We split this skill into the rules it gives an agent

12 rules. About 0 are common, 4 are distinctive, and 8 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.

• 8

  Very specific

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

• Common
• Distinctive
• Very specific

1. Distinctive:

   Use this skill for prompt components and Markdown rendering code.

   line 8
2. Distinctive:

   Prefer JSX-MD components over inline Markdown strings.

   line 19
3. Very specific:

   Use lowercase XML intrinsics for structured LLM prompt sections such as <context>, <instructions>, and <examples>.

   line 20
4. Very specific:

   Use Md only as an escape hatch for genuinely undecomposable Markdown.

   line 21
5. Very specific:

   Use Codeblock for fenced code and let it choose a safe fence length.

   line 23
6. Very specific:

   Keep render() deterministic and synchronous.

   line 24
7. Very specific:

   Do not introduce React or DOM runtime assumptions into jsx-md.

   line 25
8. Distinctive:

   Use context only for cross-cutting rendering state, not arbitrary global state.

   line 26
9. Very specific:

   Use {...} only when JSX syntax requires it, such as backticks, braces, <, >, or apostrophes inside the text.

   line 31
10. Distinctive:

    Keep XML attributes primitive and serializable.

    line 32
11. Very specific:

    Run bun test in packages/jsx-md for renderer changes.

    line 36
12. Very specific:

    Run bun run typecheck after export, type, or JSX runtime changes.

    line 37

≈ “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.