What does the Dev-tool API reference with try-it pane prompt produce?

A devtools website with Endpoint cards, Try-it pane, Changelog rail, Auth section. The vibe target is "developer-calm, precise, searchable" and the prompt body is printed in full on the page.

How well does it score?

91% average fidelity over 4 recorded runs. Best model: Claude 4.6 Sonnet. Weakest recorded run: 90% on GLM-4.6 (CN).

Are failures included?

No build failures are recorded for this prompt, and the log says so rather than implying every model succeeded elsewhere.

Concept render — composed live from this prompt's palette & layout. Reproducible with the library, not a stock screenshot.

Concept scene: Star Motes — open in library →

DevToolsFeaturedby Motif Studiopublished 2026-09-09

Dev-tool API reference with try-it pane

vibe: developer-calm, precise, searchable

advanced — 4 blocks, 3 stacks≈ 700 tokens to run (estimate)

prompt.txt — copy-paste ready

A developer-tool API reference page — documentation that treats every endpoint as a first-class card.
• Shell: left sidebar with grouped methods (Auth, Keys, Events) and a live filter; content column with a sticky mini-TOC on wide screens.
• Endpoint card anatomy: method chip + path in mono, one-line summary, request/response tabs in code blocks with a copy button, and a 'try it' affordance that opens a sandbox pane showing the exact request the card documents.
• Try-it pane: a small form (path params, auth token input, 'Send') that renders the JSON response — the demo can mock the reply, but the interaction must feel real.
• Auth section: API-key explanation in plain sentences with a reveal toggle, never a wall of jargon.
• Changelog rail: version bumps with deprecation warnings styled louder than new features.
• Typography: mono for code only; prose at a comfortable measure; every status code shown with its meaning, not just its number.

Stacks shipped:Next.jsHTMLReactBlocks:Endpoint cardsTry-it paneChangelog railAuth section

Community:▶ Re-run this prompt ⤴ Submit a remix of it ★ Your saved listRe-runs are a labelled simulation; the run log on this page is the real record.

⚠ Before you run it, know this

Lowest score was GLM-4.6 (CN) at 90/100 — Strong structure; sidebar depth wanted one more collapse level.
All models built cleanly on the first pass.