Turn Claude Code into a Design GENIUS

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: Turn Claude Code into a Design GENIUS
- URL: https://www.youtube.com/watch?v=fVPCbCH_c1c
- Topic: Interfaces + Open Design
- My current learning frame: Connect the Mobbin and Figma MCPs to Claude Code, build a sign-up mood board for a chosen app category, then export your own draft screen and have Claude critique it against Mobbin references and decide which feedback you actually accept.
- Why this matters: New playlist item from Kyle Skelly; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:00 / Evidence 1: "In today's video, I'm going to show you guys how to turn Claude code into a master designer and a strategist. To do this, we're going to be connecting Mobbin using an MCP. And honestly, this workflow is..."
- 1:49 / Evidence 2: "show you guys how to connect it. So, if we head to mobbin.com/mcp, now installing it is quite easy. So, you can see here the setup. So, first you need a paid plan to Mobbin, and then you..."
- 3:59 / Evidence 3: "what seems to work best between all of these and why? We're going to get Claude code to think like a designer here. Are there any other non-fitness apps on Mobbin that could be additional source of inspiration..."
- 5:55 / Evidence 4: "feedback of what we've gathered here from Mobbin. Now, obviously, we haven't given it any specific info about our fitness app, what makes it different, what it's supposed to do, who the demographic is, but just as a..."
- 7:27 / Evidence 5: "the premium designs that are on Mobbin. All right, so here's when Claude Code tells me that my design sucks. So, it's pulled together some reference images from Mobbin and here's its detailed critique. The color system is..."

Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A UI critique sheet for judging whether an AI interface improves control.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Intent -> Canvas -> Artifact -> Preview -> Feedback -> Iteration
   - 3 concrete examples that apply the video idea to real agentic work
   - 2 failure modes the video helps prevent
   - a checklist I can use the next time I run Codex or Claude
   - one practical exercise with a clear done signal
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.

Quality bar:
- Make this specific to "Turn Claude Code into a Design GENIUS", not a generic Interfaces + Open Design essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.