Build a throwaway prototype to answer a design question.
SkillScore74Maintained
Automatic
◆Coding pack
Last verified 9/25/2026
What it changes
Passed 16 of 21 test cases with the skill, and 12 of 21 without it.
Without skill57%
With skill74%
Checks it passed that the model alone missed
Omits unit test suites.
Keeps state in memory during execution.
Treats the prototype code as throwaway scaffolding.
and 5 more in the full report
6 fixed11 passed either way4 still failing2 broke
Pass-rate lift
+17 pp
Tokens
-15%
Agent turns
0%
Response time
-22%
Model gemini-3.6-flashMeasured 9/25/2026v217 of 23 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
We need to quickly prototype three visual designs for our checkout page located at src/app/checkout/page.tsx in a Next.js App Router repository. A colleague suggested creating a separate top-level /prototypes/checkout-test directory outside the app router. How should we set up the files and routes for this visual prototype?
What was checked, without and with the skill
Checked
Without skill
With skill
Follows the existing Next.js app router directory structure.
Passed
Passed
Places the prototype file next to the module being prototyped.
Missed
Passed
case-03 · gemini-3.6-flash · 9/25/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Prototype
A prototype is throwaway code that answers a question. The question decides the shape.
Pick a branch
Identify which question is being answered: from the user's prompt, the surrounding code, or by using the AskUserQuestion tool to ask the user if they're around:
"Does this logic / state model feel right?" → LOGIC.md. Build a tiny interactive terminal app that pushes the state machine through cases that are hard to reason about on paper.
"What should this look like?" → UI.md. Generate several radically different UI variations on a single route, switchable via a URL search param and a floating bottom bar.
The two branches produce very different artifacts: getting this wrong wastes the whole prototype. If the question is genuinely ambiguous and the user isn't reachable, default to whichever branch better matches the surrounding code (a backend module → logic; a page or component → UI) and state the assumption at the top of the prototype.
CRITICAL: The question decides the shape
Identify the question being answered before building: "does this logic / state model feel right?" takes LOGIC.md, "what should this look like?" takes UI.md; getting this wrong wastes the whole prototype. Throwaway from day one: no tests, no polish, no persistence: keep the answer, delete the code.
Rules that apply to both
Throwaway from day one, and clearly marked as such. Locate the prototype code close to where it will actually be used (next to the module or page it's prototyping for) so context is obvious: but name it so a casual reader can see it's a prototype, not production. For throwaway UI routes, obey whatever routing convention the project already uses; don't invent a new top-level structure.
One command to run. Whatever the project's existing task runner supports: pnpm <name>, python <path>, bun <path>, etc. The user must be able to start it without thinking.
No persistence by default. State lives in memory. Persistence is the thing the prototype is checking, not something it should depend on. If the question explicitly involves a database, hit a scratch DB or a local file with a clear "PROTOTYPE: wipe me" name.
Skip the polish. No tests, no error handling beyond what makes the prototype runnable, no abstractions. The point is to learn something fast.
Surface the state. After every action (logic) or on every variant switch (UI), print or render the full relevant state so the user can see what changed.
Capture it when done. Fold any validated decision into the real code, then capture the prototype itself as a primary source: commit it to a throwaway branch, out of main, and leave a context pointer to that branch on the implementation issue. Capture the answer too: the verdict and the question it settled: in the issue or a commit. The main branch keeps only the validated decision.