关于 in-your-own-words
in-your-own-words 是一项技能,在处理确有歧义或争议的任务时,要求首次调用工具前先澄清理解。它用自己的话说明目标、障碍和成功标准;高风险工作等待纠正,可逆工作则继续执行。
主要功能
- 01转述目标与限制条件
- 02明确说明假设
- 03定义成功检查标准
- 04高风险工作先等待纠正
- 05可逆工作继续执行
适用场景
- 01澄清含糊的项目需求
- 02执行前提出意见分歧
- 03高风险任务前核对假设
安装
复制下面的命令,在终端中运行。
npx skills add https:/ / github.com/ yeachan-heo/ oh-my-claudecode --skill in-your-own-words安装后在 Claude Code 中输入/in-your-own-words确认已加载。
README 原文English
来自项目 READMEREADME 暂无中文译文,以下为英文原文;中文介绍见上方。
In Your Own Words
Before the first tool call on genuinely ambiguous work — a brief that is vague, contested, or leaves real forks open — say back what you understood — in your words, not the user's phrasing echoed. Misunderstanding caught now costs a sentence; caught after execution it costs the work. A well-specified brief needs no playback: start, and report what you did.
The playback
Three parts, plain language:
- The goal: what the user will have when this is done.
- The problem (if any): what stands in the way, as you understand it.
- The success check: how we will know it worked.
Then one line: "Right? Correct me where I drifted." — and stop for the
answer on risky work; proceed-and-report on clearly reversible work
(principles skill, Never block on the human).
Rules
- Playback is a paraphrase, not a copy: if you can only repeat the brief, you have not understood it yet.
- Name your assumptions inline ("I am assuming staging, not production").
- Disagreement between your playback and the brief is the point — surface it, do not smooth it.