npx claudepluginhub spsk-dev/consensusThis skill uses the workspace's default tool permissions.
Validates any conclusion by dispatching it to 3 independent AI models. Each model evaluates from a different analytical lens. Results synthesized with confidence scores on a 1-10 scale.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Designs, implements, and audits WCAG 2.2 AA accessible UIs for Web (ARIA/HTML5), iOS (SwiftUI traits), and Android (Compose semantics). Audits code for compliance gaps.
Validates any conclusion by dispatching it to 3 independent AI models. Each model evaluates from a different analytical lens. Results synthesized with confidence scores on a 1-10 scale.
claude /install-plugin consensus@spsk-dev/consensus
/consensus "GraphQL is better than REST for our mobile API"
/consensus --evidence @analysis.md "The auth middleware is the root cause"
/consensus --domain architecture "Microservices is right for this team size"