A Single Claude Code Skill Just Hit #1 on GitHub — 27 Diagram Types

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

Source video:
- Title: A Single Claude Code Skill Just Hit #1 on GitHub — 27 Diagram Types
- URL: https://www.youtube.com/watch?v=iIrlOSA1GhQ
- Topic: Creative Automation
- My current learning frame: Pick one repetitive output you generate regularly and write a single-folder skill for it with a tight always-loaded instruction file, an on-demand reference library, and one refusal gate modeled on this repo's pre-output checklist.
- Why this matters: New playlist item from Signal Coders; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:00 / Evidence 1: "Yesterday, I published a video about the official skills repository, the format's own authors finally showing everyone how an instruction file should be written. Short bodies, trigger-loaded descriptions, push the precision into scripts, whisper instead of shout. I..."
- 1:34 / Evidence 2: "audit against the official spec, the two gates that make it good, the scripts, what happens when a skill starts refusing work, who pays, and the honest limits. Standards note, I pulled the full repository this morning and..."
- 3:08 / Evidence 3: "Yesterday, I quoted the official guidance on the description field, the metadata that lives permanently in the model's context for every skill you install. The published figure, name, and description together, around 100 words. That's the permanent text..."
- 5:06 / Evidence 4: "community skill respects. Three levels, metadata always loaded, the instruction body loaded on trigger, and bundled resources loaded only as needed with the crucial line, "Scripts can execute without loading." Most skills we've read this month are one..."
- 7:03 / Evidence 5: "named in the file, a paper tone, an ink tone, and a rust accent. And if they're unchanged, stop and ask the user. The prompt it supplies offers five options. Pull the palette from your website, extract it..."
- 11:05 / Evidence 6: "linter. Tests for the checker, not just the checker. Think about what that means. A diagram is a picture. To a screen reader, it's a blank rectangle. Unless someone did this work, and the thing enforcing it isn't..."
- 15:10 / Evidence 7: "because the two videos together make one argument I didn't expect to be making this week. Yesterday the format's authors published the reference implementation. Short bodies, pushy descriptions, precision in code, structure instead of shouting. Today, the number..."

Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule

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, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
   - answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
   - 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
   - a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
   - one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
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 "A Single Claude Code Skill Just Hit #1 on GitHub — 27 Diagram Types", not a generic Creative Automation essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.