We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

• ≈0

  Common · estimate

  Many files like this have a rule of this kind.

• ≈9

  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:

   Run the bounded review/fix orchestration without replacing source-skill rules.

   line 8
2. Distinctive:

   Follow each source skill for its local operation and use this skill only for ordering and pass accounting.

   line 17
3. Distinctive:

   Run at most three review/fix passes.

   line 22
4. Distinctive:

   Use all-findings mode for CRITICAL, MAJOR, MINOR, and NIT.

   line 23
5. Distinctive:

   Run an all-findings review and record its review id, head, and validated finding count.

   line 30
6. Distinctive:

   If the count is zero, stop clean.

   line 32
7. Distinctive:

   Run brutal-pr-finding-fixer continuously in all-severity mode.

   line 33
8. Distinctive:

   Stop when the fixer made no code-changing commit, no generated occurrence was actionable, a hard guard blocked, or pass three completed.

   line 34
9. Distinctive:

   If fixes were pushed and fewer than three passes ran, refresh the head and repeat.

   line 36

≈ “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.