agentleFS
msimchowitzmsimchowitz/writing-skills/AGENTS.md

writing-skills

AGENTS.md54 starsChanged 4 months agoMITView on GitHub

These instructions apply to the whole repository. - Immediate child directories under for-agents/ containing SKILL.md are installable agent skills. - Everything under for-humans/ is for people and must not contain SKILL.md. Do not route ordinary writing tasks there. paper-writing may point to the guide or consult the relevant chapter for explicit template-use, teaching, or human-instruction requests. Otherwise load the focused agent references. - Keep private papers, proposals, downloaded arXiv source, and user drafts outside this repository. - Preserve license and…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

The file

Show its rules and text

We split this AGENTS.md into the rules it gives an agent

18 rules. About 0 are common, 5 are distinctive, and 13 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 13

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Keep private papers, proposals, downloaded arXiv source, and user drafts outside this repository.

    line 14
  2. Very specific:

    Read the selected SKILL.md in full.

    line 21
  3. Distinctive:

    Read only the references or assets needed for the requested change.

    line 22
  4. Very specific:

    Check sibling skills before changing a shared workflow.

    line 23
  5. Very specific:

    Run python3 scripts/validate-repo.py to establish a clean baseline.

    line 25
  6. Very specific:

    Keep the frontmatter name equal to the folder name.

    line 30
  7. Very specific:

    Put trigger conditions and the complete operating procedure in SKILL.md.

    line 31
  8. Very specific:

    Use relative links. Never add a username, home-directory path, or assumed Documents layout.

    line 34
  9. Distinctive:

    Keep instructions direct and testable.

    line 36
  10. Very specific:

    Keep SKILL.md under 500 lines.

    line 38
  11. Very specific:

    Update agents/openai.yaml when a skill's name or user-facing scope changes.

    line 40
  12. Distinctive:

    Keep private corpora outside this repository.

    line 45
  13. Very specific:

    Keep planning and drafting separate where the repository already does so, especially for grant-planning and grant-writing.

    line 64
  14. Distinctive:

    Keep each LaTeX entry point in the outermost project directory.

    line 71
  15. Very specific:

    Use a stable, descriptive <project-name>-main.tex filename, never a generic main.tex.

    line 72
  16. Very specific:

    Do not finish a writing task with the canonical PDF named main.pdf or available only under build/.

    line 76
  17. Very specific:

    Use improve-human-writing-guide for every proposed or applied change to the human guide.

    line 81
  18. Very specific:

    Do not edit generated files in build/ by hand.

    line 100

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

Instructions for agents

These instructions apply to the whole repository.

Repository boundaries

  • Immediate child directories under for-agents/ containing SKILL.md are installable agent skills.
  • Everything under for-humans/ is for people and must not contain SKILL.md. Do not route ordinary writing tasks there. paper-writing may point to the guide or consult the relevant chapter for explicit template-use, teaching, or human-instruction requests. Otherwise load the focused agent references.
  • Keep private papers, proposals, downloaded arXiv source, and user drafts outside this repository.
  • Preserve license and attribution files, especially in humanizer and general-writing.

Before editing

  1. Read the selected SKILL.md in full.
  2. Read only the references or assets needed for the requested change.
  3. Check sibling skills before changing a shared workflow. The writing skill owns routing; general-writing owns the Humanizer-first prose pipeline.
  4. Run python3 scripts/validate-repo.py to establish a clean baseline.
  5. Inspect the working tree and preserve unrelated changes.

Skill design

  • Keep the frontmatter name equal to the folder name.
  • Put trigger conditions and the complete operating procedure in SKILL.md.
  • Move detailed domain knowledge, long examples, and checklists into references/; place reusable starter files in assets/.
  • Use relative links. Never add a username, home-directory path, or assumed Documents layout.
  • Keep instructions direct and testable. State what an agent must inspect, produce, preserve, and verify.
  • Keep SKILL.md under 500 lines. Add an abstraction only when it removes repeated instructions or gives one skill clear ownership of a workflow.
  • Update agents/openai.yaml when a skill's name or user-facing scope changes. The default prompt must mention the exact $skill-name.

Optional corpora

Keep private corpora outside this repository. When a task would benefit from original examples, use a directory the user supplied for that task. If no directory was supplied, ask where the relevant example folder lives and make clear that the user can answer none.

Accept either the corpus directory itself or a parent containing the relevant example-papers or example grants directory. Do not search above the repository or assume a home-directory layout. If the corpus is unavailable, use the distilled reference bundled with the relevant skill and say that the original artifacts were not inspected. Never copy private corpus content into a contribution without explicit permission.

Cross-skill behavior

  • Let writing route requests; do not duplicate full domain instructions in the router.
  • Let general-writing invoke Humanizer and then enforce the author's house style. Domain skills should call that workflow once rather than reimplement it.
  • Keep planning and drafting separate where the repository already does so, especially for grant-planning and grant-writing.
  • Preserve factual claims, citations, notation, and format constraints during prose edits.

Named LaTeX artifacts

  • Keep each LaTeX entry point in the outermost project directory.
  • Use a stable, descriptive <project-name>-main.tex filename, never a generic main.tex.
  • Compile to build/<project-name>-main.pdf, then copy that exact PDF to <project-name>-main.pdf in the outermost project directory.
  • Do not finish a writing task with the canonical PDF named main.pdf or available only under build/.

Human guide changes

Use improve-human-writing-guide for every proposed or applied change to the human guide. Its prose workflow is mandatory: run Humanizer in embedded mode, then general-writing and its evaluation checklist before finalizing wording. Compile from for-humans/human-writing-guide after every meaningful source change:

latexmk -g -pdf -interaction=nonstopmode -halt-on-error \
  -outdir=build human-writing-guide-main.tex

Inspect the rendered PDF. Before finishing, publish the exact build at the documented top-level name:

cp build/human-writing-guide-main.pdf human-writing-guide-main.pdf
cmp -s build/human-writing-guide-main.pdf human-writing-guide-main.pdf

Do not edit generated files in build/ by hand.

Finish

Run:

python3 scripts/validate-repo.py

For installer changes, also smoke-test both link and copy modes in a temporary directory. Report any test that could not be run.

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.