Sci issue intake
A skill family for evidence-bounded SCI manuscript workflows: literature vetting, claim-evidence alignment, paper revision, reviewer preflight, LaTeX editing, and submission packaging.
npx -y skills add keithhegit/sci-using-kit --skill sci-issue-intakeAssembled 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 a SCI paper task begins from a vague request, reviewer comment, advisor feedback, suspected flaw, manuscript confusion, or multi-step repair need
SKILL.md
1.5 KB, as published. Nobody here has run it
SCI Issue Intake
Overview
Convert a messy paper problem into a bounded revision brief before touching manuscript text.
Core principle: no manuscript edit until the issue type, evidence need, and success criteria are explicit.
Intake Fields
Use the fields below directly. If the project has an issue-intake template, update that template too.
Minimum fields:
- project and paper version
- user concern or reviewer comment
- affected section/file
- issue type: citation, claim, method, result, figure/table, LaTeX, submission, marketing
- evidence needed
- what must not change
- success criteria
Classification
| Issue type | Next branch |
|---|---|
| Citation or related work | sci-literature-vetting |
| Prose quality or section logic | sci-paper-revision |
| Results interpretation | sci-evidence-discussion |
| Prior-work comparison | sci-comparative-positioning |
| Submission readiness | sci-reviewer-preflight |
| TeX/package/reference breakage | sci-latex-editing |
Output
Produce a short brief:
- issue summary
- target files/sections
- evidence bundle to collect
- branch skill to use next
- open questions, only if blocking
Common Mistakes
- Treating reviewer tone as truth without mapping it to evidence.
- Jumping to a rewrite before identifying the claim being repaired.
- Letting one issue expand into a whole-paper rewrite.