菜单
Break a large, parallelizable goal into bounded work units, coordinate existing agent/worktree machinery, integrate, and verify. Explicit-only.
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。
Read-only correctness review with actionable findings first, tight file/line evidence, severity, and a concise residual-risk summary.
Create or improve codewhale skills. Use when the user wants a new skill, wants to update an existing skill, or needs guidance on when a skill should be a skill versus MCP, hooks, tools, or a plugin scaffold.
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
Generate a small set of independent candidate solutions in worktrees, judge them against one explicit rubric, and apply the winner only after PASS verification.
Choose and produce an appropriate chart/dashboard/visual explanation from data, with legible encodings and source/assumption notes.
Reproduce, minimize, localize, identify root cause, and distinguish diagnosis from an authorized fix. Prefer root-cause over symptom patches.
| name | batch |
| description | Break a large, parallelizable goal into bounded work units, coordinate existing agent/worktree machinery, integrate, and verify. Explicit-only. |
| invocation | explicit-only |
Explicit-only. Do not start from ambient wording alone.
Use for large parallelizable goals that need coordinated sub-work.
