skills.rest
danycapo8
danycapo8COMMUNITY
Explore all skills by this author →
GitHub

golden-case-runner

Run golden-case suites against the AI Patient Simulator in staging and generate structured QA reports.

Updated Apr 23, 2026
Search Tags:#reporting#qa-testing#evidence-collection#golden-cases#patient-simulator#staging-labs
One-click install
npx skills add https://github.com/danycapo8/labs-skills --skill golden-case-runner
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: golden-case-runner
Source: https://github.com/danycapo8/labs-skills/tree/main/golden-case-runner
Command: npx skills add https://github.com/danycapo8/labs-skills --skill golden-case-runner

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill automates running approved golden-case suites against the AI Patient Simulator in a staging environment, collecting complete request/response evidence and producing a structured QA report to support validation and root-cause analysis.

Core Features & Use Cases

  • End-to-end QA orchestration: execute a suite of golden cases, capture raw evidence, and generate a consolidated report.
  • Staging-first validation: ensures tests run against the staging Labs endpoint before production release.
  • Reproducibility & traceability: retains artifacts for each case to support debugging and audit trails.

Quick Start

Provide the approved golden-case suite and a valid staging endpoint to start a regression run and generate the final QA report.

Frequently Asked Questions about golden-case-runner

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

FAQPage Schema
How do I automate golden-case QA testing against a patient simulator in staging?▼

Golden-case QA testing against a patient simulator is automated by executing approved test suites, capturing raw request/response evidence, and generating a structured report for validation and root-cause analysis.

What is the best way to collect evidence for regression testing in a staging environment?▼

Evidence collection for regression testing in staging is handled by running golden-case suites, persisting complete request and response artifacts, and evaluating them against expected results to ensure traceability.

Do I need an approved test suite to run validation against the AI Patient Simulator?▼

Yes, validation against the AI Patient Simulator requires an approved golden-case suite and a valid staging endpoint to construct payloads, execute POST requests, and generate the final QA report.

Can I reproduce reported failures using golden-case suites in staging labs?▼

Reported failures are reproduced by running the specific golden-case suites against the staging Labs endpoint, collecting the raw request and response evidence, and evaluating the outputs against expected results.

How does evidence persistence work during staging-first validation?▼

Staging-first validation persists complete request and response artifacts for each executed golden-case, retaining the evidence to support debugging, audit trails, and final evaluation against expected results.

Related Skills

Explore More Data & Analytics Skills→
datagouvdatagouv
13

siade-sync-openapi-payloads

Generate and validate SIADE staging payloads against OpenAPI schemas with rspec.

Official
Advanced
ace3ace3

qa

Route QA requests to the smallest report-only QA role.

Community
Intermediate
tyronerosstyroneross
1

design-validation

Audit live pages and native simulators for design and accessibility compliance.

Community
Advanced
jamesrochabrunjamesrochabrun
194

qa-test-planner

Generate QA test plans, manual cases, regression suites, and bug reports.

Community
Advanced