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

modelscope-evaluation

Skill4 starsChanged 8 months agoApache-2.0View on GitHub

Turn plain-language evaluation requests into benchmark extraction, remote evaluation jobs, and publishable result artifacts.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Use this skill when the user wants to extract, normalize, run, or publish model evaluation results.

    line 8
  2. Distinctive:

    Use local extraction for lightweight tasks.

    line 34
  3. Distinctive:

    Use PAI DLC only for real model evaluation or long-running inference.

    line 35
  4. Very specific:

    When remote submission is needed, create configs/pai.required.env if required PAI values are missing and wait for continue.

    line 36
  5. Distinctive:

    Never fabricate benchmark values.

    line 66
  6. Distinctive:

    Never merge incompatible units into one score field.

    line 67
  7. Distinctive:

    Never overwrite existing scores without an explicit merge rule.

    line 68
  8. Distinctive:

    Prefer dry-run style extraction before mutating repository content.

    line 69

≈ “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 Evaluation

Use this skill when the user wants to extract, normalize, run, or publish model evaluation results.

Request Style

  • Accept natural requests such as:
    • Run an MMLU pilot for this model.
    • 把 README 里的评测表抽出来，整理成结构化 JSON。
  • First decide whether the task is:
    • metadata extraction
    • score normalization
    • a real evaluation run

Primary Scripts

  • scripts/evaluation_manager.py
  • scripts/run_eval_job.py
  • scripts/run_vllm_eval_job.py
  • scripts/inspect_eval_uv.py
  • scripts/inspect_vllm_uv.py
  • scripts/lighteval_vllm_uv.py
  • scripts/submit_pai_dlc.py

Workflow

  1. Inspect existing README tables, JSON, YAML, and logs before generating anything new.
  2. Normalize benchmark names and units.
  3. Use local extraction for lightweight tasks.
  4. Use PAI DLC only for real model evaluation or long-running inference.
  5. When remote submission is needed, create configs/pai.required.env if required PAI values are missing and wait for continue.
  6. Save machine-readable outputs under eval/ or another explicit directory.

Credential Gate

Pause remote execution until these exist:

  • ALIBABA_CLOUD_ACCESS_KEY_ID
  • ALIBABA_CLOUD_ACCESS_KEY_SECRET
  • PAI_REGION
  • PAI_WORKSPACE_ID

Output Rules

Always preserve provenance:

  • source file or evaluator
  • model identifier
  • task name
  • timestamp
  • normalization decisions

Examples And References

  • examples/USAGE_EXAMPLES.md
  • examples/example_readme_tables.md
  • examples/metric_mapping.json

Guardrails

  • Never fabricate benchmark values.
  • Never merge incompatible units into one score field.
  • Never overwrite existing scores without an explicit merge rule.
  • Prefer dry-run style extraction before mutating repository content.

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