gza-test-and-fix
Run verify_command from gza.yaml, fix any errors found, then commit all fixes.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Run verify_command from gza.yaml, fix any errors found, then commit all fixes.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional 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-test-and-fix |
| description | Run verify_command from gza.yaml, fix any errors found, then commit all fixes. |
| allowed-tools | Read, Edit, Glob, Grep, Bash(uv run:*), Bash(git:*) |
| version | 3.0.0 |
| public | true |
Run the project's verify_command (from gza.yaml), fix any errors, and commit all fixes.
Read verify_command directly from gza.yaml and note inner_verify_command if present. If uv run gza config is available in this environment, you may use it as an optional confirmation or to inspect merged config, but do not treat gza config failure as an error when gza.yaml was readable. If verify_command is empty or not set in gza.yaml, stop and tell the user to set verify_command in gza.yaml.
Repeat up to 3 times:
Important: Run the full verify_command each iteration. Do NOT filter or skip test files. All errors and failures are relevant. Fix the root cause in the source, not the test.
If errors remain after 3 iterations, report them to the user.
If any files were modified during Step 2:
Run git status and git diff --name-only to see what changed.
Stage the modified files with git add <file> for each file (do not use git add -A).
If there are uncommitted changes already on the current branch, include your fixes in a single new commit on top (do NOT amend someone else's work). If the working tree was clean before you started (no prior uncommitted work), your fixes form a fresh new commit.
Commit with a descriptive message summarising what was fixed, e.g.:
Fix mypy and pytest errors
- Fixed type errors in src/foo/bar.py
- Fixed failing test in tests/test_bar.py
If no files were modified, report that no fixes were needed.
git push — leave pushing to the user.