skills.rest
kapilvirenahuja
kapilvirenahujaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

garura:validate

Validate milestone changes with tiered E2E and judge-based acceptance checks.

3|Updated Jan 25, 2026
Search Tags:#playwright#e2e testing#cypress#qa validation#milestone gating#system evals#acceptance verdict
One-click install
npx skills add https://github.com/kapilvirenahuja/garura --skill garura-validate
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: garura:validate
Source: https://github.com/kapilvirenahuja/garura/tree/main/core/components/plays/validate
Command: npx skills add https://github.com/kapilvirenahuja/garura --skill garura-validate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of deciding whether committed milestone changes are truly acceptable by validating the running product against locked, milestone-specific acceptance criteria in a deployed environment.

Core Features & Use Cases

  • Milestone-scoped, tiered verification: Runs baseline (cumulative regression), new (this milestone), and regression (change-surface) scenario tiers in order.
  • E2E + independent judge acceptance: Executes Playwright/Cypress-style E2E tests against a preview/staging deployment, then has a judge evaluate runtime behavior against system-level evals.
  • Controlled fix loop with routing: When failures occur, generates milestone-scoped remediation and routes changes back to implement (without directly invoking code-building), retrying up to three iterations.
  • Per-milestone verdict output: Produces a structured ACCEPT/REJECT verdict file and evidence artifacts suitable for audit and release decisions.

Quick Start

Run garura:validate for milestone T-001 by providing the issue context and the deploy URL for the preview/staging environment you want validated.

Frequently Asked Questions about garura:validate

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

FAQPage Schema
How do I validate milestone acceptance criteria using E2E tests in a staging environment?▼

Milestone validation executes tiered Playwright or Cypress E2E tests against a deployed staging environment, running baseline, new, and regression scenarios to verify changes against locked acceptance criteria.

What happens if baseline regression tests fail during milestone QA validation?▼

Baseline regression failures halt the milestone validation process immediately, skipping subsequent test tiers and routing remediation back to implementation without directly invoking code builders.

How does automated milestone gating decide whether to accept or reject a release?▼

Automated milestone gating evaluates E2E test results and judge-based system evaluations against acceptance criteria, generating a structured ACCEPT or REJECT verdict file with supporting evidence artifacts.

Can I run milestone-scoped Playwright and Cypress E2E tests without affecting my full regression suite?▼

Yes, milestone validation scopes scenarios strictly to the specific milestone, executing tiered E2E tests for baseline cumulative regression, new milestone scenarios, and change-surface regression independently.

What is the remediation loop process when E2E tests fail during milestone validation?▼

When E2E tests fail, the system generates milestone-scoped remediation routed back to implement, retrying up to three iterations without directly invoking code-building tools.

Does milestone validation work with both Playwright and Cypress for deployed E2E testing?▼

Yes, milestone validation supports both Playwright and Cypress-style E2E testing frameworks to execute tiered verification against preview or staging deployments.

Related Skills

Explore More Software Engineering Skills→
masermediagroup-stackmasermediagroup-stack
1

deploy-to-vercel

Deploy projects to Vercel and obtain preview URLs via CLI or no-auth fallback.

Community
Advanced
harkersharkers

reviewer-agent

Review bounded work for correctness and output evidence-linked findings with a disposition.

Community
Advanced
drvossdrvoss
42

e2e-testing

Generate Playwright or Cypress end-to-end test suites for critical user journeys.

Community
Advanced
creeper-RedWHUcreeper-RedWHU

task-kanban

Execute Playwright E2E tests for a Vue 3 Task Kanban app.

Community
Advanced