How to Build Tokens Studio DTCG JSON from a Figma Variable Brief
Token JSON invents #0A84FF and a brand mark. Quote every hex from the brief. If a collection is unnamed, write COLLECTION UNKNOWN.
The matching generator is the Tokens Studio DTCG JSON from a Figma Variable Brief (No Invented Brand Logos) (Tokens Studio Dtcg Json From Figma Variable Brief No Invented 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).
Quote every token name and value from the brief
Write Tokens Studio W3C DTCG JSON from a Figma variable brief. No invented hex values or brand logos. 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:
Figma variable brief (names, values I lock, modes I allow): [Brief]
Token sets I allow: [Sets]
DTCG types I allow: [Types or color dimension]
Words I must not use: [Banned]
What I must never invent (hex, logos, extra modes): [Never]
Output format: [Format]
Language for comments: [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.
Use only collections listed in Inputs
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:
- Honesty ledger: Brief names, Sets, Types, Lang, Max. Forbidden: invented hex, invented logos, extra modes.
- Set map: each Sets line to a JSON file or OTHER leftover.
- JSON body: DTCG objects with $type and $value from Brief only. Stay at or under Max tokens.
- Modes: only modes named in Brief. If a dark value is missing, write VALUE UNKNOWN rather than inverting.
- Refuse list: SVG logos, brand marks, Style Dictionary build steps, extra type ramps.
- Types: only Types. Do not add typography unless listed.
- Never: do not invent #0A84FF if Brief did not lock it.
- Compliance pass: quote Banned and Never hits. Cut them. Count tokens vs Max. 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 hex values 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:
- Tokens Studio DTCG JSON from Brief. Not a generic scale pack and not a logo sheet.
- Never invent hex values, logos, or extra modes.
- 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.
Print token count against the max
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 (tokens studio dtcg json, figma variable brief tokens, no invented brand logos) 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.