poteto@poteto

人很容易掉進一個陷阱：去微管理你的 agent，而不是去修正形塑它行為的環境。 pstack 0.15.9 現在附了一個新的 /correct 技能：如果你一直因為同樣的錯誤去糾正 agent，它會找出模式，然後用架構、型別和檢查把問題修好。 我喜歡把快速湧進程式碼庫的 commit 想像成一棵盆栽，想往哪長就往哪長，長得超快。你要做的不是向混亂屈服，而是用對的限制有意識地馴服它 0.15.9 也改進了： • /architect：現在包含如何設計對 agent 友善的架構的說明 • 新增 /benchmark-checklist 技能，根據 @brendangregg 的效能基準測試清單 這裡有個 prompt，你可以丟給 grok bot，用 pstack 開始幫程式碼庫設計更好的架構： /poteto-mode 建立一個新的 Project agent 來重構並重新設計我的 repo 架構，讓它對 agent 更友善。它要同時用 /correct 和 /architect 技能翻過去的 commit，找出 agent 最常掉進的坑，不管是程式碼品質、效能還是 bug。如果相關，也可以用 /recall 技能找過去的對話當脈絡。它要做一個高層級的計畫給我審。它也應該靠做原型來回答自己的開放問題，而不是丟回給我。帶著有真實數據佐證的計畫回來找我。等我核准計畫後，用 stack 或 full autopilot playbook（問我要哪個）來執行

it's easy to fall into the trap of micromanaging your agents instead of correcting the environment that shapes its behavior. pstack 0.15.9 now ships a new /correct skill: if you keep correcting agents for the same mistakes, it finds the pattern and fixes it with architecture, types, and checks. i like to imagine that commits rapidly flowing into the codebase are like a bonsai tree rapidly growing in whatever direction it pleases. what you want to do is not to give in to the chaos, but tame it intentionally with the right constraints 0.15.9 also has improvements to: • /architect: now includes instructions on designing agent friendly architecture • a new /benchmark-checklist skill based on @brendangregg's benchmarking checklist here's a prompt you can give to grok bot to start architecting a better codebase with pstack: /poteto-mode create a new Project agent to refactor and rearchitect my repo so that our architecture is more agent friendly. it should use both the /correct and /architect skill to look through past commits and find the most common pitfalls that agents fall into, whether its with code quality, performance, or bugs. if relevant you can also use the /recall skill to find past conversations for context. it should make a high level plan for me to review. it should also answer its own open questions by prototyping rather than defer to me. come back to me with a plan backed by real data. once i approve the plan, use either the stack or full autopilot playbook (ask me which i want) to execute