brainstorming with claude by making it ask questions using the AskUserQuestion tool is indeed a very convenient experience. i really like using it with a custom plugin i made out of this prompt by jesse
kudos to the cc ux team
Prompts to use with Fable 5.2 to improve your codebase.
1/ Full health check. from Alex Albert,Anthropic
Read this entire project and find everything that's broken, inconsistent, inefficient, or no longer needed. Fix what you're sure about and list the rest for me to review.
2/ Simplify by cutting the superfluous. from Anthony Riera
I want you to audit our codebase, is anything here unnecessary, overly complicated in our
current setup, or based on weak assumptions? Challenge them. #1 What can be deleted entirely? #2 What can be simplified now that unnecessary pieces are gone? Then make the changes. Prefer deleting over simplifying, simplifying over optimizing, and optimizing over automating. This product is being used by thousands of customers, do not cut any corners.
3/ Find the implicit state machine. from Steve Ruiz and Kun Chen and RicardoSawir
audit and find implicit state machines in this <codebase/directory/module> that would drive
concrete improvements if made explicit. fewer words, big visuals
or with consider for UX/DX/AX.
Find all of the implicit state machines in my app (there are probably a ton). Make the best decision that will elevate all three: the user experience (UX), developer experience (DX), and agent experience (AX) always, without breaking anything. Also, make state machines explicit.
4/ Review agent configuration. from WquGuru & Vox
Review my entire agent setup: AGENTS.md, CLAUDE.md, skills, commands, subagents, hooks, settings/permissions, and MCP servers. Check for gaps in guardrails and whether it follows current best practices for Fable 5.2.
5/ shadcn/improve
run https://t.co/qoRSy4zk73 for my codebase.
强烈推荐所有用 Claude Code、Codex 写项目的人,这周抽一个晚上把这句提示词跑一遍,
Anthropic 的 Alex Albert 说,每次出新模型,他都拿同一句提示词把所有项目过一遍,截至今晚 现在,这条帖子 76 万浏览、1.4 万多收藏,收藏差不多是点赞的两倍。
原文就一句话:
"Read this entire project and find everything that's broken, inconsistent, inefficient, or no longer needed. Fix what you're sure about and list the rest for me to review."
可直接复制的中文版(中文为翻译):
“通读整个项目,找出所有坏掉的、不一致的、低效的、已经不需要的东西。你有把握的就修掉,其余的列出来给我审。”
很多人以为让 AI 大扫除,就是放手让它全面重构,改得越多越好,
但最关键的是后半句:把“有把握的”和“拿不准的”分成两堆,前一堆它动手,后一堆你拍板。
就好比请保洁上门,明显的垃圾直接扔,抽屉里拿不准的东西先摆桌上,等你回来认。
这才是精髓。
新手跑之前,先做这三步:
1️⃣ 先开一个新分支,或者至少 commit 一次,改坏了随时能退回去,
2️⃣ 项目没写测试的,第一次只让它列清单、不改代码,
3️⃣ 盯着额度,这周 Pro 用户最多能拿 50% 的周额度跑 Fable 5.2(到 11 月 17 日 15:59),但官方帮助中心写明了,Fable 比其他 Claude 模型更耗用量。
第 2 步可以用这个安全版,是我加的,不是 Alex 的原话:
“通读整个项目,找出所有坏掉的、不一致的、低效的、已经不需要的东西,全部列成清单,每条标上你有几成把握。这一轮先不要改任何代码。”
这对编程新手和带团队的老板都是个实在的提醒:新模型到手,先拿它体检自己的老项目,比盯着跑分靠谱。
但这里一定要留个清醒,
“有把握”是模型自己判断的,没有测试兜底,它眼里“不再需要”的代码,可能正是你当初留的保险,
原帖回复区就有人吐槽,几个小时就把一周的额度用光了。
新模型到手,第一件事从来不是写新功能,而是先给老项目做一次体检。