0xSago retweeted
翻了一下最近两个月,我用Agent干活最爱说的几句Prompt:
1. 从第一性原理出发,找到最本质原因,修复一下。
2. 先问一些不清晰的问题,对齐我的喜好,然后再出3版方案。
3.不要默认我提出的问题定义就是正确的。你先分析我真正想解决的底层需求,判断我有没有把症状误认为原因、把手段误认为目标。如果存在更值得解决的问题,直接指出来
4. 不要只考虑这个改动产生的直接效果。继续推演它的二阶、三阶影响,尤其关注对其他模块、用户行为、系统复杂度和长期维护成本的潜在影响。
5. 其他领域里有没有类似的方案,用跨领域的方式全面思考,找到最优解。
6. 先假设你当前认为最合理的方案是错误的。站在最强反对者的角度,寻找能够推翻它的证据、反例和边界情况。然后重新评估方案,看看有没有更好的解法。
7. 深入分析整个代码库的 Git 历史、关键 PR 和架构演变过程。找出哪些设计是有意为之,哪些是历史遗留,哪些是为了解决已经不存在的问题而引入的。识别可以安全移除的历史包袱。
8. 假设明天有一个完全不了解项目、但是能力很强的工程师来接手。请评估他理解整个项目需要付出的认知成本,找出那些命名混乱、抽象过度、职责不清晰、需要大量上下文才能理解的代码,并提出简化方案。
9. 全面分析最近XX天里的所有的PR,找出最慢的那几个,看看有没有导致卡顿、可以优化的地方。
10. 全面复盘最近XX时间的 Bug、返工、回滚和重复修改。不要只统计发生了什么,要分析这些问题背后有没有共同的根因。把能够预防的共性问题沉淀成项目规则、自动化或者Skill,避免我们反复支付同样的成本。
0xSago retweeted
最近给组里做了一次 AI 开发分享,顺手整理成了文章。
写了我平时怎么用 Codex、Claude,常用哪些 Skill 和提示词,怎么让 Agent 自己测试,以及最后我怎么 Review。
欢迎大家分享自己的见解~
0xSago retweeted
The whitelist checker is now live 🟨
Not on the list yet? We’ve only just started, and reviews are ongoing.
→ Take your time with the questions, submit your application, and share it on X. Every application is reviewed individually.
fungolabs.org/checker
0xSago retweeted
Introducing SNURPS by Catapult Trade
4,444 NFTs · Mint Date: September 30
catapult.trade/snurps
code: 4444
72 hours to get in
0xSago retweeted
Codex 和 Claude Code 天天被吹,但真有人把它们的源码开放平替做出来了,我上手翻了下 iPolloWork 的仓库,说说它到底不一样在哪。
它最狠的一点:不光帮你写代码,还能把活干完,而且结果能接着改。
1️⃣ 写代码,读懂仓库、规划、执行、检查一条龙
2️⃣ 办公,文档表格幻灯片直接出,不是甩你一段文字
3️⃣ 设计,网站幻灯片生成完在画布上原位改字换图调颜色
4️⃣ 视频,内置 Studio 加时间线直接剪
本地优先,Mac、Windows、Linux 都能跑,暂时没 Release,得自己拉源码。
个人用免费,3 人以上得先拿书面授权,这条别踩。
🔗 github.com/Devin-AXIS/iPollo…
0xSago retweeted
As engineering, product, design, DS, etc. melt into a new kind of role, I was reflecting on what roles might look like in the future. For example, when I look at the Claude Code team I see what I think is five archetypes:
1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship
2. Builder: quickly turns a prototype/idea into production-grade product/infra
3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance
4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit
5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales
Many people span across 2 roles, and sometimes 3 roles. I also notice that these roles are not really tied to job function -- eg. across Anthropic, some designers match category 1, some 2, some 3; same for engineers, PM, DS.
A healthy team needs a mix of these, depending on the product:
- A product that is new and pre-PMF needs people that are strong at 1+2+3
- A product that is growing and has found PMF needs 2+3+4 and some 5
- A product that has strong PMF needs 3+4+5 and some 2
Maybe product roles of the future will look more like this, and less like the domain-specific roles of today?
























