agentleFS
hyf020908hyf020908/modelscope-skills/skills/modelscope-paper-publisher/SKILL.md

modelscope-paper-publisher

Skill4 starsChanged 8 months agoApache-2.0View on GitHub

Turn plain-language publication requests into evidence-backed Markdown reports for ModelScope repositories.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants a research-style write-up, release note, or technical summary backed by real project evidence.

    line 8
  2. Distinctive:

    Verify claims, citations, and links.

    line 21
  3. Distinctive:

    Never fabricate claims, ablations, or benchmark wins.

    line 32
  4. Distinctive:

    Never cite links you did not verify.

    line 33
  5. Distinctive:

    Prefer a shorter accurate report over a longer speculative one.

    line 34

≈ “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

ModelScope Paper Publisher

Use this skill when the user wants a research-style write-up, release note, or technical summary backed by real project evidence.

Request Style

  • Accept requests like:
    • Write a short technical report for this fine-tuning run.
    • 基于这些实验结果生成一篇可上传到仓库的总结。

Workflow

  1. Gather local evidence first: metrics, README files, configs, outputs.
  2. Choose the closest template.
  3. Draft locally.
  4. Verify claims, citations, and links.
  5. Upload only after the content is supported.

Assets

  • Templates: templates/standard.md, templates/arxiv.md, templates/ml-report.md, templates/modern.md
  • Script: scripts/paper_manager.py
  • Reference: references/quick_reference.md

Guardrails

  • Never fabricate claims, ablations, or benchmark wins.
  • Never cite links you did not verify.
  • Prefer a shorter accurate report over a longer speculative one.

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.