adversarial-qc
OfficialCatch AI mistakes with parallel verifier checks.
Software Engineering#quality control#adversarial review#evidence-based auditing#multi-agent verification#factuality checking#QC certificate
AuthorLegalQuants
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It helps you reduce the risk of incorrect or weak AI-generated deliverables by running two independent reviewers against a structured checklist and comparing their evidence.
Core Features & Use Cases
- Parallel multi-agent verification (single-model or cross-model) to catch surface and structural issues.
- Checklist-based auditing with evidence for factual claims, numbers, logic, attribution, formatting, consistency, and scope.
- Actionable escalation by outputting a QC certificate that flags disagreements for human review and blocks shipping in high-risk scenarios.
- QC outputs including an inline summary and an auditable PDF certificate trail.
Quick Start
Ask your AI assistant to run the adversarial-qc skill on the deliverable you are about to send and produce a QC certificate.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: adversarial-qc Download link: https://github.com/LegalQuants/lq-skills/archive/main.zip#adversarial-qc Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.