agentleFS
LocloveLoclove/cumcm-skills/skills/cumcm-shared/SKILL.md

cumcm-shared

Skill4 starsChanged 3 months agoMITView on GitHub

Internal shared-reference package for CUMCM mathematical-modeling skills. Use only when another cumcm-* skill needs official contest-format constraints, anonymity rules, citation and formula standards, data-provenance gates, AI-use boundaries, or final submission quality gates. Do not invoke as a standalone modeling workflow.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    Use this package as a dependency of other cumcm-* skills.

    line 8
  2. Distinctive:

    Treat official problem statements and current official contest rules as higher priority than all historical examples.

    line 13
  3. Distinctive:

    Treat user-provided attachments as primary evidence.

    line 14
  4. Distinctive:

    If a current rule conflicts with a local reference, follow the current official rule and mark the local reference stale.

    line 15
  5. Distinctive:

    Never allow participant identity, school, or region information to remain in paper body, abstract, appendices, or support materials.

    line 30
  6. Distinctive:

    Never let a paper claim a result that cannot be traced to data, code, manual calculation, or a cited source.

    line 31
  7. Distinctive:

    Never treat historical excellent papers as templates to copy.

    line 32
  8. Distinctive:

    Never hide missing code, broken programs, or mismatched outputs behind prose.

    line 33
  9. Distinctive:

    Never present the enhanced 25-page minimum or Song-font profile as an official national rule.

    line 34

≈ “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 Shared References

Use this package as a dependency of other cumcm-* skills.

Loading Rules

  • Load only the exact referenced file needed by the active skill.
  • Treat official problem statements and current official contest rules as higher priority than all historical examples.
  • Treat user-provided attachments as primary evidence. Do not invent data, formulas, citations, or submission requirements.
  • If a current rule conflicts with a local reference, follow the current official rule and mark the local reference stale.

Shared Files

FileOpen when
references/format-spec-2026.mdChecking paper page order, page limits, electronic file constraints, appendices, and support-material requirements.
references/enhanced-writing-profile.mdEnforcing the repository default of Song-style Chinese typography, 25--30 body pages, Nature-style argument flow, and figure-text integration.
references/quality-gates.mdBuilding a final go/no-go checklist across modeling, data, code, figures, paper, and package.
references/citation-formula-standards.mdEnforcing at least 8 references/data citations when external sources are used, and checking formula display rules.
references/data-provenance.mdCreating or auditing source-data, processing, output, and figure traceability.
references/competition-ethics.mdHandling originality, AI-use disclosure, non-discussion boundaries, and external-data caution.

Non-Negotiables

  • Never allow participant identity, school, or region information to remain in paper body, abstract, appendices, or support materials.
  • Never let a paper claim a result that cannot be traced to data, code, manual calculation, or a cited source.
  • Never treat historical excellent papers as templates to copy. Use them only for structural patterns.
  • Never hide missing code, broken programs, or mismatched outputs behind prose.
  • Never present the enhanced 25-page minimum or Song-font profile as an official national rule; label it as the repository/user profile and let current official rules take precedence.

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.