SkillCompass
Evaluate agent skills, identify their weakest dimensions, and track whether improvements actually work.
Evaluate agent skills, identify their weakest dimensions, and track whether improvements actually work.
SkillCompass is a local-first evaluator and manager for people who maintain agent skills. It scores a skill across six dimensions, identifies the weakest area to improve, and tracks versions so later evaluations show whether a change helped. Usage hooks feed an inbox that surfaces unused skills, stale evaluations, declining adoption, and updates, while SKILL.md edits trigger structural and security-pattern checks. SHA-256 snapshots make regressions recoverable. It is not a general code reviewer, runtime debugger, or tool for creating skills from scratch.
Resource types
Use cases
Platforms
Scan iOS and macOS projects for common App Store rejection risks before submission.
Audit JavaScript and TypeScript codebases with fallow-aware agent workflows
Runtime
Capabilities
Audience
Public GitHub facts last synced Jul 14, 2026.
Audit web performance, accessibility, SEO, and Core Web Vitals with an AI agent.
Review agent-generated code, tests, documentation, and platform changes before they ship.