evidence-verification

Automate evidence verification across Brick Protocol layers with bounded extraction.

Updated Jun 11, 2026
One-click install
npx skills add https://github.com/insightwavesmith/BRICK --skill evidence-verification-insightwavesmith
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evidence-verification
Source: https://github.com/insightwavesmith/BRICK/tree/main/brick_protocol/agent/skills/evidence-verification
Command: npx skills add https://github.com/insightwavesmith/BRICK --skill evidence-verification-insightwavesmith

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the process of verifying work in the Brick Protocol by automatically checking support evidence through local commands, fixtures, and records.

Core Features & Use Cases

  • Evidence Verification: Automates the checking of support evidence across different layers of the Brick Protocol.
  • Layered Inspection: Inspects the various layers of evidence including Brick, Agent, Link, Graph projection, and Raw/claim_trace.
  • Token-Cost Discipline: Provides guidelines on bounded evidence extraction and usage to maintain efficiency.
  • Error Repair & Reporting: Identifies repairable issues and reports candidate Brick boundaries and Link transitions.

Quick Start

Run the 'evidence-verification' skill to verify support evidence for the last build execution.

Frequently Asked Questions about evidence-verification

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

FAQPage Schema
How do I automate support evidence verification in the Brick Protocol?

Automated evidence verification in the Brick Protocol checks support records, local commands, and fixtures through multi-layered inspection to validate work execution.

What layers of evidence inspection does the Brick Protocol support?

Evidence inspection covers multiple layers including Brick, Agent, Link, Graph projection, and Raw/claim_trace to verify protocol execution thoroughly.

How do I check local command fixtures and support records for errors?

Checking local command fixtures and support records identifies repairable issues and reports candidate Brick boundaries and Link transitions for error repair.

Can I bound evidence extraction to maintain token-cost discipline?

Bounded evidence extraction enforces token-cost discipline by providing guidelines that limit extraction scope and maintain processing efficiency.

Does evidence verification work with the last build execution records?

Evidence verification supports checking the last build execution by running the verification process to validate support evidence automatically.

What is the best way to report repairable issues in Brick boundaries and Link transitions?

Reporting repairable issues involves automated error repair reporting that identifies and surfaces candidate Brick boundaries and Link transitions during inspection.