GitHub Repository

🔬 Verifiable AI-Augmented Engineering Framework - Stop AI hallucinations with formal traceability (REQ→ART→TC). Agent Skills for Claude Code, Cursor, VS Code & Copilot. Enterprise-grade: ISO 9001, ISO 27001, GxP-ready. Red Team verification, multi-cycle lifecycle, behavioral anti-patterns.

44 starsJavaScript

Agile V Skills – Open skills for verifiable, traceable AI engineering

Name: Agile V Skills – Open skills for verifiable, traceable AI engineering
Availability: InStock
Author: JoshuaWellbrock

by JoshuaWellbrock·Mar 13, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainBold Bet

Enforces test independence in AI agents to break the confirmation bias loop.

Strengths

•Separates test generation from code generation to prevent agent confirmation bias.
•Maps every artifact to a Requirement ID for full traceability and auditing.

Weaknesses

•Requires integrating specific skill files into your existing agent runtime manually.
•Niche appeal limited to teams building complex agentic systems with compliance needs.

Post Description

We've been wrestling with a specific problem: when you use AI agents to build real software, how do you make sure the output is actually verified, not just syntactically correct, but traced back to requirements and independently tested?

Most AI coding workflows are just "write this, now test this." The agent that writes the code also writes the tests for the code it just wrote. That's not testing, that's confirmation bias in a loop.

Curious whether others have tried to enforce test independence structurally in agentic workflows, and whether the Skills format (vs. system prompts or tool definitions) is something people are actually using or think is the right abstraction for this.