agentsclimarketplace

Sci paper revision

Skill keithhegit/sci-using-kit/skills/sci-paper-revision

A skill family for evidence-bounded SCI manuscript workflows: literature vetting, claim-evidence alignment, paper revision, reviewer preflight, LaTeX editing, and submission packaging.

Install
npx -y skills add keithhegit/sci-using-kit --skill sci-paper-revision

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when rewriting, polishing, de-AI-ing, compressing, or restructuring SCI manuscript sections while preserving verified numbers, citations, methods, and evidence boundaries

SKILL.md

1.6 KB, as published. Nobody here has run it

SCI Paper Revision

Overview

Revise manuscript text without changing the scientific truth conditions.

Core principle: style may improve; claim strength must not increase unless evidence increases.

Required Inputs

Use the fields below directly. If the project has a section-revision template, update that template too.

Required fields:

  • target section and source file
  • current text
  • verified numbers and citations that must remain true
  • metric scope: detector-only, end-to-end, payload, power, accuracy, reproducibility, qualitative architecture
  • evidence level: measured once, repeated measurement, simulated, literature-supported, qualitative, future work
  • revision goal

Revision Rules

  • Preserve verified numbers.
  • Preserve citation meaning.
  • Remove promotional adjectives if they do not add information.
  • Replace broad claims with evidence-bounded claims.
  • If evidence is weak, expose the limitation instead of hiding it.
  • If comparative language appears, run sci-comparative-positioning.

Output

  • revised text
  • rationale for material changes
  • unsupported-claim warnings
  • consistency notes for abstract/introduction/conclusion

Common Mistakes

  • Making prose smoother by deleting caveats.
  • Turning "observed in HIL" into "validated in deployment."
  • Making baseline names sound stronger than the experiment supports.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.