fix-todos
Analyzes the items in TODO.md and spins up subagents to address them. Use when the user asks to fix, address, or burn down todos
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。
菜单
Analyzes the items in TODO.md and spins up subagents to address them. Use when the user asks to fix, address, or burn down todos
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
Adversarial review of changes, a commit, or the whole codebase for design-discipline violations — carve-outs, test-shape pattern matching, rules that don't generalize. Use after implementing a feature or pass, before committing nontrivial changes, or when the user asks whether the code has drifted into patching.
Reviews the MLIR dialects and ensures that they are properly tested and documented. Use when the user asks to review dialects, ops, or passes
| name | fix-todos |
| description | Analyzes the items in TODO.md and spins up subagents to address them. Use when the user asks to fix, address, or burn down todos |
Fix the current set of todos:
For each todo item, spin up a subagent with the picked model so you don't pollute your context. Don't run subagents in parallel, since they will get into each others way when modifying, building, and committing files. The subagent should:
Additional instructions provided by the user: $ARGUMENTS