a model for text, ideas, or code |
| Conference craft: structure, experiments, figures, rebuttals, checklists | `references/conference-writing.md` | Planning a paper, restructuring sections, prepping a submission or rebuttal |

`scripts/check_prose.py` is a fast mechanical pass for em dashes, banned filler,
hedge stacking, and suspicious bib entries. It catches the boring violations so your
attention goes to the ones that need judgment. Per the user's global rule, do not run
it yourself: write it into the relevant workspace if needed and hand over the exact
command.

## The three commitments

Everything in this skill reduces to three things the user cares about. Keep them in
mind even when you have only loaded this index.

**1. The text contains no em dashes and no filler.** Not because em dashes are wrong
in general, but because in this user's papers they signal a sentence that was never
restructured, and filler signals a claim that was never sharpened. Replace an em dash
with a period, a colon, a comma, or parentheses, whichever the actual logic calls for.
Details and the filler list are in `references/writing-style.md`.

The rest: https://github.com/Leanmcp/gateway-skills/blob/HEAD/skills/research-paper-integrity/SKILL.md