paper-reviewer
Skill229 starsChanged 2 months agoMITView on GitHub
Use this skill when the task is to review an academic paper PDF from the repo input folder, run specialized auditors, and compile a final report.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- whoisraibolt/paper-skillstheir own version, first seen Oct 13, 2026
- Boom5426/Nature-Paper-Skillstheir own version, first seen Oct 9, 2026
- darker2016/WorkbuddySkillGroups4DSHtheir own version, first seen Aug 14, 2026
- Chanw-research/claude-code-paper-writingtheir own version, first seen May 10, 2026
- yipng05-max/-skillstheir own version, first seen Apr 2, 2026
- tcztzy/skillstheir own version, first seen Apr 2, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- Boom5426/Nature-Paper-Skills★ 661same name
- yipng05-max/-skills★ 302same name
- Chanw-research/claude-code-paper-writing★ 42same name
- darker2016/WorkbuddySkillGroups4DSH★ 6same name
- astoreyai/claude-skills★ 3same name
- tcztzy/skills★ 2same name
- JieyuZhao/claude-skills★ 1same name
- whoisraibolt/paper-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- AGENTS.mdAGENTS.md
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. 0 are common, 5 are distinctive, and 13 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
13
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
If the user names a bare PDF filename, first look for it under inputs/.
- Distinctive: line 24
If the user gives a repo-relative path, use it.
- Distinctive: line 25
If the user gives an absolute path, use it as provided.
- Very specific: line 38
Run the conservative applicability router and record its complete decision in work/<paper_id>/selection/reviewer_selection.json.
- Very specific: line 39
Write the active run roster and selection provenance to work/<paper_id>/selection/selected_reviewers.json.
- Very specific: line 45
Run the editor to author work/<paper_id>/editor/editor_decisions.json.
- Very specific: line 51
If parsed artifacts, all selected reviewer JSON files, and work/<paper_id>/selection/selected_reviewers.json already exist, use …
- Very specific: line 57
Do not use editor-only refresh when reviewer evidence, parser artifacts, or reviewer selection needs to change.
- Very specific: line 65
Never guess missing evidence.
- Very specific: line 67
If parsed artifacts are poor, fix preprocessing before trusting reviewer outputs.
- Distinctive: line 68
Treat parser-quality preflight warnings as reportable caveats.
- Very specific: line 69
Never generate or infer repaired parser content.
- Distinctive: line 70
Keep final-report traceability in the traceability appendix.
- Very specific: line 72
If the final report cites external studies, registry records, web pages, or other external evidence, include the external-sources appendix …
- Distinctive: line 73
Put parser/preprocessing issues in the technical appendix and describe them as limitations of the review artifacts.
- Very specific: line 74
Treat scripts/check_final_report.py as a structure and traceability smoke check, not as independent verification that external sources are …
- Very specific: line 75
Treat every conditional specialist as a full-quality reviewer.
- Very specific: line 76
If a reviewer's assigned scope is absent, return run_status: ok with an empty findings array.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Paper Reviewer Skill
This skill runs a reproducible multi-agent paper-review workflow for academic PDFs.
Use this skill when
- the input is an academic paper PDF
- the task is review, auditing, or verification
- the user wants a structured report
- the task involves literature claims, references, numeric checks, or internal cross-references
Do not use this skill when
- the user wants only a summary
- the user wants only proofreading
- the user wants only a rewrite
- parsed artifacts already exist and the request is unrelated to the review pipeline
Default input convention
- If the user names a bare PDF filename, first look for it under
inputs/. - If the user gives a repo-relative path, use it.
- If the user gives an absolute path, use it as provided.
Workflow
For fresh runs, use scripts/review_paper.py as the primary entry point.
The pipeline stages are:
- Resolve the input PDF path.
- Derive
paper_idfrom the filename stem unless explicitly provided. - Preprocess the PDF into
work/<paper_id>/parsed/. - Render run-specific prompts into
work/<paper_id>/prompts/. - Launch preflight reviewers from
config/reviewers.json. - Validate preflight JSON and stop on blocking parser-quality failures.
- Route substantive reviewers around parser-quality warnings using the deterministic artifacts and parser-quality JSON.
- Run the conservative applicability router and record its complete decision in
work/<paper_id>/selection/reviewer_selection.json. Mixed, unknown, or lower-confidence classifications automatically expand to every conditional specialist. - Write the active run roster and selection provenance to
work/<paper_id>/selection/selected_reviewers.json. - Rerender prompts using the selected reviewer roster and parser-quality guidance.
- Launch the 8 universal review-stage reviewers and every applicable conditional specialist. The full roster contains 19 substantive reviewers.
