ETL Error Diagnosis with Claude Code: Result JSON Schema

A production playbook for ETL error diagnosis in cross-industry operations using Claude Code: result json schema, run-scoped inputs, logs, typed results, and artifacts.

Audience: Data platform teams

The problem

Data platform teams need ETL error diagnosis to run repeatedly against pipeline logs, schemas, samples, and freshness checks. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.

Implementation path

Define the outer result contract once, let the ETL error diagnosis skill own body.data, and reject terminal output that does not match the expected schema.

Tradeoffs and failure modes

Schema enforcement adds upfront design work, but removes prompt parsing from the product surface. For ETL error diagnosis, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.

Result shape

{
  "schema_version": "argo.result.v1",
  "summary": "ETL error diagnosis completed",
  "body": { "type": "etl_error_diagnosis", "data": {}, "exceptions": [] },
  "artifacts": []
}

Run this on Argo