Visible AI-driven robotics demos powered by VLM policies, MCP skills, and AI coding agents. Reviewable HTML reports — frames, maps, tool traces, scores — instead of buried terminal logs.
Skill Claude CodeCodex
Run frozen Roboclaws Eval Harness rows on CloudML with bounded parallelism, official cml lifecycle commands, executor-backed JuiceFS transfer, durable task receipts, verified collection, and explicit retry/preemption evidence. Use when a user asks to run, refresh, resume, monitor, collect, or debug a Roboclaws…
Skill Claude CodeCodex
Prepare, run, review, and explicitly promote bounded Skill or existing-MCP Eval Evolution campaigns through the canonical eval facade.
Skill Claude CodeCodex
Select and run Roboclaws validation, product, eval-suite, and live-agent eval rows from a plan, diff, or explicit capability request.
Skill Claude CodeCodex
Complete household-world goals through public household MCP tools.
Skill Claude CodeCodex
Label visible cleanup-relevant movable objects from grouped RAW-FPV frames without creating executable cleanup handles.
Skill Claude CodeCodex
Use this skill whenever the user asks whether a Roboclaws live-agent report run is faster, wants to compare Agent SDK/Codex/Claude cleanup reports, asks about model-call work, residual latency, speedup validity, or report performance under provider/network variance. The skill extracts sanitized JSON metrics first and…
Skill Claude CodeCodex
Align scene Gaussian/splat, USD/mesh, and robot map assets into an honest digital-twin evidence workflow. Use when a new Gaussian scene arrives, when B1/Map12-style assets need to be connected, when map anchors are being projected into a 3D scene, or when an agent must decide whether an alignment is candidate…
Skill Claude CodeCodex
Create blog, README, social, or demo-review visual showcases from completed Roboclaws run artifacts, especially chaptered GIFs/contact sheets for household cleanup runs. Use when asked to turn report output, robotviews, traces, or runresult.json into polished visual result evidence without rerunning the robot task.