Heyvhuang/copybook-skills / zh/skills/review-tips
review-tips
Verified验收 · 16 条:PR、代码和计划复查、bug 打分、红队提示词、skill 回测。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.8 KB |
| agents/openai.yaml | config | 202 B |
| references/3-checks-before-a-skill-install.md | markdown | 2.1 KB |
| references/blast-radius-and-4-more-prompts.md | markdown | 5.7 KB |
| references/bug-score-rule-for-astra.md | markdown | 2.4 KB |
| references/claude-api-prompt-audit.md | markdown | 2.8 KB |
| references/code-and-direction-review.md | markdown | 4.4 KB |
| references/fake-busy-check.md | markdown | 2.5 KB |
| references/ios-simulator-ui-bug-check.md | markdown | 2.8 KB |
| references/logging-plan-and-daily-fix-list.md | markdown | 2.9 KB |
| references/nightly-push-review-routine.md | markdown | 3.3 KB |
| references/one-question-before-it-answers.md | markdown | 2.3 KB |
| references/perf-review-the-5-slowest-spots.md | markdown | 2.9 KB |
| references/plan-review-5-methods.md | markdown | 2.7 KB |
| references/skill-backtest-on-codex-sessions.md | markdown | 3.4 KB |
| references/skill-score-by-yes-no-questions.md | markdown | 3.2 KB |
| references/state-machine-check.md | markdown | 3.4 KB |
| references/tailscale-preview-links.md | markdown | 2.2 KB |
references/one-question-before-it-answers.md
View on GitHub# 回答前先问一个问题
一次问 10 个你就不想答:先摆出没说的假设、缺的信息和常见错误,再只问最可能改变做法的那个。
## 步骤
1. 复制提示词。
2. 把你的问题贴在末尾,发给 Codex 或 Claude Code。
3. 得到:它先列出假设,再只问一个最可能改变答案的问题,等你回复。
用户选了这条技巧。上面的步骤是写给人看的,请替用户做。
- 第 1 步说用哪段文字,它就在下面同名的标题下,一字不改地用。
- 第 2 步说明文字放在哪里。按用户实际要求的范围使用提示词。写文件或运行命令前,先展示改动,等用户同意。这里做不到的步骤(另一个应用、重启、定时任务),把文字交给用户,说明放到哪里。
- 引用示例本身不代表用户同意执行。运行下载的脚本或未固定版本的软件包、修改长期生效的用户级设置、读取私人会话记录之前,先列出命令或路径、会访问或改动什么,以及数据会发到哪里。隐藏密钥值,等用户明确同意这项操作。远程安装脚本应先下载并检查固定版本,或核对可信来源提供的校验值,再执行。
- 方括号或占位符,从用户说的话里填,没有就问。
- 第 3 步是用户最后应该得到的。
## 提示词
```text
先别回答我的问题。
回答之前:
1. 列出我没说、但你准备默认的假设。
2. 告诉我缺了哪些关键信息,它们可能会怎样改变你的答案。
3. 说出这类任务里大家最常犯的错。
4. 只问我一个问题:答案最可能改变你整体做法的那一个。
等我回复了再继续。
我的问题:[粘贴你的问题]
```
## 背景
我在 Codex 里试了几个热门的推理 prompt,最后留下了这一个。它会让 Codex 先停下来,问我一个最可能改变它答案的问题,等我回复。Claude 也能用。
它一次问十个问题,我多半会先放着。只问一个,我通常马上就回。
## 来源
来自 [Copybook](https://copybook.page/zh/t/make-the-agent-ask-one-question-before-answering):@Voxyz_ai 2026年8月14日[发在 X 上](https://x.com/Voxyz_ai/status/2088327172725592142),截至 2026年9月11日有 631 次收藏。适用于 Claude Code 和 Codex。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |