We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

• ≈0

  Common · estimate

  Many files like this have a rule of this kind.

• ≈4

  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 for paginated search results, tables, product lists, article lists, or infinite-scroll pages where an API is not available.

   line 15
2. Very specific:

   After each page, call wait_for for the list area or a short timeout, then capture another snapshot.

   line 32
3. Very specific:

   Stop at max_pages, no next control, duplicate page content, or a user requested stopping condition.

   line 34
4. Distinctive:

   If a CAPTCHA, login wall, or consent wall blocks scraping, stop and report it.

   line 40
5. Distinctive:

   If selectors are unstable, return the current URL/title and a screenshot so the flow can be adjusted.

   line 41
6. Very specific:

   Never bypass site controls outside browser automation.

   line 46
7. Distinctive:

   Never scrape credentials, cookies, hidden auth tokens, or private profile data unless the user explicitly owns the session and requested …

   line 47

≈ “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.