Popular repositories Loading
-
azimuth-testbed
azimuth-testbed PublicInteractive testbed for AZIMUTH decision analysis — runs live pre-commitment analysis via the Anthropic API. No data stored.
JavaScript
-
skills
skills PublicAgent skills for Claude Code that have to earn their keep: each carries evidence of the real failure behind it, gets re-tested on new model releases, and is publicly retired when models stop needin…
-
skill-harness
skill-harness PublicMeasures whether an AI agent skill actually does anything: same task with and without the skill, compared honestly. UNMEASURED is a first-class verdict, never a made-up score. Pre-alpha.
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.



