Loading...
Loading...
Found 76 Skills
Monitorar e manter a documentação completa da persistência em .specsfy/DATABASE.md, com inventário tabular de bancos, schemas, tabelas, campos, relações e migrations. Use quando o monitor de contexto apontar persistência pendente, sempre que banco, tabela, coleção, model persistente, coluna, índice, relação, schema ou migration for criado ou alterado, e ao auditar se o mapa de dados corresponde ao código. Preserva notas e decisões humanas fora do inventário detectado.
Authoring, building, validating, and running PostgreSQL database migrations with the @schemavaults/dbh package. Use when a project depends on @schemavaults/dbh and you are creating or editing Kysely migration files, setting up a migrations/ directory, or when the user mentions migrations, up()/down(), schema changes, or the dbh CLI's migrate / build-db-migrations / validate-migration-directory commands.
PostgreSQL database helper. Use when writing SQL queries, exploring schema, or working with the database.
Generate database migration scripts with rollback support for various databases. Use when creating schema migrations or database changes.
Plans and executes safe Prisma schema migrations with data backfills, rollback strategies, and SQL preview. Handles complex schema changes including data transformations. Use for "Prisma migrations", "schema changes", "database migrations", or "data backfills".
Expert in Drizzle ORM for TypeScript — schema design, relational queries, migrations, and serverless database integration. Use when building type-safe database layers with Drizzle.
Postgres schema and query rules, independent of the calling language. TRIGGER — load BEFORE writing or editing a .sql file, a migration, or any schema, index, constraint or query change against Postgres: new tables, foreign keys, status columns, claim or lease queries, backfills, ON CONFLICT upserts. SKIP for MySQL, SQLite and other engines, and for code that never touches SQL.
Create and manage Dexie/IndexedDB repositories with type-safe interfaces, converters, and standardized CRUD operations. Use when (1) adding entity storage, (2) implementing save/load/delete operations, (3) designing database schema and indexes, (4) converting between database (Db*) and domain types, (5) handling database errors or migrations, (6) using existing repositories (SettingsRepository, WorkoutsRepository, TemplatesRepository, CustomExercisesRepository, BenchmarksRepository, ActiveWorkoutRepository). Triggers include "database", "repository", "save data", "fetch from database", "delete from storage", "database schema", "database table", "indexes", "migration", "persist", "convert workout", "converter", "buildPartialUpdate", "mock repository", "database error", "bulk operations", "import/export", or specific repository names.
Postgres-backed observability and policy store for the skill system. Provides tables for policy profiles (effect allowlists), skill execution runs, and step-level events. Use when setting up the skill system database or querying execution history.
Use when a project's house style already exists somewhere and needs to become something the tooling can check - the developer hands over a standards document, points at an older or company base schema whose naming should be adopted, says "our team does it this way", or asks why an apply preview warned about a name. Derives the patterns from the real schema, verifies them against it, and writes .pythia/conventions.json and conventions.md.
Use this skill when you need to alter the PocketBase database schema - creating, updating, or deleting collections. Never write migration SQL by hand.
Design a Lark Base for the user's business through a guided interview: find the one unit of work the business repeats, then derive the tables, links, formulas and a phased build order from the numbers the owner actually wants to see. Ends with a Base Blueprint document plus an acceptance test, ready to hand to whoever builds it. Use when the user wants a database designed for their business ("design my Lark Base", "what tables do I need", "help me build a database for my company", "帮我设计多维表格", "我的业务要怎么建表"), when their existing base has become one giant table and they want it restructured, or when they are unsure whether something should be a field, a select, or its own table. NOT for physically building or editing a Base via API or lark-cli (this skill produces the blueprint; building is a separate job), NOT for turning an already-filled database into reports or dashboards (that is breakthrough-database-to-dashboard), and NOT for setting up a second-brain vault (that is my-second-brain, installed separately).