一键导入
simplify
Use when user wants a pre-review cleanup pass on changed code by running parallel reviews for reuse, code quality, and efficiency, then applying worthwhile fixes without changing behavior.
菜单
Use when user wants a pre-review cleanup pass on changed code by running parallel reviews for reuse, code quality, and efficiency, then applying worthwhile fixes without changing behavior.
Forces exhaustive problem-solving using corporate PUA rhetoric and structured debugging methodology. MUST trigger when: (1) any task has failed 2+ times or you're stuck in a loop tweaking the same approach; (2) you're about to say 'I cannot', suggest the user do something manually, or blame the environment without verifying; (3) you catch yourself being passive — not searching, not reading source, not verifying, just waiting for instructions; (4) user expresses frustration in ANY form: 'try harder', 'stop giving up', 'figure it out', 'why isn't this working', 'again???', '換個方法', '為什麼還不行', '你再試試', '加油', '你怎麼又失敗了', or any similar sentiment even if phrased differently. Also trigger when facing complex multi-step debugging, environment issues, config problems, or deployment failures where giving up early is tempting. Applies to ALL task types: code, config, research, writing, deployment, infrastructure, API integration. Do NOT trigger on first-attempt failures or when a known fix is already executing successfully
Forces exhaustive problem-solving with corporate PUA rhetoric. Trigger on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '換個方法', '為什麼還不行'). ALL task types. Not for first failures.
| name | simplify |
| description | Use when user wants a pre-review cleanup pass on changed code by running parallel reviews for reuse, code quality, and efficiency, then applying worthwhile fixes without changing behavior. |
Use this as a pre-review cleanup gate. The goal is not formal approval; it is to inspect changed code for reuse opportunities, code quality issues, and efficiency issues, then fix the worthwhile findings without changing behavior.
/simplify-style cleanup pass before reviewer or code-reviewerDo not use this skill for:
Recommended placement:
implement -> simplify -> code-reviewer and/or reviewer -> receiving-code-review
Skip the full three-agent pass when:
git diff HEAD so both staged and unstaged changes are includedgit diffAGENTS.md, repo conventions, and any relevant skillsFor medium or large diffs, spawn three read-only subagents in parallel in a single round. Use explorer agents when possible because this is codebase analysis, not implementation.
Each agent must receive:
The three review domains are:
Use the prompt templates in:
Important:
| Goal | Prefer | Avoid |
|---|---|---|
| Readability | Clear names, explicit branches, small coherent helpers | Dense one-liners, clever tricks |
| Scope control | Touched files, recent diff, user-specified paths | Repo-wide cleanup without request |
| Safety | Targeted verification after edits | Assuming refactor is safe |
| Comments | Intent and constraints | Narrating obvious code |
| Agent usage | Three parallel read-only reviewers, one controller applying fixes | Multiple editing agents touching the same files |
This Codex skill adapts the /simplify flow used in Claude-based workflows into a Codex-native skill. See references/upstream-agent.md for the source notes and adaptation details.