O que skillval faz?
Deterministic evals for agent skills (agentskills.io) - skill vs baseline arms measure whether a skill changes model behavior
Deterministic evals for agent skills (agentskills.io) - skill vs baseline arms measure whether a skill changes model behavior
skillval is a Claude Code agent skill that deterministic evals for agent skills (agentskills.io) - skill vs baseline arms measure whether a skill changes model behavior.
npx skills add dungle-scrubs/skillvalInstalled? Explore more Programação e Desenvolvimento skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Deterministic evals for agent skills (agentskills.io) - skill vs baseline arms measure whether a skill changes model behavior
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.