graph-as-policy

Program robots with GaP (graph-as-policy) — compile natural-language tasks into typed, verified robot skill graphs and run them on simulators or real robots. Use when the user mentions GaP or graph-as-policy, robot manipulation, robot skills, robot tools or capabilities, skill registries, open-robot-skills, LIBERO or MuJoCo manipulation sims, pick-and-place, grasping or perception strategies, generating or hand-authoring robot task graphs, robot benchmarks, or asks what a robot can do. Covers searching registries (gap registry / gap skills / gap tools), capability checks (gap check), running graphs in sim (gap run --sim), generating graphs from language (gap generate), authoring graphs with gap.builder, creating skill bundles and registries with scaffolded unit tests (gap skills new / gap skills test / gap registry init), debugging traces (gap viz, gap trace-diff), and safety-gated real-robot runs.

Echo strings back from an in-process fixture model. Use when a loader test needs a minimal tool bundle with a tools.py.

Produce a greeting for a named entity via a canonical script and a bundled prompt template. Use when a loader test needs a minimal skill bundle with scripts and prompts.