agentsclimarketplace

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

Install
npx -y skills add hiteshbandhu/skills-i-use --skill build-robotics-ai

Assembled 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

RuleSource
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

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.