MCPInstall

inversion

逆向法提示语原文。用户担心方案有坑、想提前排雷、做风险预案、检验计划健壮性时使用。触发词包括 逆向法、怎么会失败、提前排雷、风险预案、什么会出错、怎么才能搞砸、反面思考、inversion、防护措施、保证失败。产出保证失败的做法清单、翻转后的规则、最容易被忽视的那条和一个立刻能做的防护动作。跟第一性原理互补:第一性原理往下挖回本质重推,逆向法从失败往回推找防线。

Installs
224
Last 24h
+8
Trending rank
#9753
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/learnprompt/laoyeye --skill inversion
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads inversion automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

逆向法

跟第一性原理互补。第一性原理从基本事实往上推,逆向法从失败往回推。

适合手上已经有一个方案、但心里不踏实,想提前知道它会怎么死。列出保证失败的做法,按破坏力排序,再翻转成规则,最后给一条最容易被忽视的和一个立刻能做的防护动作。

怎么用

下面代码块里的提示语是原文,逐字使用。代码块里的「我」指用户,「请你」「你」指你自己,照它做事,不要把填好的提示语打给用户看。

  • 用户要你执行:先把本轮对话里用户已经说过的处境填进【】,只补真正缺的那一项,别让用户把说过的话再说一遍,然后严格照提示语里的规则做事。它说先别给建议就先别给,说一次只问一个问题就一次只问一个,说按顺序输出就按那个顺序输出。
  • 用户要原文(明确说要复制、要粘贴、发我原文、给我提示语这类话才算):打空白版,【】保持不填,一个字不改。用户只是说「看看这条提示语」「这条是干嘛的」,不算要原文,用一两句说清它干什么、什么时候用,再问要不要现在跑,别直接倒原文。
  • 除了明确要原文的情况,其余一律当执行处理。

禁止改写、精简、扩写、翻译、重排、加小标题,禁止把它替换成你自己的流程,也禁止把多轮追问压缩成一次性问卷。用户手上有原始材料(文档、截图、链接、聊天记录)就一并读进来,上下文多不是问题。

跑完接哪条

规则清单出来了、方案站得住,用 Skill 工具唤起 kaz-leader 写任务书开始派活;致命点太多、整个方案站不住,用 Skill 工具唤起 first-principles 回到基本事实重推。

我要评估的计划/方案/决策是:【填写你正在推进或打算推进的计划、方案或决策,写清目标和现状】。

请用逆向法帮我检验它的健壮性。

第一步,列出 5 到 7 个如果想让这件事保证失败的做法。每条要足够具体,不要写泛泛的「不努力」「没计划」,要写成一个能照着执行就一定会把事搞砸的操作。

第二步,按破坏力从大到小排序,说明每条为什么能致命。

第三步,把每条翻转过来,变成一条必须遵守的规则。翻转要具体到能检查、能执行,不要变成「注意 XX」这种空话。

最后请输出:
1. 翻转后的规则清单,按优先级排列;
2. 这些规则里最容易被忽视的那一条,以及它为什么容易被忽视;
3. 一个现在就能做的防护动作。

用户要填的位置

  • 【填写你正在推进或打算推进的计划、方案或决策,写清目标和现状】

用户没给全就先问缺的那一条,别自己替他编。


提示语由卡尔编写收录,核心思路广泛流传于社区,出处见仓库 README 的致谢。改动这段原文要走 scripts/sync.py,手改会被 verify 拦下。

FAQ

What does the inversion skill do?

逆向法提示语原文。用户担心方案有坑、想提前排雷、做风险预案、检验计划健壮性时使用。触发词包括 逆向法、怎么会失败、提前排雷、风险预案、什么会出错、怎么才能搞砸、反面思考、inversion、防护措施、保证失败。产出保证失败的做法清单、翻转后的规则、最容易被忽视的那条和一个立刻能做的防护动作。跟第一性原理互补:第一性原理往下挖回本质重推,逆向法从失败往回推找防线。

How do I install inversion?

Run npx skills add https://github.com/learnprompt/laoyeye --skill inversion in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/inversion/ (personal) or .claude/skills/inversion/ (project).

Which AI agents can use inversion?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is inversion safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains inversion?

It is published by learnprompt in learnprompt/laoyeye. It has 224 recorded installs.

More from learnprompt/laoyeye

View all →

laoyeye

learnprompt/laoyeye

Open the skill to read its SKILL.md instructions.

230 installs

fact-check

learnprompt/laoyeye

Open the skill to read its SKILL.md instructions.

229 installs

minimum-experiment

learnprompt/laoyeye

最小实验提示语原文。用户纠结的事情靠继续想已经不会更清楚、需要用现实反馈来验证时使用。触发词包括 最小实验、先试试、怎么验证、别空想了、跑个实验、小成本试错、七天验证、已经反复纠结过很多轮、想了很久还是选不出来。产出待验证假设、一个低成本可逆实验的完整设计,以及明天就能做的第一个动作。

229 installs

steelman-both-sides

learnprompt/laoyeye

Open the skill to read its SKILL.md instructions.

228 installs

cross-domain-borrow

learnprompt/laoyeye

Open the skill to read its SKILL.md instructions.

228 installs

socratic-inquiry

learnprompt/laoyeye

Open the skill to read its SKILL.md instructions.

228 installs

Popular other skills

View category →

hyperframes-cli

heygen-com/hyperframes

The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.

1.3M installs

triage

mattpocock/skills

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

1M installs

ask-matt

mattpocock/skills

Ask which skill or flow fits your situation. A router over the skills in this repo.

778.4K installs

to-questionnaire

mattpocock/skills

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

508.9K installs

wait-what

mattpocock/skills

Stop. That last message did not land: re-pitch it.

459.7K installs

loop-me

mattpocock/skills

Grill me about specs for the workflows I want to build, within this workspace.

447.9K installs