How to Write Sanity Schema Types from a Content Brief
Sanity specs invent a production dataset and a fake Studio navbar. The brief named card with heading, image, and summary. Body NOT IN INPUTS.
The matching generator is the Sanity Schema Types from a Content Brief (No Fake UI Screenshots) (Sanity Schema Types From A Content Brief No Fake Ui Screenshots) 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).
Lock schema fields before you name a type
Write Sanity schema types from a content brief. No fake UI screenshots or invented slugs. 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:
Content brief I lock (type names, fields I allow): [Brief]
Dataset I lock (or UNKNOWN): [Dataset]
Sanity API version I lock (or UNKNOWN): [Version]
Words I must not use: [Banned]
What I must never invent (slugs, extra fields, fake UI screenshots): [Never]
Output format: [Format]
Language: [Lang]
Portable Text fields I allow (or NONE): [Rich]
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.
Define fields only from the content brief
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 types and fields, Dataset, Version, Rich, Lang. Forbidden: invented slugs, extra fields, fake UI.
- Field table: each field in Brief quoted with type if Brief named a type. Types not listed stay TYPE UNKNOWN.
- Schema: defineType only from Brief. defineField only from Brief. Dataset from Dataset or DATASET UNKNOWN.
- Portable Text: quote Rich or write NONE. Do not add a body field if Brief omitted it.
- Refuse list: Contentful content-type JSON, Strapi schema.json, Webflow CMS dump, screenshot mockups, invented /blog slugs.
- Version: quote Version or write VERSION UNKNOWN.
- Never: do not draw a fake Studio navbar. Do not invent slug.current values.
- Compliance pass: quote Banned and Never hits. Cut them. 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 Contentful dumps and screenshot mocks
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:
- Sanity schema from Brief only. Not Contentful and not a screenshot.
- Never invent slugs, extra fields, or fake UI.
- Portable Text only if pasted.
- 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.
Keep Portable Text NONE if the brief omitted it
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 (sanity schema types, content brief lock, no fake ui screenshots) 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.