semantic-trust
OfficialEnhance trust in collaborative claims with cross-agent verification and decay scoring
AuthorInnerScopeHearing
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill assesses the trustworthiness of shared claims made by multiple agents, considering corroboration, age, and contradictions.
Core Features & Use Cases
- Cross-Agent Corroboration: Determines how trustworthy a claim is based on agreement from various agents.
- Trust Decay: Scores how recent claims are and factors their age into trustworthiness.
- Contradiction Handling: Identifies and penalizes contradicting claims, promoting resolution and transparency.
- Use Case: For a company feed, this Skill helps verify facts shared across departments before elevating them to a 'semantic/durable' level.
Quick Start
Run the 'scoreClaim' function on a list of assertions and contradictions from different agents to evaluate their trustworthiness.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferences
💻 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: semantic-trust Download link: https://github.com/InnerScopeHearing/otchealth-claude-tools/archive/main.zip#semantic-trust 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 620,000+ vetted skills library on demand.