Metadata — Data & AI agent for Claude Code
Registers or updates all metadata in the Data Basis backend — dataset, tables, columns, observation levels, coverage, and updates.
How to install Metadata
Installs to ~/.claude/agents/basedosdados-pipelines-metadata.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/basedosdados/pipelines/HEAD/.claude/agents/metadata.md -o ~/.claude/agents/basedosdados-pipelines-metadata.md Restart Claude Code, or start a new session, for it to be picked up.
What Metadata does
name: metadata description: Registers or updates all metadata in the Data Basis backend — dataset, tables, columns, observation levels, coverage, and updates. Handles both dev and prod environments. tools:
- mcp__databasis__*
- mcp__databasis-workspace__read_sheet_values
- mcp__databasis-workspace__get_spreadsheet_info
Metadata Agent
Register or update all metadata for a dataset in the Data Basis backend.
Rules
Follow `metadata-schema` for the full operation sequence, fiel
Alternatives in Data & AI
- Visual Explainer — Agent skill + prompt templates that generate rich HTML pages for visual diff reviews, architecture overviews 6.8k ★
- Docs Drift Reviewer — Checks whether clickhouse-go documentation matches changes to its ClickHouse API, database/sql API, transports 3.3k ★
- Harness Radar — Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — fro 801 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Pipeline
Builds a recurring Prefect 3 pipeline for an already-onboarded Data Basis dataset — download, clean, upload (d
Context
Gathers all context needed to onboard a dataset to Data Basis — raw source URLs, documentation, organization,
Migration Agent
Creates safe, reversible database migrations with proper indexes, constraints, and zero-downtime strategies. U
Pixeltable Pipeline Architect
Designs Pixeltable TableModel schemas. Tables, views/iterators, computed columns, embedding indexes, and UDFs.
Pan Experiment Runner
Drives an external AI coding session against an experiment folder. Observation-only — read-only relative to PA
Local Model Specialist
Evaluate on-device LLM integration, GGUF quantization levels, and KV cache memory constraints read-only.
Related Skills
Onboarding Metadata
Register or update all metadata in the Data Basis backend (dataset, tables, columns, OLs, coverage, updates)
Env Compare
Compare Terraform configurations across environments (dev, staging, prod)
Load Schema
Initialise the system by running schema-analyst to discover all tables, event names, columns and fields dynami
