skill-reviewlisted

# Skill Review Skill Operationalizes `spec/claude/skill-review/` — reviews one Claude Code skill against its authoring specs and persists the result as a processable plan under `.audits/skill-review/`. The plan is the deliverable; the skill is the procedure that produces and, later, retires it. ## German trigger phrases This skill also triggers on equivalent German-language requests, including: - "prüfe diesen Skill" - "Skill-Review für X" - "Audit von skills/" - "ist dieser Skill spec-konform" - "schließe den Skill-Review-Plan" ## Why this is a skill, not an agent - **Mid-flow interactivity** — scope confirmation (which skill, narrowed aspect?) and item-closure decisions happen with the user in the loop; an agent's fire-and-forget contract would lose that. - **Persistent on-disk output is the contract** — the `review-plan` artifact under `.audits/` must survive past the current turn and be worked off incrementally; skills own persistent state, agents return structured reports. - **Orchestrator of specs + (potentially) dispatches agents** — this skill may chain to `pull-request-create` in the same thread after the plan is closed; the skill-orchestrates-agent-executes pattern (see `skill-vs-agent`) defaults the orchestrator to skill form. - Counter-dimension considered: *context-window impact* from reading three specs plus the target skill would bias toward an agent, but the read volume is bounded (each spec is one file, the target skill is one folder) and the user wants