- Validate each reviewer JSON output under
work/<paper_id>/reviews/. - Conservatively normalize reviewer outputs into a precision-first, lossless
work/<paper_id>/editor/normalized_bundle.json. Preserve every source finding's details and do not merge findings merely because they share a quote or path. - Build
work/<paper_id>/editor/editor_input.mdfrom the deterministic editor brief, the lossless bundle, and a compact provenance index. Validate the source reviewer JSON files, but do not duplicate them in the editor input or truncate evidence. - Run the editor to author
work/<paper_id>/editor/editor_decisions.json; validate dispositions and deterministically render its prose tooutputs/<paper_id>/report.md. - Smoke-check the final report with
scripts/check_final_report.py --bundle work/<paper_id>/editor/normalized_bundle.json.
The supported quality defaults are gpt-6.1-sol, xhigh reasoning for substantive reviewers and the editor, and high for parser-quality preflight and applicability routing. GPT-6 Luna (gpt-6-luna) is an optional lower-cost override using the same workflow. Selected reviewer tests and one complete pipeline comparison found uneven Luna coverage; Sol remains the default. The full comparison required manual Luna recovery after a sleep-related timeout, and structural report checks did not establish semantic completeness. It is not a general accuracy or unattended-recovery benchmark. There is one public workflow rather than separate static and dynamic modes.
Editor-only refresh
If parsed artifacts, all selected reviewer JSON files, and work/<paper_id>/selection/selected_reviewers.json already exist, use scripts/refresh_editor.py --paper-id <paper_id> to resume synthesis without rerunning reviewers. The helper:
- Validates every selected reviewer JSON against the schema, semantic rules, and provenance constraints.
- Rebuilds the precision-first lossless
work/<paper_id>/editor/normalized_bundle.jsonfrom the validated reviews. - Rerenders prompts and rebuilds the deterministic brief, lossless bundle, and provenance-only editor input using the active reviewer config.
- With
--run-editor, reruns the editor and smoke-checks the final report.
Do not use editor-only refresh when reviewer evidence, parser artifacts, or reviewer selection needs to change. Correct or rerun invalid reviewer output first; the helper will refuse to synthesize it.
Current editor-only refresh requires unchanged runtime resources and current acceptance receipts. Retain older runs with their original runtime; do not invent completion records or rewrite checkpoint hashes. See docs/evidence_gates.md in ordinary checkouts for migration and optional shadow-verification details.
Critical rules
- Internal reviewers return JSON only.
- The editor authors all substantive report prose; the shared deterministic renderer writes Markdown and its traceability map from validated editorial decisions.
- Literature and reference verification require web search when enabled.
- Never guess missing evidence; use
cannot_verify. - Preserve exact source locations whenever possible.
- If parsed artifacts are poor, fix preprocessing before trusting reviewer outputs.
- Treat parser-quality preflight warnings as reportable caveats; treat high-confidence blocking parser findings as a reason to stop before substantive review.
- Never generate or infer repaired parser content. Do not invoke an external parsing service or an LLM-generated repair layer. If deterministic artifacts do not support a reliable check, use
cannot_verify. - Keep final-report traceability in the traceability appendix. Do not reintroduce repeated traceability footers in the body.
- Literature and novelty critiques must be grounded in concrete studies or marked
cannot_verify; do not assert lack of novelty from vague prior-work impressions. - If the final report cites external studies, registry records, web pages, or other external evidence, include the external-sources appendix using only source details already present in reviewer evidence.
- Put parser/preprocessing issues in the technical appendix and describe them as limitations of the review artifacts. Mention one in the main report only when it materially reduces confidence in a substantive conclusion or prevents verification of an important claim.
- Treat
scripts/check_final_report.pyas a structure and traceability smoke check, not as independent verification that external sources are real or current. - Treat every conditional specialist as a full-quality reviewer. Skip one only when a high-confidence classification shows that its entire remit is materially absent. The theory-logic specialist checks formal validity and assumption-to-result logic; the universal model/equation auditor separately checks notation, definitions, and text-equation consistency.
- If a reviewer's assigned scope is absent, return
run_status: okwith an empty findings array. Do not turn the absence of an empirical design, formal model, dataset, experiment, or other method into a criticism. - A missing, stale or invalid editor-decisions object remains incomplete. Preserve diagnostics; do not promote a Markdown acknowledgement or transcript fragment.
Output conventions
- Parsed artifacts:
work/<paper_id>/parsed/ - Reviewer selection:
work/<paper_id>/selection/ - Reviewer outputs:
work/<paper_id>/reviews/ - Final report:
outputs/<paper_id>/report.md
The expected final report shape is synthesis-first and consequence-ranked: a compact executive summary; 3 to 6 confirmed corrections when supported; a concise revision sequence; separate material qualifications and exploratory development advice; domain sections; and late appendices for bibliography maintenance, copyediting, external sources, parser limitations, review scope, and traceability. Use one short plain-language review-scope paragraph near the end rather than listing agents or routing metadata.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

