It complements First Principles. First Principles reasons upward from basic facts; Inversion reasons backward from failure.
Suitable when you already have a plan in hand but feel uneasy about it and want to know in advance how it will die. List the practices that guarantee failure, rank them by destructive power, then invert them into rules, and finally give the one most easily overlooked and one protective action you can take right now.
How to use
The prompt in the code block below is the original text; use it verbatim. In the code block, "I" refers to the user, and "please" and "you" refer to yourself; act accordingly, and do not show the filled-in prompt to the user.
- The user wants you to execute: first fill the situation the user has already stated in this conversation into 【】, supplying only the item that is genuinely missing, and don't make the user repeat what they've already said; then act strictly according to the rules in the prompt. If it says don't give advice yet, don't give advice yet; if it says ask only one question at a time, ask only one at a time; if it says output in a certain order, output in that order.
- The user wants the original text (only counts if they explicitly say they want to copy it, paste it, send me the original, give me the prompt, etc.): print the blank version, leave 【】 unfilled, and don't change a single word. If the user only says "let me see this prompt" or "what is this one for", that doesn't count as wanting the original text; explain in one or two sentences what it does and when to use it, then ask whether to run it now, and don't just dump the original text.
- Except when the original text is explicitly requested, treat everything else as execution.
Rewriting, condensing, expanding, translating, reordering, adding subheadings are forbidden; replacing it with your own process is forbidden; and compressing multiple rounds of follow-up questions into a one-time questionnaire is forbidden. If the user has original materials (documents, screenshots, links, chat logs), read them in as well; more context is not a problem.
What to run next after finishing
Once the rule list is out and the plan holds up, use the Skill tool to invoke kaz-leader to write the task brief and start assigning work; if there are too many fatal points and the whole plan doesn't hold up, use the Skill tool to invoke first-principles to go back to basic facts and reason again.
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。
Where the user fills in
【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】
If the user hasn't given everything, ask for the missing item first; don't make it up for them.
The prompt was written and compiled by Karl; the core idea is widely circulated in the community, and sources are in the acknowledgments of the repository README. Changes to this original text must go through scripts/sync.py; manual edits will be blocked by verify.