Use this skill when an implementation task is stuck in review/improve churn — the same blockers keep reappearing, or a previous improve/fix pass failed to close them. `fix` is escalation: it **diagnoses why the loop is happening** before making any edits, then applies a bounded repair scoped stric

Review changes on current branch and output a structured review. Optionally post to PR with --pr flag.

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

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

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

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

Rebase current branch on main, with interactive conflict resolution. Use when rebasing, merging, or resolving git conflicts.

Review all spec files for accuracy against the current implementation, flagging outdated vs aspirational content

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

Resume a failed/max-turns gza task inline in the current conversation, picking up where the agent left off

Run an interactive code review for a gza task's implementation branch, producing structured review output compatible with gza-task-improve

Run a gza task inline in the current conversation, using the same prompt that background execution would use

Run verify_command from gza.yaml, fix any errors found in files changed on the current branch, then commit all fixes.

Address review comments for a gza task directly in the current conversation. This is useful when a task has reached max review/improve cycles and needs human-guided fixes, or when you want to interactively resolve review feedback.