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:

   When comparing images, use the same checklist for every image.

   line 30
2. Distinctive:

   Use the image viewer or native vision capability available in Codex, Hermes, or Claude.

   line 35
3. Distinctive:

   Use an external OCR or vision service only when the user approves it and the required credentials are already configured.

   line 37
4. Distinctive:

   Do not infer sensitive identity, health, ethnicity, or exact location without reliable evidence and a legitimate user request.

   line 42
5. Distinctive:

   Do not claim that an object, logo, person, or place is certain when the image only supports a tentative match.

   line 44
6. Distinctive:

   Never upload a private image to an external service without user approval.

   line 46

≈ “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.