跳到正文
meng shao· @shao__meng · X·· 2 小时前AI 评分70
AI 导读

Hassan 公开他日常用 Agent 做应用的六步工作流:用 WisprFlow 录 1–5 分钟语音作 prompt,补截图或 Inspo MCP 作视觉参考,用 grill-me skill 让 Agent 主动追问澄清,拿到 v1 后发反馈迭代,每个新功能合并 PR 前先要快速录屏验证,满意就发到 X 否则扔掉。

正文 · 原文

Hassan 把他日常做应用的工作流公开了!

语音 → 视觉参考 → 澄清问答 → v1 反馈 → 录屏验收 → 发帖或扔掉 的闭环;harness 混用 Claude Code(Opus 5.5 high) 与 OpenCode(DeepSeek V4.1 Flash / GLM 5.3),并给 Agent 接上部署/模型/设计类 CLI 与 skills。

六步工作流
· 用 @WisprFlow 录 1–5 分钟语音作 prompt,细节越多越好
· 补视觉灵感:截图,或 Inspo MCP,让 Agent 知道想要的样子
· 用 @mattpocockuk 的 grill-me skill,让 Agent 主动追问澄清,而不是一上来闷头写
· 拿到 v1 后,再发一串反馈、功能需求与设计微调(通常又是一段语音)
· 每个新功能合并 PR 前,先要一段 快速录屏,证明真能跑
· 迭代到满意再发到 X;不满意就扔掉

工具栈
· Harness:Claude Code + Opus 5.5(high);OpenCode + DeepSeek V4.1 Flash / GLM 5.3
· 给 Agent 的能力:Vercel + GitHub CLI(推代码、部署);Together skills(聊天/图像/语音模型);Design/animation skills(间距与交互指引)

引用Hassan@nutlope
How I build apps these days: 1. Record a 1-5 minute prompt with @WisprFlow The more detail, the better. 2. Add visual inspo so the agent knows what I have in mind (screenshots or Inspo MCP). 3. Use @mattpocockuk's grill-me skill to have the agent ask clarifying questions. 4. Get back a v1, then send a list of feedback, feature requests, and design tweaks (via another voice recording usually). 5. For each new feature, ask for a quick screen recording to verify it works before merging the PR. 6. Keep iterating until I'm happy, then post it on @X or throw it away. For my harness, I use a mix of Claude Code with Opus 5.5 (high) and OpenCode with DeepSeek V4.1 Flash / GLM 5.3. I also give my agents some CLIs & skills: • Vercel + GitHub CLIs so they can push code and deploy apps. • Together skills so they can use chat, image, & voice models from Together • Design/animation skills so they have guidance on spacing & interactions
在 X 查看被引用的帖子

来源:meng shao · x.com