agentleFS
Sign inStart free
PerryLinkPerryLink/dsh-research-skills/skills/manuscript-preflight/SKILL.md

manuscript-preflight

Skill0 starsChanged 5 days agoApache-2.0View on GitHub

Run the pre-submission checks a journal or committee will run: structure/declarations, statistics, meta-analysis arithmetic, citations and retractions.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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
  1. Distinctive:

    Keep the manuscript unchanged unless the user asks for edits.

    line 13
  2. Distinctive:

    Do not claim a journal's acceptance criteria were met.

    line 32
  3. Distinctive:

    Do not state that an image is manipulated.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Manuscript preflight

Rules

  • Report what was checked, what was not, and with which rule set.
  • A checklist pass is not a quality verdict; say so.
  • Keep the manuscript unchanged unless the user asks for edits.

Steps

  1. manuscript_check for structure, declarations, and the applicable reporting guideline starter items.
  2. statcheck for reported t/F/chi-square/r/z values, df and p values.
  3. meta_analysis when pooled effects are reported (effect sizes, Q, I², τ²).
  4. cite_verify + retraction_watch for the reference list.
  5. image_integrity for PNG panels where reuse/duplication is a concern; report only matched regions.
  6. research_report the findings; hand the sealed record to the user.

Output

  • Findings grouped by check, each with a locator (section/page/claim).
  • Explicit "not checked" list (e.g., JPEG images, figures not supplied).
  • A short fix order: blocking → warning → optional.

Never

  • Do not claim a journal's acceptance criteria were met.
  • Do not state that an image is manipulated; report repeated pixels only.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free