Hassan Reveals His Daily App Development Workflow: Six Steps from Voice Prompt to Screen Recording Acceptance
English text is being prepared.
Hassan revealed his own six-step daily workflow for building apps: use WisprFlow to record a 1–5 minute voice prompt, add screenshots or Inspo MCP as visual references, use the grill-me skill to have the Agent proactively ask clarifying questions, after getting v1 continue to send feedback and design tweaks, require a quick screen recording to verify each new feature before merging the PR, and if satisfied post it to X, otherwise discard it. His harness mixes Claude Code with Opus 5.5 (high) and OpenCode with DeepSeek V4.1 Flash / GLM 5.3, and connects the Agent to Vercel and GitHub CLI, Together skills, and design/animation skills.
Why read this
AI score 70
The original text strings together voice prompts, clarifying follow-up questions, and screen recording acceptance into a reusable six-step process, and lists the specific tool combinations.
Topics
View original postHow 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
View original
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
Body
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）