Optimize the release-management skill family

[potiuk]

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

10 skills, 73,971 body tokens in total; 4 over the 200-token always-on budget, 8 over the 5,000-token body budget.

skill	body tokens (budget 5,000)	always-on tokens, est. (budget 200)	lines (cap 500)
release-rc-cut	11,865 ⚠	~274 ⚠	931 ⚠
release-prepare	10,908 ⚠	~400 ⚠	991 ⚠
release-verify-rc	10,802 ⚠	~323 ⚠	967 ⚠
release-keys-sync	4,868	~204 ⚠	438
release-promote	6,968 ⚠	~180	560 ⚠
release-vote-draft	6,745 ⚠	~169	572 ⚠
release-announce-draft	5,976 ⚠	~188	534 ⚠
release-audit-report	5,697 ⚠	~164	518 ⚠
release-vote-tally	5,617 ⚠	~182	557 ⚠
release-archive-sweep	4,525	~183	429

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.