What problem does it solve?
This Skill uncovers and prioritizes edge cases and failure modes across a feature's lifecycle, turning vague risk concerns into concrete, testable scenarios so teams can prevent regressions and outages before shipping.
Core Features & Use Cases
- Systematic 12-dimension exploration: Walks inputs through validation, transform, logic, persistence, and side effects to enumerate failure modes across Invalid Input, Concurrency, Network, Auth, Time, Scale, and more.
- Quantified prioritization: Assigns likelihood and impact scores to every scenario (L x I) and sorts risks so engineering effort focuses on the highest exposure.
- Runnable tests for HIGH+ risks: Auto-generates tests that use real code paths and the project's test framework, verifies execution, and logs outcomes to a scenario TSV for traceability.
- Operational guardrails: Enforces hard rules, rollback commands, and stop conditions to keep automated test generation safe and auditable.
Quick Start
Ask the agent to analyze edge cases for the checkout API, enumerate scenarios across all 12 dimensions, and generate runnable tests for every HIGH+ finding.