Schema Mapping with Claude Code: API Runtime Pattern
A production playbook for schema mapping in cross-industry operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Data integration teams
The problem
Data integration teams need schema mapping to run repeatedly against source schemas, target schemas, samples, and transform rules. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the schema mapping instructions as a skill, send source schemas, target schemas, samples, and transform rules as run-scoped inputs, execute with Claude Code, poll terminal status, and consume argo.result.v1 instead of parsing a transcript.
Tradeoffs and failure modes
The API boundary forces the workflow to define inputs, terminal states, and result shape before customers depend on it. For schema mapping, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Run request
POST /api/skills/<skill_id>/run
provider=claude-code
workflow=schema-mapping
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo