cosmos3-ci-smoke

CI smoke skill for the skill-eval pipeline: two trivial, CPU-only file-writing tasks that finish in a couple of minutes. Use only to exercise the eval CI end to end (trigger → runner → sequential cells → PR comment → dashboard). Not a real Cosmos skill.

Jump to install Review files

Repository: NVIDIA/cosmos-framework
Last source activity: October 30, 2026 at 03:31
Detected SKILL.md language: English
Stars: 588
Forks: 188

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/NVIDIA/cosmos-framework/tree/main/.github/scripts/skill_eval/cosmos3-ci-smoke.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/NVIDIA/cosmos-framework --skill cosmos3-ci-smoke

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

2 files

SKILL.md

Source instructions · Read-only preview

name: cosmos3-ci-smoke
description: CI smoke skill for the skill-eval pipeline: two trivial, CPU-only file-writing tasks that finish in a couple of minutes. Use only to exercise the eval CI end to end (trigger → runner → sequential cells → PR comment → dashboard). Not a real Cosmos skill.

# Skill-eval CI smoke Two tiny tasks that prove the evaluation pipeline without touching a model: 1. **smoke-hello** — write `outputs/hello.txt` containing exactly the line `cosmos skill eval smoke OK` and print it back. 2. **smoke-python** — with `python3`, compute the sum of the integers 1..100 and write `{"sum": 5050}` to `outputs/sum.json`. Record what you did in `result_summary.md`. No GPU, network or credentials are needed; everything runs in the task container's working directory.

View on GitHub

Back to search Back to installation

cosmos3-qwen3-vl-robovqa-sft

Fine-tune Qwen3-VL-8B-Instruct, a vision-language model from outside the Cosmos family, with the Cosmos Framework posttrain SFT path on robot-video question answering (RoboVQA), on one GPU, and score it before and after with the same evaluator. Use when the user asks to "fine-tune Qwen3-VL with Cosmos Framework", "train a non-Cosmos model or a VLM in the framework", "run SFT on robot videos / RoboVQA", "reproduce the Qwen3-VL RoboVQA result", or wants a worked post-training example with a measured before and after (environments, data preparation, preflight, training, Hugging Face export, evaluation). Not for Cosmos3 checkpoints (use cosmos3-post-training) and not for LoRA (the SFT path trains every parameter).

2026-10-31

cosmos3-generate-media

Generate images, videos, and audio-synchronized videos with the Cosmos3 audiovisual generator models (Edge / Nano / Super / Super-4Step) through any of the seven supported serving paths: diffusers in-process, cosmos_framework torchrun, vLLM-Omni, SGLang, TensorRT-LLM, distilled TensorRT-LLM, or NIM. Use when the user asks "generate a video from a prompt", "run text2image / text2video / image2video with Cosmos3", "serve a Cosmos3 generator", or asks which Cosmos3 generation backend fits their GPU. Self-contained: sample prompts, reference images and negative prompts ship in this skill's assets/.

2026-10-30

cosmos3-skill-authoring

Author new Cosmos3 agent skills and their eval configs, and get them through the skill eval. Use when adding a skill under .agents/skills/, migrating a cookbook notebook or README into a skill, writing or updating an eval.config, choosing eval cases and assertions, fixing a skill after a failed or self-corrected eval cell, reading an eval report on the dashboard, or preparing a skill PR. Covers the required structure, the writing rules that decide first-attempt pass/fail, the eval.config schema (multi-case evals), how the evaluator judges, and how to run the eval in GitHub CI or locally. Do not use it to run the Cosmos3 workloads themselves (the per-workload skills do that) or to change the evaluator.

2026-10-30

View all from this repository

cosmos3-ci-smoke

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository