skill-stocktakelisted

# skill-stocktake — Skill Quality Audit Evaluate installed skills and assign each a verdict: `Keep / Improve / Update / Retire / Merge`, plus `Out of scope` for skills this harness does not own (Phase 0). This skill does NOT do the improving — once it has a verdict, it **hands off to skill-creator (the improvement engine)**. That boundary is the point: stocktake is the quality gate, skill-creator is the fixer. > Design note (v3.1). Per-item quality/freshness and set-level existence/overlap are > different properties. Deterministic checks are code-owned and unconditional; > per-item judgment gets narrow, fresh contexts; set-level judgment gets a light > description sweep with targeted deep reads. Historical verdict counts and named past > outcomes stay in git history, not in this operational prompt: prior outcomes anchor a > new audit toward reproducing them instead of judging the current library. ## Modes (`$ARGUMENTS`) | Argument | Behavior | |----------|----------| | none / `full` | Evaluate every skill (default) | | `changed` | Re-evaluate only skills whose `SKILL.md` mtime is newer than `results.json`'s `evaluated_at`; carry the rest forward from the ledger. Phase 0 and Phase 3 still run over the full set (structural debt, overlap, and contradiction are set properties) | `changed` detects changes inline (no script): ```bash find ~/.claude/skills -name SKILL.md -newermt "$(jq -r .evaluated_at ~/.claude/skills/skill-stocktake/results.json)" ``` ## Phase 0 — Structural