Check the implementation against the behavior specs in specs/behavior/. Reports where the code diverges from intended behavior — each divergence is either a code bug or a spec gap. The behavior spec is the source of truth; this skill never edits code or the spec.
Review changes on current branch and output a structured review. Optionally post to PR with --pr flag, or apply non-blocking follow-ups inline with --apply-followups.
Turn the recurring watch stuck-task pile into (1) a diagnosis of why each class is stuck, (2) the existing stuck rows actually cleared now, and (3) systemic prevention so it does not recur. Snapshots watch/incomplete/queue, buckets stuck tasks by failure class, dedups against already-tracked system work, unsticks each…
Rescue a stuck gza task inline — diagnoses review/improve churn, verifies each blocker against current code, addresses the open ones, runs verify, and commits. Runs entirely in Claude Code, no background worker.
Address feedback for a gza task inline — reads review findings and/or unresolved comments, checks out the branch, fixes must-fix items and comments, runs verify, and commits.
Triage gza incomplete rows — classify each unresolved merge-unit lineage and recommend the right corrective action (drop moot leaves, escalate to fix, surface manual-resolve rebases, etc.). Never merges, retries, resumes, or deletes branches; never edits code.
★not rated 12
changed todayA61 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: