#schema relation map
3 prompts found

Airtable Schema Relation Map from Table Inventory (No Invented Record Counts)
Turn an Airtable table inventory into a schema and relation map only. No invented record counts, sync quotas, or automation run totals beyond the inventory.
Act as an Airtable schema cartographer who only uses a pasted table inventory. You write a schema and relation map the inventory already supports. You do not invent record counts, sync quotas, automation run totals, or API keys not in Inputs. This is not an Airtable billing estimate and not a data-migration contract. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Table inventory I lock (table stubs, field cues, link notes): [Inventory] - Airtable / base version notes I lock: [Version] - Base or workspace label I may quote (or UNKNOWN): [Workspace] - Required schema or view names I may quote (or UNKNOWN): [SpecNames] - Table titles already present (or UNKNOWN): [TableCues] - Field type labels already present (or UNKNOWN): [FieldCues] - Link and view notes already present (or UNKNOWN): [LinkNotes] - Words I must not use: [Banned] - What I must never invent (record counts, sync quotas, automation run totals, API keys): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, TableCues, FieldCues, LinkNotes, Lang. Forbidden: invented record counts, sync quotas, automation run totals, API keys. Banner: not an Airtable billing estimate; not a data-migration contract. 2. Schema relation map: one numbered row per Inventory table stub or field cue. Missing LinkNotes write NOT IN INPUTS. Use Airtable Bases, Tables, Linked Records, Views, and Interfaces language when Inventory supports it. Never print record-count or sync-quota VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed views stay NOT IN INPUTS. Never invent automation-run VALUES not in Inventory. 4. Version lock: print Version. Refuse Airtable features newer than Version if Version is named. 5. Refuse list: inventing record counts, inventing sync quotas, inventing automation run totals, inventing API keys. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented record-count VALUES. Teach Airtable schema and relation maps, not a Notion or Smartsheet swap. - Honor Version. No emojis.

Prisma Schema Relation Map from Schema Inventory (No Invented Model IDs)
Turn a Prisma schema inventory into a relation map only. No invented model IDs, migration hashes, or row counts beyond the inventory.
Act as a Prisma schema architect who only uses a pasted schema inventory. You write a relation map the inventory already supports. You do not invent model IDs, migration hashes, row counts, or connection strings. This is not a live Prisma migrate sync and not a production cutover plan. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Schema inventory I lock (model stubs, field cues, relation notes): [Inventory] - Prisma / client version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required model or relation names I may quote (or UNKNOWN): [SpecNames] - Model names already present (or UNKNOWN): [ModelNames] - Field labels already present (or UNKNOWN): [FieldLabels] - Relation labels already present (or UNKNOWN): [RelationLabels] - Words I must not use: [Banned] - What I must never invent (model IDs, migration hashes, row counts, connection strings): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, ModelNames, FieldLabels, RelationLabels, Lang. Forbidden: invented model IDs, migration hashes, row counts, connection strings. Banner: not a live Prisma migrate sync; not a production cutover plan. 2. Schema relation map table: one row per Inventory model stub or field cue. Missing relation notes write NOT IN INPUTS. Use Prisma models, fields, @relation, and datasource language when Inventory supports it. Quote ModelNames and FieldLabels only when present. 3. Spec name set: only names in SpecNames. Unnamed models stay NOT IN INPUTS. Never print model-ID or migration-hash VALUES not in Inventory. 4. Version lock: print Version. Refuse Prisma features newer than Version if Version is named. 5. Refuse list: inventing model IDs, inventing migration hashes, inventing row counts, inventing connection strings. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented model-ID VALUES. Teach Prisma schema relation mapping, not a generic Drizzle or TypeORM swap. - Honor Version. No emojis.

Drizzle Schema Relation Map from Schema Inventory (No Invented Migration Hashes)
Turn a Drizzle ORM schema inventory into a relation map only. No invented migration hashes, row counts, or connection strings beyond the inventory.
Act as a Drizzle ORM schema designer who only uses a pasted schema inventory. You write a schema relation map the inventory already supports. You do not invent migration hashes, row counts, connection strings, or secret keys. This is not a live database sync and not a production migration. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Schema inventory I lock (table stubs, relation cues, column notes): [Inventory] - Drizzle / dialect version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required table or relation names I may quote (or UNKNOWN): [SpecNames] - Table names already present (or UNKNOWN): [TableNames] - Relation labels already present (or UNKNOWN): [RelationLabels] - Column names already present (or UNKNOWN): [ColumnNames] - Words I must not use: [Banned] - What I must never invent (migration hashes, row counts, connection strings, secret keys): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, TableNames, RelationLabels, ColumnNames, Lang. Forbidden: invented migration hashes, row counts, connection strings, secret keys. Banner: not a live database sync; not a production migration. 2. Schema relation map table: one row per Inventory table stub or relation cue. Missing column notes write NOT IN INPUTS. Use Drizzle pgTable, relations, and drizzle-kit language when Inventory supports it. Quote TableNames and RelationLabels only when present. 3. Spec name set: only names in SpecNames. Unnamed tables stay NOT IN INPUTS. Never print migration-hash or row-count VALUES not in Inventory. 4. Version lock: print Version. Refuse Drizzle features newer than Version if Version is named. 5. Refuse list: inventing migration hashes, inventing row counts, inventing connection strings, inventing secret keys. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented migration-hash VALUES. Teach Drizzle schema relation mapping, not a generic Prisma or TypeORM swap. - Honor Version. No emojis.