flâneur

Sundial — Agent skills for your AI setup

sundial.md · 240 words · saved by 2 readers

The open registry for agent skills. Browse, install, and publish reusable AI skills for Claude Code, Cursor, Gemini, ChatGPT, Antigravity, GitHub Copilot, OpenCode, OpenHands, Amp, Goose, Kilo Code, Trae, Junie, Windsurf, Codex, Cline, Roo Code, Continue, and any agent that reads markdown.

Sundial is a research lab in San Francisco studying human-agent collaboration. We build infrastructure for people to understand the work models do, steer them, and shape how they behave. Model autonomy doubles every few months, but our capacity to review their work stays fixed. Closing that gap means making the work legible: understanding what was done, by whom, and why. Sundial builds instruments to keep that record and learn from it. What we study Q.I Long-horizon verification How can we efficiently verify agent work that would take humans weeks or months? Q.II Surfaces for…

saved by

related reading