dev-verify

Verify code changes with evidence-backed test and build results.

520|175|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/evolution-foundation/evo-nexus --skill dev-verify-evolution-foundation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dev-verify
Source: https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/dev-verify
Command: npx skills add https://github.com/evolution-foundation/evo-nexus --skill dev-verify-evolution-foundation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents teams from claiming a change is complete based on optimism by turning “should work” updates into concrete, verifiable evidence.

Core Features & Use Cases

  • Verification-first workflow: Converts unclear “works in theory” claims into a checklist of behavior to prove, then verifies it in a prioritized order (tests, then build/typecheck, then targeted checks, then manual validation).
  • Evidence-based reporting: Produces an output that clearly states what was verified, which commands/tests were run, what passed, and what failed or remains unverified.
  • Failure transparency: If something fails, it must be reported clearly instead of being glossed over, including when no realistic verification path exists.

Quick Start

Ask an AI agent to verify that my proposed refactor actually works by mapping the expected behavior, running the narrowest relevant tests or checks first, and returning an evidence-focused pass/fail summary.

Frequently Asked Questions about dev-verify

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

FAQPage Schema
How do I verify that my code changes actually work before shipping?

To verify code changes before shipping, map expected behavior into a checklist and prove it using prioritized validation: run existing tests, execute typecheck and build commands, perform narrow direct checks, and document manual validation steps with transparent pass or fail evidence.

What is the best way to prove a refactoring did not break existing features?

The best way to prove a refactoring is safe involves running an evidence-backed verification workflow that prioritizes existing tests first, followed by build validation and targeted command checks, ensuring you produce a clear report of what passed and what failed.

How do I document evidence reporting for release readiness validation?

Document release readiness evidence by generating a focused summary that explicitly states what was verified, lists the exact tests and commands executed, and transparently reports any failures or areas that remain unverified without overstating completion.

Why does my feature verification only produce vague claims of completion?

Feature verification often yields vague claims when it lacks an evidence-first workflow, which requires moving from theoretical confidence to concrete proof by running prioritized tests and build validation checks, then transparently documenting any failures.

What should I do when build validation fails during code verification?

When build validation fails during code verification, you must report the failure transparently instead of glossing over it, detailing what specifically failed or remains unverified in your evidence-backed validation summary.

Can I use automated testing to check release readiness for feature fixes?

You can check release readiness for feature fixes by prioritizing existing automated tests first, then running typecheck and build validation, and finally documenting any remaining manual validation steps to produce comprehensive evidence of completion.