manuscript-review
Skill4 starsChanged 7 months agoMITView on GitHub
Audit technical manuscripts for mathematical correctness, logical soundness, notation consistency, evidence quality, and figure or code alignment. Use when Codex needs to review a paper, verify derivations, prioritize findings, or produce a rigorous findings-first assessment instead of rewriting prose blindly.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- pradyumnasagar/open-research-skillstheir own version, first seen Nov 8, 2026
- Mathews-Tom/armorytheir own version, first seen Nov 1, 2026
- HeartWise-AI/ai-writing-skillstheir own version, first seen Sep 4, 2026
- bladecoder/narrative-skillstheir own version, first seen Apr 13, 2026
- emaduneme/communications-skills-claudetheir own version, first seen Apr 1, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- Mathews-Tom/armory★ 340same name
- HeartWise-AI/ai-writing-skills★ 29same name
- pradyumnasagar/open-research-skills★ 8same name
- emaduneme/communications-skills-claude★ 3same name
- bladecoder/narrative-skills★ 0same 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 repository8 other files it gives its agents.
- inline-paper-criticSkill
- literature-searchSkill
- mathematical-enhancerSkill
- math-ocrSkill
- scientific-presenterSkill
- scientific-simplifierSkill
- tikz-figure-builderSkill
- writing-commenterSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this skill for serious review passes on papers, notes, appendices, or technical drafts where the main job is to find problems, verify …
- Distinctive: line 14
Read the full manuscript context first, including appendices, bibliography, macros, figures, and any supporting code that drives results.
- Distinctive: line 16
Verify critical calculations independently when feasible.
- Distinctive: line 17
Use computational verification tools when available for symbolic algebra, identities, spot checks, and code-backed results.
- Distinctive: line 19
Check code-manuscript consistency when the paper depends on scripts, notebooks, generated figures, or implemented algorithms.
- Distinctive: line 20
Check whether the manuscript actually delivers the goals stated in the abstract and introduction.
- Distinctive: line 26
Check appendices before claiming a derivation is missing.
- Distinctive: line 29
Prefer a short list of high-signal findings over a noisy dump of minor edits.
- Distinctive: line 30
If no major issues are found, say that explicitly and note any residual uncertainty or untested areas.
“Common” is measured: kept by at least 6 in 10 of the 5 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
Manuscript Review
When to use this skill
Use this skill for serious review passes on papers, notes, appendices, or technical drafts where the main job is to find problems, verify important claims, and report actionable findings.
Workflow
- Read the full manuscript context first, including appendices, bibliography, macros, figures, and any supporting code that drives results.
- Identify the main claims and the highest-risk derivations, proofs, experiments, and references before going broad.
- Verify critical calculations independently when feasible. Check limiting cases, dimensions, signs, factors, boundary conditions, and whether stated results follow from the setup.
- Use computational verification tools when available for symbolic algebra, identities, spot checks, and code-backed results. If you verify something numerically or symbolically, say so explicitly in the findings.
- Trace notation across the document. Confirm symbols are defined before use and stay stable across sections, figures, and code.
- Check code-manuscript consistency when the paper depends on scripts, notebooks, generated figures, or implemented algorithms.
- Check whether the manuscript actually delivers the goals stated in the abstract and introduction.
- Produce findings first. Order them by severity and point to exact locations.
- Distinguish confirmed errors, likely issues, and open questions. Do not blur them together.
Quality Bar
- Check appendices before claiming a derivation is missing.
- Focus on issues that affect validity, interpretation, reproducibility, or reader comprehension.
- Be specific about what you verified and how.
- Prefer a short list of high-signal findings over a noisy dump of minor edits.
- If no major issues are found, say that explicitly and note any residual uncertainty or untested areas.
For a formal audit pass, use references/review-checklist.md when the manuscript is mathematically dense, has code-backed figures or computations, or needs a full findings report.
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.

