What does AgentSkill-Eval do?
Automated evaluation, failure diagnosis, and regression analysis platform for agent skill development and design.
Automated evaluation, failure diagnosis, and regression analysis platform for agent skill development and design.
AgentSkill-Eval is a comprehensive platform designed for the automated evaluation, failure diagnosis, and regression analysis of AI agent skills. It enables developers to systematically test agent behaviors, identify failure points, and track performance regressions over time. The platform supports popular agent frameworks such as Claude Code, Cursor, and Codex, providing a unified interface for skill validation. By automating the evaluation process, it reduces manual testing effort and helps ensure consistent agent behavior across updates. The tool works by running predefined test scenarios, capturing execution logs, and comparing results against baseline metrics to detect anomalies and regressions. This makes it invaluable for teams developing and maintaining complex agent skills who need reliable quality assurance.
npx skills add ranmaoxia0123/AgentSkill-EvalInstalled? Explore more Coding & Development skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Automated evaluation, failure diagnosis, and regression analysis platform for agent skill development and design.
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.