Route a vague Prisma Next prompt to the right specific skill. Use for "help me with Prisma Next", "what is Prisma Next", "explain Prisma Next", "I'm new to PN", "where do I start", "what can I do with Prisma Next", "what can I do next with Prisma", "just ran createprisma", "tour of Prisma Next", "Prisma Next overview", and comparison questions like "Prisma Next vs Prisma 7", "PN vs Drizzle", "PN vs Kysely", "PN vs TypeORM". Do NOT use when the prompt clearly matches a workflow skill — adoption / quickstart / first-touch orientation / brownfield introspection, schema / contract editing, migration authoring (db update / migration plan / migrate), migration review on deploy / concurrent migrations, queries / db.orm / db.sql / TypedSQL, Supabase / RLS / role binding, runtime / db.ts / middleware wiring, build / Vite plugin / Next.js plugin, debug / structured error envelopes / PN-* error codes, or feedback / bug report / feature request — load that sibling skill directly.
npx skills add https://github.com/prisma/prisma --skill prisma-next
> Edit your data contract. Prisma handles the rest.
This skill exists to disambiguate vague Prisma Next prompts. When the user hasn't yet committed to a specific workflow (e.g. *"help me with Prisma Next"*, *"explain how Prisma Next works"*, *"I'm new to PN, where do I start?"*), this skill fires and routes them to the right specific skill.
prisma-next-quickstart.prisma-next-contract.prisma-next-migrations.prisma-next-migration-review.prisma-next-queries.asUser / asAnon / asServiceRole), auth.users FKs, @prisma-next/extension-supabase → prisma-next-supabase.db.ts, middleware, environment config → prisma-next-runtime.prisma-next-build.prisma-next-debug.prisma-next-feedback.If the user's prompt clearly matches one of the workflow skills, route there directly without asking.
Otherwise, ask one disambiguating question. Pick from:
prisma-next-quickstart (first-touch orientation path).prisma-next-quickstart.prisma-next-contract vs the others.prisma-next-migrations vs prisma-next-migration-review.db.ts and middleware at runtime?"* → prisma-next-build vs prisma-next-runtime.prisma-next-debug.prisma-next-feedback.If you still can't tell which skill applies, ask the user what they want to do. Do not guess.
Prisma Next is a contract-first data layer. You author a data contract (a contract.prisma file, or a TypeScript builder). The framework emits machine-readable artifacts (contract.json, contract.d.ts) and gives you three runtime surfaces on SQL targets: a typed SQL query builder (db.sql.from(...)), a typed ORM client (db.orm.User.select(...)), and a raw SQL escape hatch (db.sql.raw(...)). On MongoDB targets only the ORM lane exists, and its keys are collection storage names (db.orm.users) rather than PSL model names — prisma-next-queries § *MongoDB ORM addressing* covers the rule. Migrations are planned from the contract diff; you review them, optionally edit the migration.ts for data transforms, and apply.
Three steps the user does:
prisma-next-contract)prisma-next-migrations)migration.ts and execute it. (prisma-next-migrations)Everything else — queries, runtime wiring, build integration, debugging, feedback — sits on top of those three.
prisma-next-feedback.Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.
Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.
Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.
Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.
Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.
BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Use when: bullmq, bull queue, redis queue, background job, job queue.
Create custom external web service APIs for Moodle LMS. Use when implementing web services for course management, user tracking, quiz operations, or custom plugin functionality. Covers parameter validation, database operations, error handling, service registration, and Moodle coding standards.
Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.
Take prisma/prisma-next from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.