菜单
Six-dimension code review of the current branch's diff against main. Delegates to the code-reviewer agent for the actual review and reports findings.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Write comprehensive tests using project conventions: AAA pattern, edge-case checklist, httpx.MockTransport, conftest fixtures, parametrize where it reads better than copy-paste.
Audit Prefab UI card builders (`build_*_ui` in `katana_mcp_server/src/katana_mcp/tools/prefab_ui.py`) for user-centric content: real names over IDs, no redundant text dumps, named helpers over ad-hoc rendering. Reports findings; does not modify code. Use when reviewing card UX or after touching `prefab_ui.py`.
Groom the Rolling Backlog (project #5) by reading current state and proposing diffs — not re-deriving the queue from scratch. Surfaces drift between issue state and project status, missing classification, and stale priorities. Asks per-category confirmation before mutating the board.
Quick pre-flight validation of staged and unstaged changes before committing. Lighter than the verifier/code-reviewer agents — focuses on catching common mistakes in the current changeset.
Scan editable code for tech debt, anti-patterns, and improvement opportunities across 5 categories. Reports findings; the code-modernizer agent applies fixes.
Open a PR for the current feature branch — self-review the diff, organize commits, push, create the PR, wait for CI and review, then address feedback. Use when implementation is complete and ready for review.
| name | review |
| description | Six-dimension code review of the current branch's diff against main. Delegates to the code-reviewer agent for the actual review and reports findings. |
| allowed-tools | ["Read","Grep","Glob","Bash(git diff *)","Bash(git log *)","Bash(git show *)","Bash(uv run poe check)"] |
Full review of branch changes for correctness, security, design, and Katana conventions.
code-modernizer agent to actively rewrite.uv run poe check only to confirm green; don't second-guess linters.The code-reviewer agent (.claude/agents/code-reviewer.md) covers:
data envelope, spec/pydantic regen, help resource)Spawn it via the Agent tool with subagent_type: code-reviewer.
uv run poe check
If it doesn't pass, surface the failures as [BLOCKING] issues.
If the review reveals a pattern worth codifying (new anti-pattern, missing convention, pitfall), update CLAUDE.md so future work benefits.
LSP findReferences (or git grep) and read each caller. Diff-only review misses ripple effects.code-reviewer agent — does the actual reviewverifier agent — mechanical gate (passes/fails, no design opinions)pr-preparer agent — process readiness (coverage, ADRs, help resource)/open-pr skill — runs review automatically before opening PR