paper-review-pipeline — Claude Code skill: what it does
paper-review-pipeline is a Claude Code skill that reviews near-final ML conference papers section by section, prioritizes issues from P0 to P2, and drafts rebuttal responses.
no license ★ 475 updated 2026-10-13
npx skills add cnfjlhj/ai-collab-playbook --skill paper-review-pipeline -a claude-codeWhat paper-review-pipeline does
The skill runs a two-sided review of an almost-finished paper aimed at venues like ICML, ICLR, NeurIPS or AAAI. One pass goes section by section — Abstract, Introduction, Method, Experiments and onward — with concrete edit suggestions. The other builds a prioritized issue list grouped by category: narrative, evidence, experimental design, statistics, reproducibility, citations, formatting. Each entry gets a P0, P1 or P2 tag, a section anchor and a proposed fix.
A separate track handles reviewer feedback: it parses comments, sorts them by type and drafts a point-by-point rebuttal within a stated word or page limit. Citations that can't be verified get flagged as [CITATION NEEDED] rather than invented. When touching LaTeX source, the skill avoids breaking \cite{}, \ref{}, \label{} or math environments.
For a near-final PDF, the skill finishes its own review first and only then asks whether to hand off to the external paperreview service — it won't submit anything on its own.
What it helps with
- break a paper down by section and flag weak spots
- build a P0–P2 issue list sorted by category
- catch citations that don't match the claims they support
- draft a point-by-point rebuttal to reviewer comments
- run a pre-submission check before sharing with an advisor
Example prompts for the agent
- Run paper-review-pipeline on my ICLR draft and list the P0 issues
- Parse these reviewer comments and help me draft a rebuttal
- Check the Experiments section for missing baselines and stats reporting
How to install paper-review-pipeline
1Skills CLI (Vercel)
npx skills add cnfjlhj/ai-collab-playbook --skill paper-review-pipeline -a claude-code2Manually: put the files in place
~/.claude/skills/paper-review-pipeline/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/paper-review-pipeline/
1Skills CLI (Vercel)
npx skills add cnfjlhj/ai-collab-playbook --skill paper-review-pipeline -a codex2Manually: put the files in place
.agents/skills/paper-review-pipeline/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add cnfjlhj/ai-collab-playbook --skill paper-review-pipeline -a cursor2Manually: put the files in place
.cursor/skills/paper-review-pipeline/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install cnfjlhj/ai-collab-playbook skills/full/paper-review-pipeline2Manually: put the files in place
.github/skills/paper-review-pipeline/SKILL.md1Skills CLI (Vercel)
npx skills add cnfjlhj/ai-collab-playbook --skill paper-review-pipeline -a gemini-cli2Platform CLI
gemini skills install https://github.com/cnfjlhj/ai-collab-playbook --path skills/full/paper-review-pipelineManually: put the files in place
.devin/skills/paper-review-pipeline/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about paper-review-pipeline
How do I install paper-review-pipeline in Claude Code?
Run npx skills add cnfjlhj/ai-collab-playbook --skill paper-review-pipeline -a claude-code; the skill lands at ~/.claude/skills/paper-review-pipeline/SKILL.md.
What does paper-review-pipeline do?
It reviews a near-finished ML paper two ways: a section-by-section pass with edits, and a prioritized P0/P1/P2 issue list by category covering narrative, evidence, citations and more. It also drafts rebuttal responses.
How does paper-review-pipeline differ from paperreview?
paper-review-pipeline handles local self-review and rebuttal drafting. The separate paperreview service only gets involved on explicit user request, and only for a near-final PDF.