Test Generation with Claude Code: API Runtime Pattern
A production playbook for test generation in cross-industry operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: QA and developer productivity teams
The problem
QA and developer productivity teams need test generation to run repeatedly against source files, fixtures, failing traces, and acceptance criteria. 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 test generation instructions as a skill, send source files, fixtures, failing traces, and acceptance criteria 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 test generation, 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=test-generation
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo