Menu
Compatibility wrapper that routes inline task execution to the first-class gza run-inline command
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
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.
Run an interactive code-only review for a gza task's implementation branch and produce structured review output compatible with gza-task-improve
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.
Check the behavior spec set for coherence, ownership boundaries, and plain-language discipline without editing the spec or the code
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 row by its clearing action (drop moot/dead/stale, spawn follow-up, hand review-loop rows to /gza-task-fix), then ranks and files `system`-tagged prevention fixes by blast radius (cascade-preventer first). Never merges, retries, resumes, deletes branches, or edits code.
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.
| name | gza-task-run |
| description | Compatibility wrapper that routes inline task execution to the first-class gza run-inline command |
| allowed-tools | Bash(uv run:*), AskUserQuestion |
| version | 3.0.0 |
| public | true |
Use the first-class runner command instead of reconstructing lifecycle behavior in this skill.
Require a full prefixed task ID (for example, gza-1234).
If no task ID is provided, list pending tasks and ask which one to run:
uv run gza next
Run the task with run-inline:
uv run gza run-inline <TASK_ID>
Optional flags (only when the user explicitly requests them):
uv run gza run-inline <TASK_ID> --resume
uv run gza run-inline <TASK_ID> --no-docker
uv run gza run-inline <TASK_ID> --max-turns <N>
uv run gza run-inline <TASK_ID> --force
Report the command exit status and tell the user to use gza log <TASK_ID> if they want full runner/provider logs.
run-inline is runner-managed task execution (prompt building, worktree setup, provider launch, status transitions, artifacts, and provenance).