physical ai skills

48 tagged physical ai, measured the same way as everything else here.

Browse within: robotics 35openclaw 32raspberry-pi 28reachy-mini 28newton 9sensor-data 9time-series 9jepa 7machine-learning 7world-models 7

computer-use

01

autonomous-ai/autonomous-os

Skill Claude CodeCodex

Control the user's Mac via the paired Autonomous Buddy companion app — open/close apps, navigate URLs in Chrome, type text into focused fields, fire keyboard shortcuts, show desktop notifications, write to clipboard, click named UI buttons via macOS Accessibility. Also covers vision-driven tasks (screenshot…

256 +9 2d ago A 211 tokens original Apache-2.0

faq

02

autonomous-ai/autonomous-os

Skill Claude CodeCodex

Explain how to run and use this repository's local Web UI, with detailed guidance for every Settings section and its visible controls. Use for questions about web development, Monitor, Setup, or Settings.

256 +9 2d ago A 41 tokens original Apache-2.0

wellbeing

03

autonomous-ai/autonomous-os

Skill Claude CodeCodex

Proactive coaching across hydration, breaks, meals AND posture. Use when an [activity] event fires (message starts with [activity] Activity detected: . — labels include drink, break, celebrate, the fatigue label "yawning", or sedentary raw labels like "using computer"; sedentary events may also carry a…

256 +9 2d ago A 124 tokens original Apache-2.0

rosclaw-simforge

04

ros-claw/rosclaw

Skill Claude CodeCodex

Safely install, validate, diagnose, and optimize ROSClaw simulation workflows across MuJoCo/MJWarp, ROS 2 rosbridge, turtlesim, Gazebo, Isaac Sim, Isaac Lab multi-GPU training, MCP, and the signed ROSClaw Hub. Use for evidence-backed physical-AI smoke tests, 4-GPU validation, simulator integration, Hub upload/download…

190 6d ago A 97 tokens original MIT

rosclaw-embodied

05

ros-claw/rosclaw

Skill Claude CodeCodex

A set of rules for completing robot tasks in ROSClaw, a system for running and checking robot work. It covers approved robot files, acceptance evidence, and separate rules for simulation and real hardware.

190 6d ago A 50 tokens original MIT

default

06

ros-claw/rosclaw

Skill Claude CodeCodex

Skill "default" from ros-claw/rosclaw, covering skill.md, skill id, intent, preconditions and effects.

190 6d ago A 0 tokens original MIT

AbdelStark/worldforge

Skill Claude CodeCodex

Use for WorldForge provider work: adding adapters, changing capability declarations, promoting scaffolds, debugging provider failures, updating provider catalog docs, or touching LeWorldModel, GR00T, LeRobot, Cosmos-Policy, JEPA, Genie, or JEPA-WMS. Ensures capabilities remain truthful and optional runtimes stay…

108 23d ago A 73 tokens original MIT

public-docs-release

08

AbdelStark/worldforge

Skill Claude CodeCodex

Use for WorldForge README, docs, changelog, generated provider docs, MkDocs navigation, version/release metadata, public positioning, and release or publish readiness checks. Keeps public surfaces synchronized without hype or generated-doc drift.

108 23d ago A 50 tokens original MIT

testing-validation

09

AbdelStark/worldforge

Skill Claude CodeCodex

Use when selecting, running, or fixing WorldForge validation: pytest, coverage, ruff, generated provider docs, MkDocs strict build, package contract, CI failures, and release gates. Produces the smallest credible command set first, then escalates to full validation when public behavior changes.

108 23d ago A 61 tokens original MIT

archetypeai/agent-skills

Skill Claude CodeCodex

Run Archetype AI's managed Anomaly Discovery (AD) agent over the Agents API — upload a prepared sensor CSV, resolve the pre-packaged "AD Quick Start" bundle by name (a fitted LOF detector and its threshold are already pinned), run it, poll, download a per-window anomaly score. Use when the user wants to flag "this no…

5 12d ago A 230 tokens original Apache-2.0

archetypeai/agent-skills

Skill Claude CodeCodex

Run Archetype AI's managed Manual Generation (MGA) agent over the Agents API — upload a procedure video, create a bundle from the canonical mga blueprint, run it, poll, download an ordered, timestamped manual. Use when the user has a recording of a procedure (a repair, an assembly, a workflow) and wants the platform…

5 12d ago A 221 tokens original Apache-2.0

archetypeai/agent-skills

Skill Claude CodeCodex

Run Archetype AI's managed Task Verification (TVA) agent over the Agents API — upload a recording AND a reference procedure (an SOP), create a bundle from the tva blueprint, run it, poll, download a per-step PASSED / FAILED / MISSING verdict per step. Use when the user has a recording of work that should have followed…

5 12d ago A 216 tokens original Apache-2.0