synthetic-scenarios is agent-read markdown (skill) from ai-evals-course/cartwheel-homeworks: Generate grounded eval scenarios from a spec plus ground-truth access. Use when you have a written spec for an agent and a database or corpus that can compute expected outcomes, and you need realistic usage data (scenarios) to run against the agent..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
mdr add ai-evals-course/cartwheel-homeworks/synthetic-scenarios@git:20260902.cdf1964mdr add ai-evals-course/cartwheel-homeworks/synthetic-scenarios@sha256:c748ae9a2107cc55Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_2zq2ljcpuwh6ruqn)
0 badge views in 30 days
ai-evals-course/cartwheel-homeworks · 24 stars · license none · pushed 2026-09-06 · branch main
GET https://markdownregistry.com/api/v1/artifacts/art_2zq2ljcpuwh6ruqn GET https://markdownregistry.com/api/v1/resolve?ref=ai-evals-course/cartwheel-homeworks/synthetic-scenarios GET https://markdownregistry.com/api/v1/blob/c748ae9a2107cc55b61bd4a6c9b8cb45b45a93c5743218cf4223aed0a5e84169