agentskills.codes
SC

schema

by sdemyanovCodingSource

The definitive guide for inspecting and modifying Retriever's SQLite database schema.

DatabaseDatabase migrationsSQL

Install

mkdir -p .claude/skills/schema-sdemyanov && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11476" && unzip -o skill.zip -d .claude/skills/schema-sdemyanov && rm skill.zip

Installs to .claude/skills/schema-sdemyanov

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use this skill when creating, inspecting, or migrating Retriever's SQLite schema. It is the source of truth for table layouts, path rules, custom field registry behavior, manual field locks, and schema-version behavior.
219 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • →Inspect SQLite table definitions.
  • →Manage schema migrations.
  • →Handle relative path rules for documents and previews.
  • →Register custom field entries.
  • →Manage manual-value overwrite protection rules.

How it works

This skill acts as the source of truth for Retriever's SQLite schema, providing rules and guidelines for table definitions, migrations, and field management. It operates under `retriever:routing`.

Inputs & outputs

You give it
User intent related to Retriever's SQLite schema.
You get back
Information about table layouts, path rules, custom field registry, or schema version.

When to use schema

  • →Verify current schema version
  • →Apply idempotent database migrations
  • →Register custom fields in the registry
  • →Inspect table layouts and storage rules

About this skill

Operates under retriever:routing. If the user's intent actually fits a different tier — another retriever:* skill, a Tier 2 slash, a Tier 3 tools.py subcommand, or (last resort) direct DB access — stop and re-route against the ladder before continuing.

Retriever Schema

Use this skill whenever a task touches:

  • SQLite table definitions
  • schema migrations
  • relative path rules
  • preview records
  • chunk storage
  • custom field registry entries
  • manual-value overwrite protection rules
  • structured filter validation rules

Required references

  1. Treat ../tool-template/src/10_core.py, ../tool-template/src/40_schema_runtime.py, and the generated ../tool-template/tools.py as the current source of truth.
  2. Use python3 skills/tool-template/tools.py schema-version to confirm the current schema_version and tool_version.
  3. Read schema.md for background terminology only; if it conflicts with the source fragments or schema-version, the code wins.

Rules

  • Do not invent new table names when an existing table fits the need.
  • Keep document paths relative to the workspace root.
  • Keep preview paths relative to .retriever/.
  • Preserve manual edits by locking corrected document fields until explicitly overwritten.
  • Prefer structured filter contracts over raw SQL filter strings.
  • Make migrations idempotent.
  • Prefer additive schema changes over destructive rewrites.

When not to use it

  • →When the user's intent fits a different `retriever:*` skill.
  • →When the user's intent fits a Tier 2 slash command.
  • →When the user's intent fits a Tier 3 `tools.py` subcommand or direct DB access.

Limitations

  • →The skill does not invent new table names.
  • →The skill keeps document paths relative to the workspace root.
  • →The skill keeps preview paths relative to `.retriever/`.

How it compares

This skill provides a structured approach to managing Retriever's schema, ensuring consistency and adherence to defined rules, unlike ad-hoc database modifications.

Compared to similar skills

schema side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
schema (this skill)02moNo flagsIntermediate
drizzle-orm322moNo flagsIntermediate
database-design66moReviewIntermediate
prisma-expert126moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

drizzle-orm

EpicenterHQ

Drizzle ORM patterns for type branding and custom types. Use when working with Drizzle column definitions, branded types, or custom type conversions.

32190

database-design

davila7

Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.

648

prisma-expert

davila7

Prisma ORM expert for schema design, migrations, query optimization, relations modeling, and database operations. Use PROACTIVELY for Prisma schema issues, migration problems, query performance, relation design, or database connection issues.

1234

database-schema-designer

davila7

Design robust, scalable database schemas for SQL and NoSQL databases. Provides normalization guidelines, indexing strategies, migration patterns, constraint design, and performance optimization. Ensures data integrity, query performance, and maintainable data models.

628

database-migration

wshobson

Execute database migrations across ORMs and platforms with zero-downtime strategies, data transformation, and rollback procedures. Use when migrating databases, changing schemas, performing data transformations, or implementing zero-downtime deployment strategies.

324

database-migrations-sql-migrations

sickn33

SQL database migrations with zero-downtime strategies for PostgreSQL, MySQL, SQL Server

318

Search skills

Search the agent skills registry