agentleFS
DJDeborahDJDeborah/research-mechanics-skills/skills/research-writing/SKILL.md

research-writing

Skill0 starsChanged 45 days agoMITView on GitHub

Draft or revise scientific manuscripts with claim-to-evidence traceability, clear physical definitions and preservation of essential Main/SI content. Use for mechanics research writing, figure narratives and bounded validation claims.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the writing contract.

    line 13
  2. Very specific:

    Avoid translating minimum eigenvalue = 0 into proven snap, calibration into prediction, repeated supercells into a new material family, or …

    line 19

“Common” is measured: kept by at least 6 in 10 of the 6 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.

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

Research writing

Make the scientific argument readable without losing the material that supports it.

  1. Establish the requested language, audience, manuscript version and deliverable. Use the user's chosen format. Inspect the latest full evidence-bearing Main/SI, not just the shortest or newest text.
  2. Read the writing contract. Make a claim/evidence inventory and a preservation list before major restructuring. Use assets/manuscript-map.json as a schema example, with project-relative evidence paths.
  3. Structure each result as question → observation → mechanism interpretation → evidence boundary. Give variables and DOF conventions before equations. Connect figure panels to the conclusion they support. Put physical meaning in Main and reproducible details in SI without deleting the bridge between them.
  4. Mark traced draft statements with [claim:C1] and figure references with [figure:F1]. Run python <skill-dir>/scripts/audit_manuscript.py <project>/manuscript-map.json <project>/draft.md --out <project>/writing-audit.json. The inventory can represent a DOCX/TeX draft via an extracted Markdown audit copy; use the relevant artifact workflow for rendering the final file.
  5. Inspect every flagged semantic issue yourself. Existing files or a phrase match cannot verify a scientific claim. Report supported, disputed and untested claims. Preserve originals and write the revised version to a new file unless the user asked to edit in place.
  6. Deliver the revised text, a meaningful change summary and any missing evidence. Audit tags are for review; remove them from the clean final after retaining an annotated copy and the map.

Avoid translating minimum eigenvalue = 0 into proven snap, calibration into prediction, repeated supercells into a new material family, or simulated performance into hardware demonstration. State the specific result and its range instead of making an absolute negative claim.

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.