develop-test

Generate adversarial IR inputs to test retikz JSON and zod contracts.

12|2|Updated Nov 27, 2024
One-click install
npx skills add https://github.com/Pionpill/retikz --skill develop-test
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: develop-test
Source: https://github.com/Pionpill/retikz/tree/main/.agents/skills/develop-test
Command: npx skills add https://github.com/Pionpill/retikz --skill develop-test

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It reduces the risk that retikz specs pass while real AI-generated inputs still break the implementation, by systematically hunting for adversarial IR/JSON/zod-contract failures before documentation work begins.

Core Features & Use Cases

  • Adversarial Bug Hunter sub-agent: dispatches an independent “opinion-shifted” agent to generate new input cases designed to make the implementation fail.
  • Blocking vs non-blocking triage: classifies results into BLOCKING (must-fix) and WARNING/INFO (review/backlog) based on contract-critical failure modes like JSON round-trip, zod error clarity, schema invariants, and discriminator stability.
  • Fix-to-test feedback loop: converts discovered BLOCKING issues into formal spec tests and re-runs the adversarial phase to confirm convergence.

Quick Start

Run the develop-test stage by selecting an ADR still in Proposed state, ensuring lint/tsc/vitest are currently all passing, then prompt the system to generate adversarial vitest cases and report any BLOCKING items.

Frequently Asked Questions about develop-test

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

FAQPage Schema
How do I generate adversarial test cases to break zod schema validation?

To generate adversarial test cases for zod schema validation, you can use an agentic QA sub-agent to create new IR inputs designed to violate schema invariants and discriminator stability. This approach systematically hunts for contract failures before documentation begins.

What is the best way to harden JSON round-trip equivalence against invalid AI inputs?

The best way to harden JSON round-trip equivalence is to run adversarial self-testing that generates inputs violating AI-facing contracts. This process converts discovered BLOCKING issues into formal vitest cases and iterates until all critical failures are fixed and regression-verified.

Can I use vitest to validate contract stability during alpha development without committing test code?

Yes, you can use vitest to validate contract stability during alpha development by adding only temporary adversarial test cases. The workflow requires producing structured BLOCKING/WARNING/INFO reports without committing any code, schema, or test changes.

How do I triage contract validation failures when ADR-derived specs miss real-world corner cases?

To triage contract validation failures, classify results into BLOCKING (must-fix) and WARNING/INFO (review/backlog) categories based on failure modes like JSON round-trip errors and zod parse clarity. This structured reporting isolates critical issues from minor backlog items.

Why does my zod parse error lack clarity when processing AI-generated IR inputs?

Your zod parse error lacks clarity because adversarial IR inputs may expose missing edge cases in your ADR-derived specs. An opinion-shifted agent can generate inputs to specifically target and improve zod error clarity and discriminator stability.

Does contract validation testing work without an existing ADR in Proposed state?

No, contract validation testing requires an ADR in Proposed state and a baseline where lint, tsc, and vitest are currently passing. This ensures the adversarial bug hunter has a stable foundation to generate and validate new boundary-breaking cases.