real-scenario-qa
OfficialRun release-grade startup labs on AGH
Software Engineering#artifact validation#multi-agent collaboration#agh#real-scenario qa#playbook execution#runtime auditing
Authorcompozy
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill runs release-grade end-to-end QA by executing a full fictional startup scenario on the AGH runtime and validating real outputs and collaboration behavior—without turning the agents into “testers”.
Core Features & Use Cases
- Playbook-driven lab bootstrapping: Selects (or rotates) a scenario playbook, materializes an isolated lab, registers agents, and seeds required state.
- Autonomous runtime execution: Posts a single in-persona operator kickoff, then lets agents collaborate while a read-only observer watches.
- Evidence-first auditing: Enforces required deliverables (that parse/compile/run), cross-surface evidence (CLI/API/Web/Runtime), collaboration loops, disruption recovery, and stall diagnostics.
Quick Start
Run real-scenario QA on a specific playbook by providing its playbook ref as the single argument: real-scenario-qa northstar-pay
Dependency Matrix
Required Modules
python3.agents/skills/agh-qa-bootstrap/scripts/bootstrap-qa-env.pypython3.agents/skills/real-scenario-qa/scripts/post-operator-kickoff.pypython3.agents/skills/real-scenario-qa/scripts/observe-runtime.pypython3.agents/skills/aqc-qa-evidence.pymake
Components
scriptsreferencesassets
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: real-scenario-qa Download link: https://github.com/compozy/agh/archive/main.zip#real-scenario-qa Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.