embodied ai skills

PhyAgentOS/PhyAgentOS-core

Skill Claude CodeCodex

Unified tool for managing agent LLM modes (add, remove, update, list, switch).

PhyAgentOS/PhyAgentOS-core

Skill Claude CodeCodex

Schedule reminders and recurring tasks.

PhyAgentOS/PhyAgentOS-core

Skill Claude CodeCodex

Unified tool for analyzing and displaying images (vision analysis and image display).

sou350121/VLA-Handbook

Skill Claude CodeCodex

Adversarial research analysis framework that uses structured Bull/Bear/Arbiter debates to help users make better research judgments. Maintains a belief graph as backend engine, applies statistical calibration discipline, tracks phase transitions, and detects biases. MANDATORY TRIGGERS: Use this skill whenever the user…

zju3dv/habitat-gs

Skill Claude CodeCodex

Interactively pilot a robot in habitat-gs 3D Gaussian Splatting indoor scenes via MCP tools — load a scene, move, observe with RGB/depth, run autonomous nav loops, and export video. Use for hands-on control of a live sim session, NOT for training or evaluating a navigation policy (use the habitat-gs-train skill for…

zju3dv/habitat-gs

Skill Claude CodeCodex

Train and evaluate a navigation policy in the habitat-gs simulator. Covers the full generate-episodes → train → evaluate flow for PointNav / ImageNav / ObjectNav (Habitat-Lab + DDPPO reinforcement learning) and for Vision-and-Language Navigation (StreamVLN, Uni-NaVid). Use when the user wants to train, fine-tune…

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…

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.

ros-claw/rosclaw

Skill Claude CodeCodex

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

dp-web4/SAGE

Skill Claude CodeCodex

Disciplines and references for acting as fleet coordinator/supervisor across the dp-web4 project ecosystem (SAGE, ARC-SAGE, shared-context, private-context). Use when coordinating multi-machine work, reviewing fleet state, deciding what to pull/commit/merge, evaluating training results with agent-zero defenses, or…

dp-web4/SAGE

Skill Claude CodeCodex

Show raising status across all SAGE instances in the fleet. Use when asked about raising progress, instance development, fleet status, or which phase any SAGE instance is in.

OpenGHz/embodied-ai-paper-writer

Skill Claude CodeCodex

Professional embodied-AI paper-writing coach distilled from 63 top-conference papers (CoRL, RSS, ICRA, IROS, Science Robotics, 2022–2026). Teaches writing craft only — vocabulary, sentence patterns, paragraph flow, figure/table conventions, section-by-section construction, rhetorical pivots, appendix norms. NOT a…

Yinzhanqing/embodied-eval-automation

Skill Claude CodeCodex

Plan, explain, build, run, monitor, validate, transfer, and audit reproducible embodied-model studies and batch episode collection. Use when a user wants to connect a local, SSH, or cloud GPU host; understand and compare a policy, VLA, world model, world-action model, or hybrid with a benchmark; discover and reuse…

productstein/holomime

Skill Claude CodeCodex

Automatically diagnose behavioral drift, run a therapy session, and apply corrections to the personality spec. Hands-off alignment — one command to detect and fix behavioral issues. Requires holomime Pro.

productstein/holomime

Skill Claude CodeCodex

Stress-test an AI agent's behavioral alignment with 8 adversarial scenarios. Produces a grade (A-F) and score (0-100). Use when you want to know how well an agent handles apology traps, sycophancy tests, boundary pushes, error recovery, and more.

productstein/holomime

Skill Claude CodeCodex

Detect behavioral drift patterns in AI agent conversations. Use when you want to check if an agent is over-apologizing, hedging, being sycophantic, violating boundaries, error-spiraling, sentiment-skewing, drifting formality, or hallucinating. Zero LLM cost — rule-based detection with 80+ signals across 8 detectors.