twining-semantic-review

# Twining Semantic Review — LLM-Judged Staleness Deterministic staleness (`twining_housekeeping` with `staleness_review: true`) catches orphans-by-structure: the scope path is gone, affected files deleted, branch removed. It cannot catch entries that are structurally intact but reference *concepts* the project has moved past — "Wave 3 review action items", "HMS Lancaster compliance", a sprint that closed a year ago. A future agent finding those will go looking for concepts that don't exist and hallucinate explanations. This skill puts the judging model — you — in that loop. **You are the LLM; no API key, no server-side model call, no cost beyond this session.** Nothing is archived without explicit user confirmation. ## When to Invoke - The user asks for a semantic review, deep cleanup, or "are any of these entries still relevant?" - After a milestone/version ships and its planning vocabulary is retired - Deterministic housekeeping reports clean but `twining_status` shows a large, old entry population Never run this as a side effect of another task. It is opt-in by design. ## Workflow ### 1. Ground yourself in what is CURRENT Before judging anything, build the "still alive" picture: - `git branch --list` and the current branch — active lines of work - `README.md` / project docs headline — what the project is now - `twining_status` — entry counts, current phase if tracked - The 10 most recent blackboard entries — today's working vocabulary ### 2. Load review candidate...