agentleFS
Sign inStart free
NilsHellwigNilsHellwig/acl-paper-skills/skills/camera-ready/SKILL.md

camera-ready

Skill3 starsChanged 12 days agoMITView on GitHub

Prepare and check the camera-ready version against the current ARR, ACL, ACLPUB and SemEval final-version rules (de-anonymization, acknowledgments, extra page, metadata, PDF checks).

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. flonat/flonat-research★ 150same name
    2. acprk/crypto-research-agents★ 15same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository13 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Read venue, paper_type and stage from paper.config.json and confirm them in one line (store corrections with PK config-set).

    line 14

≈ “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

Turn the accepted paper into its final version and check it against the publication rules as they are published today. Every run fetches them.

PK means python3 ${CLAUDE_PLUGIN_ROOT}/scripts/paperkit.py, run from the project root.

1. Fetch the rules

Read venue, paper_type and stage from paper.config.json and confirm them in one line (store corrections with PK config-set). If stage is review, ask whether the paper is accepted and the final version is due now.

PK guidelines camera-ready

For venue semeval fetch camera-ready-semeval instead: the SemEval paper requirements and system paper template plus ACLPUB's and the ACL template's guides. SemEval's own documents and the shared task's year page (ask for its URL; it wins) decide where they differ from ACLPUB. SemEval is not anonymous, so there is nothing to de-anonymize; check the title format and the final-version page limit in the fetched requirements.

For acl-arr it fetches the ARR author guide (camera-ready section), ACLPUB's final-version and formatting guides and the ACL template's formatting.md. On ⚠️ say what is missing. Read them in full. Then ask with AskUserQuestion, in one round: venue and paper type, the camera-ready deadline, whether the venue's own call names extra requirements (they override the general guides; ask for the text or URL), author names, order and affiliations as they should appear, and what goes in the acknowledgments (funding numbers). Ask again whenever a formatting rule leaves a choice the fetched guides do not settle.

2. Open promises

Collect open report.md items in category Review, especially changes promised in rebuttal.md, and the meta-review's requests in reviews/meta.md. Ask the user which are done; the rest are 🔴.

3. Check and prepare

Go through the fetched rules one by one. Typical points, to be confirmed against the fetched text rather than assumed:

  • \usepackage[review]{acl} becomes \usepackage[final]{acl} (or the option the guides name), authors and affiliations filled in.
  • Self-citations anonymized for review get their real form back; "anonymous" links (code, data) become the real URLs.
  • Acknowledgments added where the guides allow.
  • Page limit for the final version, and what does not count towards it.
  • Limitations and ethics sections as required.
  • PDF requirements: fonts embedded, no overfull lines into margins, PDF metadata, hyperlinks. Check them on the compiled PDF (pdffonts if available); when there is no fresh PDF, ask the user to compile.
  • Bib: PK sync reports nothing unknown or unread; entries have venue and year.

Edit only what the user approves. Cite every rule by the identifier the fetched document uses (section heading, checklist question, issue code such as H9) and the document's URL as PK guidelines prints it. Rule violations and anything left open go to report.md, category ACL-Compliance.

Done when each rule in the fetched guides is marked met, fixed or open. Report in chat, each rule with identifier and document URL, what was changed, what is open, and the rules you could not check.

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