agentleFS
Sign inStart free
NilsHellwigNilsHellwig/acl-paper-skills/CLAUDE.md

acl-paper-skills

CLAUDE.md3 starsChanged 12 days agoMITView on GitHub

Development guide for the acl-paper plugin itself. (Paper projects get their own CLAUDE.md from templates/CLAUDE.md.)

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Every rule lives in one place.

    line 19
  2. Very specific:

    Keep scripts/paperkit/ free of third-party imports and compatible with Python 3.10.

    line 23
  3. Very specific:

    Run pytest before committing.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

CLAUDE.md

Development guide for the acl-paper plugin itself. (Paper projects get their own CLAUDE.md from templates/CLAUDE.md.)

Layout

  • skills/<name>/SKILL.md: one folder per skill. User-invoked skills set disable-model-invocation: true; tests/test_repo.py holds the list of which is which.
  • scripts/paperkit.py: the CLI every skill calls as python3 ${CLAUDE_PLUGIN_ROOT}/scripts/paperkit.py. scripts/paperkit/: its stdlib-only library.
  • scripts/sources/: built-in source adapters (third-party imports allowed). The contract is the docstring of scripts/paperkit/sources.py.
  • hooks/hooks.json → scripts/hook_bibsync.py: offline bib sync after .tex/.bib edits.
  • templates/: files init copies into paper projects.

Writing skills

  • Skills are read by agents. Load the writing-for-agents skill (mattpocock-skills) before creating or editing one, if available.
  • ${CLAUDE_PLUGIN_ROOT} and ${CLAUDE_SKILL_DIR} are substituted in SKILL.md only. Reference files and templates copied into projects must not rely on them.
  • Upstream rules (ARR, ACL, ACLPUB) are fetched, never restated: a skill names the document set for paperkit.py guidelines, and states facts about the rules only as "check X in the fetched document".
  • Skills that report on upstream rules or review issues tell the agent to cite identifier and document URL (printed by paperkit.py guidelines); URLs are never written into skills.
  • Every rule lives in one place. Literature handling is in skills/literature, prose rules in skills/writing; other skills point there.

Code

  • Keep scripts/paperkit/ free of third-party imports and compatible with Python 3.10.
  • BibTeX stays raw text (bib.Entry.raw): never reformat an authoritative entry.
  • Run pytest before committing; pytest --network when touching adapters or guideline_sources.json.
  • Versions are bumped in four files at once (see CONTRIBUTING.md).

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