Build robotics ai
Skill hiteshbandhu/skills-i-use/skills/ai-engineer-talks/build-robotics-ai
Runs workflows for robotics/autonomy talks — lab co-scientist loops, Optimus systems latency, kitchen supervised autonomy, Waymo EMMA, GR00T N1 humanoid FM, open $9k humanoids. Use when the user builds robots, humanoids, AV planning, or lab automation agents.From its SKILL.md
npx -y skills add hiteshbandhu/skills-i-use --skill build-robotics-aiAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 3 commands, including `cp -r skills/build-robotics-ai ~/.claude/skills/` and 2 more.
SKILL.md
2.2 KB, 497 tokens by cl100k_base, as published. Nobody here has run it
Build robotics AI systems
Action playbook from six AI Engineer / World's Fair talks. Do not summarize talks — pick a workflow and execute it.
Supporting files (read when needed):
- workflows.md — workflows A–F (steps, deliverables, stop conditions)
- source-index.md — src-NNN → talk learnings in ingest-into-skills
Optional: {SKILL_OUTPUT_DIR}/build-robotics-ai/
Step 0 — Pick workflow
Use the decision tree below. Open the matching section in workflows.md.
What is the user trying to do?
├─ Closed-loop lab / co-scientist agent → A
├─ Humanoid systems performance (latency/data) → B
├─ Commercial kitchen/service robotics → C
├─ AV + VLM planning (Waymo EMMA) → D
├─ Adopt humanoid foundation model (GR00T) → E
└─ Ship affordable open humanoid platform → F
Stop summarizing once a workflow is identified — run its checklist.
Install
cp -r skills/build-robotics-ai ~/.claude/skills/
cp -r skills/build-robotics-ai ~/.cursor/skills/
cp -r skills/build-robotics-ai ~/.codex/skills/
From skills-i-use or ingest-into-skills (playlists/robotics-autonomy-ai-engineer/).
Cross-cutting rules
| Rule | Source |
|---|---|
| Profile end-to-end control latency | [src-002 @ 7:11] |
| Sim/real eval before planner changes | [src-004 @ 14:16] |
| Teleop safety before full autonomy | [src-006 @ 10:29] |
Disputed steps: see source-index.md. Name workflow A–F; save artifacts to ./skill-outputs/build-robotics-ai/ when requested; do not auto-commit.
Invocation examples
@build-robotics-ai humanoid data pipeline architecture
lab agent with live sensors
What ships with it: 3 files
3.2 KB alongside SKILL.md
- README.md858 B
- source-index.md1.5 KB
- workflows.md877 B