chimera skills-lifecycle

Run the measured skill-lifecycle loop (M18-4): promote proven provisionals, demote regressions. Decisions come from the store's MEASURED usage stats (never a model's self-report): a provisional skill that earns a high win rate over enough uses is promoted to active; a provisional that fails probation or an active skill whose win rate regresses is retired (kept for review). Dry-run by default; ``--apply`` closes the loop — cron it for a hands-off promote/demote cycle.

Options

--applyboolean
Actually promote/demote (default: dry-run preview).
--promote-min-usesintdefault: 5
Provisional probation length.
--promote-min-ratefloatdefault: 0.7
Win rate to promote a provisional skill.
--demote-min-usesintdefault: 5
Uses before a skill can be demoted.
--demote-max-ratefloatdefault: 0.3333333333333333
Win rate at/below which a skill is demoted.