Hassan Reveals His Daily App Development Workflow: Six Steps from Voice Prompt to Screen Recording Acceptance
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 · AI translation
Hassan has made public his day-to-day workflow for building apps!
A closed loop of voice → visual reference → clarifying Q&A → v1 feedback → screen-recording acceptance → post or throw away; the harness mixes Claude Code (Opus 5.5 high) with OpenCode (DeepSeek V4.1 Flash / GLM 5.3), and hooks the Agent up with deployment/model/design CLIs and skills.
Six-step workflow · Use @WisprFlow to record a 1–5 minute voice prompt, the more detail the better · Add visual inspiration: screenshots, or Inspo MCP, so the Agent knows the look you want · Use @mattpocockuk's grill-me skill to make the Agent proactively ask clarifying questions instead of just plowing ahead and writing · Once you have v1, send another round of feedback, feature requests and design tweaks (usually another voice recording) · Before merging a PR for each new feature, first require a quick screen recording proving it actually runs · Iterate until satisfied, then post to X; if not satisfied, throw it away
Tool stack · Harness: Claude Code + Opus 5.5 (high); OpenCode + DeepSeek V4.1 Flash / GLM 5.3 · Capabilities given to the Agent: Vercel + GitHub CLI (push code, deploy); Together skills (chat/image/voice models); Design/animation skills (spacing and interaction guidance)