We split this skill into the rules it gives an agent

11 rules. About 0 are common, 8 are distinctive, and 3 are 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.

• 3

  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 to create or curate a dataset and describes the requirement in natural language.

   line 8
2. Distinctive:

   Default to the closest of:

   line 16
3. Distinctive:

   Run SQL-based inspection only after a stable snapshot exists.

   line 35
4. Very specific:

   If split names are missing, prefer train, validation, test.

   line 40
5. Very specific:

   If schema is ambiguous, preserve raw columns and choose custom instead of forcing the wrong template.

   line 41
6. Distinctive:

   If metadata is missing, keep placeholders separate from row data.

   line 42
7. Very specific:

   Use MODELSCOPE_API_TOKEN or a prior modelscope login session for publish steps.

   line 53
8. Distinctive:

   Never force the user into a verbose dataset-writing template.

   line 57
9. Distinctive:

   Never upload private or unlicensed data by default.

   line 58
10. Distinctive:

    Never mutate rows before validating the intended schema.

    line 59
11. Distinctive:

    Keep raw and normalized outputs separate.

    line 60

≈ “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.