We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is 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.

• 1

  Very specific

  Tied to their project's names, files or tools. Probably skip.

• Common
• Distinctive
• Very specific

1. Distinctive:

   Run the dump script — one Bash call, do not read the files individually:

   line 17
2. Distinctive:

   Every Q&A turn (auto-load at start of conversation)

   line 29
3. Distinctive:

   When user asks "what do we know about X"

   line 30
4. Distinctive:

   Before writing memory (to avoid duplicating existing entries)

   line 31
5. Distinctive:

   Before answering — never speak from training data alone

   line 32
6. Distinctive:

   Don't read memory/*.md one file at a time — that's 12 tool calls for what the script does in one

   line 36
7. Distinctive:

   Don't paraphrase — use the raw markdown so citations stay verbatim

   line 38
8. Distinctive:

   Don't filter by relevance — let the agent decide what to use

   line 39
9. Very specific:

   Don't fetch sources/ — that's for ingest-source, not for normal Q&A

   line 40

≈ “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.