Home/Blog/How to Build a Design Token JSON Pack from a Scale Brief
Blog

How to Build a Design Token JSON Pack from a Scale Brief

P
promptstudio
How to Build a Design Token JSON Pack from a Scale Brief

Token packs invent accent hex. Values only from the scale brief.

The matching generator is the Design Token JSON Pack from a Scale Brief (No Invented Brand Logos) (Design Token Json Pack From Scale Brief No Invented Brand Logos) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).

Map every token name to a value or NOT IN INPUTS

Build a design-token JSON pack from a pasted scale brief. Never invent brand logos, hex values, or typefaces not in Inputs. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.

Paste these fields before you hit run:

Scale brief (token names and values): [Brief]
Token format I lock: [FormatSpec or DTCG JSON]
Color space I lock (or UNKNOWN): [Space]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Max tokens: [Max]

That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.

Emit JSON only for named values

Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.

Walk the Generate list in order:

  1. Honesty ledger: brief token count, FormatSpec, Space status, Lang, Max. Forbidden: invented hex, logos, typefaces.
  2. Token map: each name/value present or NOT IN INPUTS.
  3. JSON pack: up to Max tokens in FormatSpec. Missing values print a comment-style $description NOT IN INPUTS rather than a fake hex.
  4. Group list: color/spacing/type groups only if named in Brief.
  5. Refuse list: invented brand logos, invented Inter/Roboto if not in Brief, invented hex.
  6. Diff notes: Banned/Never cuts.
  7. Space note: quote Space or unknown.
  8. Compliance pass: Banned/Never hits. Token count vs Max. Gaps list of five. Format as Format.

If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.

Refuse invented typefaces and logos

Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.

Honor the constraints as hard stops, not vibes:

  • Token JSON from Brief only. Not a logo lockup and not fake UI.
  • Never invent hex, typefaces, or brand logos.
  • Stay at or under Max tokens.
  • No emojis.

When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.

Lock color space from Inputs

Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.

Tags on the card (design token json, no invented brand logos, token scale brief) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.

Fill the card, then run

Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.