agentleFS
LocloveLoclove/cumcm-skills/skills/cumcm-format-packager/SKILL.md

cumcm-format-packager

Skill4 starsChanged 3 months agoMITView on GitHub

Check and prepare final CUMCM paper and support-material packages, including 2026 format constraints, the default 25--30-page body, embedded Song-style Chinese fonts, figure-text integration, paper/support file size, page order, no directory, anonymity leaks, appendix code list, source-code completeness, citation count, formula rendering, and ZIP/RAR support archive readiness. Use before final submission or when the user asks for格式检查,匿名检查,附件检查,提交包,PDF检查, or final packaging.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    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:

    Run scripts/check_cumcm_package.py when paper/support files exist.

    line 13
  2. Very specific:

    Run ../cumcm-paper-writing/scripts/check_citations_formulas.py for source drafts when available.

    line 14
  3. Distinctive:

    Check paper file, support archive, appendix file list, source-code completeness, no identity leaks, and file-size limits.

    line 15
  4. Distinctive:

    Do not mark GO while required source code, appendix list, citation integrity, formula integrity, or anonymity checks fail.

    line 39
  5. Distinctive:

    Do not compress the paper itself when the rule requires an uncompressed paper file.

    line 40
  6. Distinctive:

    Do not include commitment/number pages in the electronic paper when the current rule excludes them.

    line 41
  7. Distinctive:

    Do not report the 25-page minimum or Song-font rule as a national requirement.

    line 42
  8. Distinctive:

    Do not mark GO when body-page or font verification cannot be completed under the enhanced profile.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

CUMCM Format Packager

This skill is the final gate before submission.

Workflow

  1. Load ../cumcm-shared/references/format-spec-2026.md, ../cumcm-shared/references/enhanced-writing-profile.md, ../cumcm-shared/references/citation-formula-standards.md, and ../cumcm-shared/references/quality-gates.md.
  2. Run scripts/check_cumcm_package.py when paper/support files exist. Its default enhanced profile enforces 25--30 estimated body pages and embedded Song-style Chinese fonts; use --profile official only when the user explicitly wants national-rule-only checking.
  3. Run ../cumcm-paper-writing/scripts/check_citations_formulas.py for source drafts when available.
  4. Check paper file, support archive, appendix file list, source-code completeness, no identity leaks, and file-size limits.
  5. Return a go/no-go decision with blocking issues first.

Output Contract

Submission decision
- GO / NO-GO:

Blocking issues
- ...

Format checks
| Check | Status | Evidence | Fix |

Support-material checks
| Check | Status | Evidence | Fix |

Final actions
- ...

Red Lines

  • Do not mark GO while required source code, appendix list, citation integrity, formula integrity, or anonymity checks fail.
  • Do not compress the paper itself when the rule requires an uncompressed paper file.
  • Do not include commitment/number pages in the electronic paper when the current rule excludes them.
  • Do not report the 25-page minimum or Song-font rule as a national requirement; report them as enhanced-profile checks.
  • Do not mark GO when body-page or font verification cannot be completed under the enhanced profile.

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.