gza

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.

Diagnose why a gza task failed — analyzes logs, detects loops, checks diffs, compares baselines, and suggests fixes

Synthesize operator triage guidance from failed-task history, unimplemented plan and explore work, unmerged branches, and queue state

Create a well-formed gza task with appropriate type, tags, and prompt

Compatibility wrapper that routes task resumption to first-class gza CLI resume/run-inline workflows

Rebase current branch onto the requested target branch, with interactive conflict resolution. Use when rebasing, merging, or resolving git conflicts.

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

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.

Run an interactive quality gate for a plan task and produce a go or no-go recommendation before implementation

Review documentation for accuracy, completeness, and missing information that users may need

Review all spec files for accuracy against the current implementation, flagging outdated vs aspirational content

Run an interactive quality gate for a spec file and produce a go or no-go recommendation before implementation

Run verify_command from gza.yaml, fix any errors found, then commit all fixes.

Comprehensive pre-release code review assessing test coverage, code duplication, and component interactions

Guide user through deliberate task creation with clarification and refinement before running gza add

Gather comprehensive info about a specific gza task including status, branch, commits, and logs

Analyze gza run logs to find recurring anti-patterns, wasted effort, and suggest AGENTS.md or workflow improvements

Summarize an explore task, extract the important findings, and suggest concrete next steps

Refine a draft plan by asking targeted questions, resolving gaps, and rewriting it into an implementation-ready plan

Compatibility wrapper that routes inline task execution to the first-class gza run-inline command