step9-golden-test-and-fix

Orchestrate Step9 golden residential retailer tests and triage failures for the Pear Commerce API.

Updated May 15, 2026
One-click install
npx skills add https://github.com/Pear-Commerce/pear-ai-skills --skill step9-golden-test-and-fix
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: step9-golden-test-and-fix
Source: https://github.com/Pear-Commerce/pear-ai-skills/tree/main/skills/step9-golden-test-and-fix
Command: npx skills add https://github.com/Pear-Commerce/pear-ai-skills --skill step9-golden-test-and-fix

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the manual, error-prone work of orchestrating Step9 golden residential retailer tests, triaging failures, and verifying artifact parity for the Pear Commerce API codebase, which is critical for maintaining reliable retail integration functionality.

Core Features & Use Cases

  • End-to-End Test Orchestration: Runs residential Stage9 tests for eligible retailers in parallel with a 4-retailer cap, tracks run status, and manages heartbeat automation for long-running test cycles.
  • Automated Failure Triage & Fix Workflow: Classifies test failures (transport, source, artifact mismatch), enforces deterministic fix rules, and manages fixer and watchdog subagent workflows with strict regression checks.
  • Artifact Parity Verification: Performs LLM-assisted semantic comparison of same-run curls to confirm A/C artifact alignment, with special handling for transport-only blocks like captcha or IP challenges.
  • Use Case: A Pear Commerce engineer working on the api.pearcommerce.com codebase can use this Skill to automate the full final-wave Step9 test cycle for retailers like Kroger, Target, and Walmart, eliminating manual run tracking and inconsistent failure resolution.

Quick Start

Use the step9-golden-test-and-fix skill to run residential Step9 golden tests for all non-hollywoodfeed retailers, automatically triage any failures, and verify artifact curl parity for the final test wave.

Frequently Asked Questions about step9-golden-test-and-fix

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate golden test orchestration for residential retail API integrations?

You can automate residential retail API golden test orchestration by running parallel Stage9 tests for eligible retailers with automated heartbeat tracking and run status management to eliminate manual monitoring.

How does automated failure triage work for e-commerce API test cycles?

Automated failure triage classifies e-commerce API test failures by type—transport, source, or artifact mismatch—and enforces deterministic fix rules using subagent workflows with strict regression checks.

What is LLM-assisted semantic curl comparison for artifact parity verification?

LLM-assisted semantic curl comparison verifies A/C artifact alignment by analyzing same-run curls semantically, correctly skipping transport-only blocks like captcha or IP challenges to confirm parity.

Can I run cross-retailer regression testing to prevent unintended breakage in e-commerce APIs?

Yes, cross-retailer regression testing prevents unintended breakage by validating source and codegen fixes across multiple retail integrations like Kroger, Target, and Walmart during the final test wave.

What is the maximum number of retailers I can test in parallel during a Stage9 test run?

Stage9 test runs support a maximum of 4 eligible retailers running in parallel to manage workload while maintaining efficient test cycle automation for residential integrations.