agentleFS
bas1lbas1l/claude-skills/scientific-article-writing/SKILL.md

scientific-article-writing

Skill0 starsChanged 10 days agoNo licenceView on GitHub

How Basil and Claude co-write a scientific journal article, in linked section pairs drafted and loaded together: figures first (claim check, gallery of house-style prototypes, ranked proposals, variants, export, staging); then Results with Materials and Methods (Results as verified standalone docx drafts, the Word review and trim loop with tracked changes, Methods cut to the kept Results); then Discussion with the state of the art; then Introduction with Conclusion, fitted to what was kept; then the Abstract last, alone. Takes an optional section argument (figures, results, methods, discussion, introduction, state-of-the-art, conclusion, abstract) and loads only that section's guidance, its pair's guidance and the global rules; a task spanning several stages runs as a team of background teammates, one per section, that message each other and may spawn their own subagents. Use whenever work touches a manuscript, article or paper: writing, drafting, revising, trimming or restructuring a Results, Methods, Discussion, Introduction, related-work, Conclusion or Abstract section (restructure the methods to follow the Results); generating, choosing or redrawing a paper figure; writing or shortening captions; building a figure gallery or prototype set; reviewing a reviewed or trimmed .docx edited in Word; adding context or corrections to kept text; staging figures; checking terms across figure, caption and text; verifying citations, checking references against their sources or adding missing ones. Applies in any article's code repository or manuscript folder, even when 'skill' or 'article' is not said.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “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.

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.