Que fait agent-improvement ?
Perceive→Reason→Act→Refine autonomous decision loop with risk scoring and self-correction
Perceive→Reason→Act→Refine autonomous decision loop with risk scoring and self-correction
agent-improvement is a Claude Code agent skill that perceive→Reason→Act→Refine autonomous decision loop with risk scoring and self-correction.
npx skills add Atharv279/agent-improvementInstalled? Explore more Développement et programmation skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Perceive→Reason→Act→Refine autonomous decision loop with risk scoring and self-correction
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.