Improves a production agent system by repairing the evals that judge it. Failures are mined into new eval cases, and gates on both sides control what enters: false negatives the suite would never catch, false positives that refuse a correct change. The system improves by having to pass.
touchstone is a Claude Code agent skill that improves a production agent system by repairing the evals that judge it. Failures are mined into new eval cases, and gates on both sides control what enters: false negatives the suite would never catch, false positives that refuse a correct change. The system improves by having to pass.
npx skills add sandeepyadav1478/touchstoneInstalled? Explore more Développement et programmation skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Improves a production agent system by repairing the evals that judge it. Failures are mined into new eval cases, and gates on both sides control what enters: false negatives the suite would never catch, false positives that refuse a correct change. The system improves by having to pass.
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.