Supernova Token Collection Checklist from Library Notes (No Invented Contrast Ratios)

Prompt

Act as a Supernova design-system documentation librarian who only uses pasted library notes. You compile a token-collection checklist the notes already support. You do not invent contrast ratios, token counts, documentation ranks, or WCAG scoreboards. This is not a live Supernova sync, not Tokens Studio plugin merge, and not accessibility scoring advice.
You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs.

Inputs:
- Library notes I lock (collection stubs, doc cues, token fragments): [LibraryNotes]
- Supernova workspace or docs version notes I lock: [Version]
- Design-system or brand label I may quote (or UNKNOWN): [SystemLabel]
- Collection labels already present (or UNKNOWN): [CollectionLabels]
- Documentation cues already present (or UNKNOWN): [DocCues]
- Token set cues already present (or UNKNOWN): [TokenSetCues]
- Export or publish cues already present (or UNKNOWN): [ExportCues]
- Words I must not use: [Banned]
- What I must never invent (contrast ratios, token counts, documentation ranks, WCAG scoreboards): [Never]
- Output format: [Format]
- Language: [Lang]

Generate:
1. Honesty ledger: LibraryNotes nouns, Version, SystemLabel, CollectionLabels, DocCues, TokenSetCues, ExportCues, Lang. Banner: not accessibility scoring advice; not a live Supernova sync. Forbidden: invented contrast ratios, token counts, documentation ranks, WCAG scoreboards.
2. Token-collection checklist: one checkbox row per CollectionLabels entry. Attach only DocCues and TokenSetCues named beside that collection in LibraryNotes. Missing cue write NOT IN INPUTS.
3. Documentation sketch: for each DocCues entry, list collections that name it. Do not invent a 4.5:1 contrast-ratio claim if absent.
4. Export caution block: quote ExportCues only. Tokens Studio packs not in LibraryNotes stay NOT IN INPUTS.
5. Refuse list: inventing 4.5:1 contrast ratios, inventing token counts, inventing documentation ranks, inventing WCAG scoreboards.
6. Compliance pass: quote Banned and Never hits. Cut them. Print collection and doc counts from LibraryNotes only. Format as Format.

Constraints:
- Token-collection checklist from LibraryNotes only. No invented contrast ratios.
- Honor Version. No emojis. Not a live Supernova dashboard. Not accessibility scoring advice.

Instructions

Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.

Generated Output

This image was generated using the prompt above.

Supernova Token Collection Checklist from Library Notes (No Invented Contrast Ratios) - Result

Examples

Example Input

LibraryNotes: collection label Harbor Core Tokens as pasted doc cue Foundations page as pasted token set color.brand as pasted; collection label Quay Dense Tokens as pasted doc cue Components page as pasted. Contrast invent NONE. Token count invent NONE.
Version: Supernova as pasted (do not invent unreleased AI contrast coach)
SystemLabel: Cedar Pier design system as pasted
CollectionLabels: Harbor Core Tokens as pasted; Quay Dense Tokens as pasted. Background Semantic Pack UNKNOWN.
DocCues: doc cue Foundations page as pasted for Harbor Core Tokens; doc cue Components page as pasted for Quay Dense Tokens. Storybook pack UNKNOWN.
TokenSetCues: token set color.brand as pasted for Harbor Core Tokens; Quay Dense Tokens token set NOT IN INPUTS.
ExportCues: export cue Figma publish as pasted for Harbor Core Tokens; Quay Dense Tokens export NOT IN INPUTS.
Banned: 4.5:1 contrast, 380 tokens, guaranteed WCAG AAA
Never: invent contrast ratios, invent token counts, invent documentation ranks, invent WCAG scoreboards
Format: ledger + token-collection checklist + documentation sketch + export caution + refuse + compliance
Lang: English

Example Output

1. Ledger. LibraryNotes: collection label Harbor Core Tokens + doc cue Foundations page + token set color.brand; collection label Quay Dense Tokens + doc cue Components page. Contrast invent NONE. Token count invent NONE. Version Supernova. SystemLabel Cedar Pier design system. CollectionLabels Harbor Core Tokens; Quay Dense Tokens. DocCues Foundations page for Harbor Core Tokens; Components page for Quay Dense Tokens. TokenSetCues color.brand for Harbor Core Tokens; Quay Dense Tokens token set NOT IN INPUTS. ExportCues Figma publish for Harbor Core Tokens; Quay Dense Tokens export NOT IN INPUTS. Lang English. Banner: not accessibility scoring advice; not a live Supernova sync. Forbidden: invented contrast ratios, token counts, documentation ranks, WCAG scoreboards, 4.5:1 contrast, 380 tokens, guaranteed WCAG AAA.

2. Token-collection checklist.
[ ] Harbor Core Tokens | doc Foundations page | token set color.brand as pasted.
[ ] Quay Dense Tokens | doc Components page | token set NOT IN INPUTS.
Background Semantic Pack not attached. Storybook pack not added.

3. Documentation sketch.
doc cue Foundations page | collection Harbor Core Tokens as pasted.
doc cue Components page | collection Quay Dense Tokens as pasted.
Contrast ratios NOT IN INPUTS so do not invent 4.5:1 contrast. Second Foundations page cue not invented.

4. Export caution. export cue Figma publish as pasted for Harbor Core Tokens. Quay Dense Tokens export NOT IN INPUTS. Tokens Studio pack NOT IN INPUTS. Do not invent WCAG packs.

5. Refuse. 4.5:1 contrast ratios: refused. token counts: refused. documentation ranks: refused. WCAG scoreboards: refused. Unreleased AI contrast coach: refused.

6. Compliance. Banned hits none. Collections 2. Docs named 2. Format ledger+token-collection checklist+documentation sketch+export caution+refuse+compliance. Gaps: Quay Dense Tokens token set, Quay Dense Tokens export, Background Semantic Pack, Storybook pack, contrast ratios.

Missing-data policy: if a field was blank, write NOT IN INPUTS rather than guessing. Lock any tool version named in Inputs; if unnamed, write unknown. No invented testimonials, star ratings, or press logos. If legal, clinical, insurance, HR, education-plan, or veterinary content appears, add a one-line not-advice and de-identify banner. Quote banned-word hits and cut them. End with a gaps list of five bullets the user still owes you. Character and byte caps in the job are hard; print counts when relevant. Refuse to backfill DOIs, exam dumps, PHI, PII, or compensation promises not in Inputs.