Optimize the pr-management skill family

[potiuk]

Part of #1342 — apply the setup-family optimization recipe to the pr-management family.

8 skills, 53,477 body tokens in total; 7 over the 200-token always-on budget, 6 over the 5,000-token body budget.

skill	body tokens (budget 5,000)	always-on tokens, est. (budget 200)	lines (cap 500)
pr-management-triage	11,607 ⚠	~223 ⚠	968 ⚠
pr-management-code-review	8,957 ⚠	~218 ⚠	714 ⚠
pr-management-quick-merge	7,350 ⚠	~315 ⚠	549 ⚠
pr-stale-sweep	6,726 ⚠	~224 ⚠	621 ⚠
reviewer-routing	5,194 ⚠	~236 ⚠	532 ⚠
pre-first-pr-check	3,450	~247 ⚠	342
pr-management-mentor	2,980	~244 ⚠	258
pr-management-stats	7,213 ⚠	~152	439

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.