evaluating-cosmos-policy

82 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By Orchestra-Research/AI-Research-SKILLs (GitHub) · coding · 14,447 stars · scanned at commit 773a529

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.

Found in 11 places.

18-multimodal/cosmos-policy/SKILL.md, line 20uv run --extra cu128 --group libero --python 3.10 \
18-multimodal/cosmos-policy/SKILL.md, line 105git clone https://github.com/NVlabs/cosmos-policy.git
18-multimodal/cosmos-policy/SKILL.md, line 115export CUDA_VISIBLE_DEVICES=0

Show 8 more

18-multimodal/cosmos-policy/SKILL.md, line 124uv run --extra cu128 --group libero --python 3.10 \
18-multimodal/cosmos-policy/SKILL.md, line 174for suite in libero_spatial libero_object libero_goal libero_10; do
18-multimodal/cosmos-policy/SKILL.md, line 224git clone https://github.com/moojink/robocasa-cosmos-policy.git
18-multimodal/cosmos-policy/SKILL.md, line 235uv run --extra cu128 --group robocasa --python 3.10 \
18-multimodal/cosmos-policy/SKILL.md, line 290git clone https://github.com/NVlabs/cosmos-policy.git
18-multimodal/cosmos-policy/SKILL.md, line 298uv sync --extra cu128 --group libero --python 3.10
18-multimodal/cosmos-policy/SKILL.md, line 309export CUDA_VISIBLE_DEVICES=0
18-multimodal/cosmos-policy/SKILL.md, line 373python -m robocasa.scripts.download_kitchen_assets

Downloads and installs other software

The author does not mention this.

Found in 3 places.

18-multimodal/cosmos-policy/SKILL.md, line 225uv pip install -e robocasa-cosmos-policy
18-multimodal/cosmos-policy/SKILL.md, line 303uv pip install -e robocasa-cosmos-policy
18-multimodal/cosmos-policy/references/robocasa-commands.md, line 98- clone `https://github.com/moojink/robocasa-cosmos-policy.git` and install it with `uv pip install -e robocasa-cosmos-policy`

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'evaluating-cosmos-policy' ] || [ -L ~/.agents/skills/'evaluating-cosmos-policy' ]; then echo 'A skill folder named evaluating-cosmos-policy already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Orchestra-Research/AI-Research-SKILLs' "$d" && git -C "$d" checkout --quiet '773a52944ba4747a18bd4ae9ade53fff041adcbc' -- '18-multimodal/cosmos-policy' && mkdir -p ~/.agents/skills && cp -R "$d"/'18-multimodal/cosmos-policy' ~/.agents/skills/'evaluating-cosmos-policy' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'evaluating-cosmos-policy' ~/.claude/skills/'evaluating-cosmos-policy' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for Orchestra-Research/AI-Research-SKILLs shows the score of its lowest-scoring skill.

SkillTrust badge for Orchestra-Research/AI-Research-SKILLs

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/Orchestra-Research/AI-Research-SKILLs.svg)](https://zalavijaysinh.github.io/skilltrust/repos/Orchestra-Research/AI-Research-SKILLs/)

Score history

Date	Version	Score
2026-11-08	`773a529`	82
2026-11-07	`773a529`	82