agentleFS
Sign inStart free
hyf020908hyf020908/modelscope-skills/skills/modelscope-tracking/SKILL.md

modelscope-tracking

Skill4 starsChanged 8 months agoApache-2.0View on GitHub

Add local, file-based experiment tracking to ModelScope workflows from plain-language requests.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 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.

  • 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 experiment tracking that stays local, transparent, and easy to publish later.

    line 8
  2. Distinctive:

    If tracking is not initialized, initialize it automatically in the current project.

    line 15
  3. Distinctive:

    Create or reuse a run id.

    line 24
  4. Distinctive:

    Never store secrets in tracking files.

    line 47
  5. Distinctive:

    Keep metric names stable across runs.

    line 48
  6. Distinctive:

    Prefer append-only logs over in-place mutation.

    line 49

≈ “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 Tracking

Use this skill when the user wants experiment tracking that stays local, transparent, and easy to publish later.

Request Style

  • Accept requests such as:
    • Track this SFT run.
    • 把最近几次实验整理成可比较的报告。
  • If tracking is not initialized, initialize it automatically in the current project.

Primary Script

  • scripts/run_tracker.py

Workflow

  1. Initialize .modelscope-tracking/ when missing.
  2. Create or reuse a run id.
  3. Log metrics and artifacts as files, not opaque state.
  4. Summarize runs into Markdown, JSON, or CSV.
  5. Publish reports later with ordinary ModelScope upload workflows.

Directory Layout

.modelscope-tracking/
  project.json
  runs/
  artifacts/
  reports/

References

  • references/logging_metrics.md
  • references/retrieving_metrics.md
  • references/alerts.md

Guardrails

  • Never store secrets in tracking files.
  • Keep metric names stable across runs.
  • Prefer append-only logs over in-place mutation.

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