Optimize the repo-health skill family

[potiuk]

Part of #1342 — apply the setup-family optimization recipe to the repo-health family.

7 skills, 26,554 body tokens in total; 5 over the 200-token always-on budget, 2 over the 5,000-token body budget.

skill	body tokens (budget 5,000)	always-on tokens, est. (budget 200)	lines (cap 500)
dependency-license-audit	5,247 ⚠	~249 ⚠	522 ⚠
audit-finding-fix	5,111 ⚠	~204 ⚠	516 ⚠
license-compliance-audit	4,633	~208 ⚠	426
flaky-test-triage	3,070	~204 ⚠	314
ci-runner-audit	2,203	~201 ⚠	245
workflow-security-audit	3,177	~198	343
dependency-audit	3,113	~193	325

Body tokens are from docs/mode-economics.md; always-on figures are a chars ÷ 4 estimate of description + when_to_use. ⚠ marks a budget exceeded. Line counts include the generated pre-flight block.

Order of work (per the umbrella):

1. Trim the frontmatter of every skill marked ⚠ in the always-on column.
2. Split any over-cap body, moving sub-action-specific rules into sibling files byte-for-byte.
3. Wording pass on the rest, with headings, golden-rule headlines, code blocks and the pre-flight block kept byte-identical.
4. Run each touched skill's eval suite before and after, outside the sandbox.

Record any inconsistencies found but not fixed (eval-coupled wording, stale headings) in the PR description.