一键导入
cosmos3-codebase-nav
Use when navigating the Cosmos3 integration in NPA or locating upstream Cosmos3 framework files, defaults, scripts, configs, recipes, and docs.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when navigating the Cosmos3 integration in NPA or locating upstream Cosmos3 framework files, defaults, scripts, configs, recipes, and docs.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when ingesting, validating, curating, or querying production sensor data as a versioned dataset-of-record, or wiring the dataset-ingest-curate workflow.
Use when generating adversarial scenarios via RL, ranking mined failures of a policy-under-test, or wiring the adversarial-scenario-hardening workflow.
Use when Cosmos3 setup, fetch, inference, CUDA, uv, Docker, Hugging Face, GitHub, NGC, or checkpoint staging fails in NPA or in an upstream Cosmos framework checkout.
Use when setting up Cosmos3 access through NPA, checking source or Hugging Face reachability, staging the public Cosmos3 framework and checkpoint cache, or deciding which NPA workflow to use before inference.
Use for Claude Code reviews that need robotics, simulation, GPU-routing, sim-to-real, or BDD100K pipeline domain context.
Use when submitting, validating, or debugging NPA SkyPilot workflow YAMLs and workflow runner paths.
| name | cosmos3-codebase-nav |
| description | Use when navigating the Cosmos3 integration in NPA or locating upstream Cosmos3 framework files, defaults, scripts, configs, recipes, and docs. |
Adapted from NVIDIA cosmos-framework
skills/atomic/cosmos3-codebase-nav/SKILL.md.
Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. Used under OpenMDW-1.1.
See skills/LICENSE-NVIDIA-COSMOS3-OPENMDW-1.1 and
skills/NOTICE-NVIDIA-COSMOS3.
Use this skill when the user asks where Cosmos3 setup, access checks, inference defaults, parser settings, workflows, or post-training configs live. Also use it when reviewing or modifying PRs that touch Cosmos3 support in NPA.
Primary NPA files:
| Need | File |
|---|---|
| Cosmos3 access, fetch, redaction, parser config, inference arg builder | npa/src/npa/workbench/cosmos/cosmos3.py |
| Human CLI commands for real workflows | npa/src/npa/cli/cosmos/__init__.py |
| SDK compatibility exports | npa/src/npa/workbench/cosmos/__init__.py, npa/src/npa/sdk/workbench/cosmos.py |
| Fetch workflow | npa/src/npa/workflows/skypilot/cosmos3-ea-fetch.yaml |
| Text-to-image H100 smoke workflow | npa/src/npa/workflows/skypilot/cosmos3-text-to-image-inference.yaml |
| Unit tests for access, fetch, inference YAML, and skill artifacts | npa/tests/workbench/test_cosmos3_access.py |
CLI tests for check and fetch | npa/tests/cli/test_cosmos3_cli.py |
The agent-skill artifacts live in this repository under:
skills/atomic/cosmos3-setup/SKILL.mdskills/atomic/cosmos3-codebase-nav/SKILL.mdskills/atomic/cosmos3-env-troubleshoot/SKILL.mdskills/workflows/cosmos3-inference/SKILL.mdskills/workflows/cosmos3-post-training/SKILL.mdThere is no supported Cosmos skill-display subcommand. Cosmos3 skills are not platform commands, job templates, or SDK callables. They are SKILL.md files for coding agents to read.
The only retained Cosmos3 SkyPilot YAMLs are real executable workflows:
cosmos3-ea-fetch.yamlcosmos3-text-to-image-inference.yamlDo not restore cosmos3-setup.yaml, cosmos3-codebase-nav.yaml,
cosmos3-env-troubleshoot.yaml, or cosmos3-post-training.yaml as skill
launchers unless the product direction changes to a real executable workflow.
When a task needs upstream package internals, inspect a clone of
https://github.com/NVIDIA/cosmos-framework.git.
Common upstream paths:
| Need | Upstream path |
|---|---|
| Sampling args, setup args, override models | cosmos_framework/inference/args.py |
| Per-modality defaults | cosmos_framework/inference/defaults/<mode>/sample_args.json |
| Inference script | cosmos_framework/scripts/inference.py |
| Training script | cosmos_framework/scripts/train.py |
| Ray serving presets | cosmos_framework/inference/ray/configs/latency.yaml, throughput.yaml |
| SFT recipe TOMLs | examples/toml/sft_config/<recipe>.toml |
| SFT launch shells | examples/launch_sft_<recipe>.sh |
| SFT schema | cosmos_framework/configs/toml_config/sft_config.py |
| Setup docs | docs/setup.md |
| Inference docs | docs/inference.md |
| Training docs | docs/training.md |
Start with rg in NPA:
rg -n "NPA_COSMOS3|Cosmos3|cosmos3-text-to-image|guardrails" npa
If the answer depends on upstream behavior, inspect the upstream file rather than guessing from NPA wrappers.
Keep NPA and upstream responsibilities separate. NPA owns CLI/SDK wrappers, SkyPilot workflows, image defaults, and tests. NVIDIA's repo owns Cosmos3 framework semantics, inference arguments, recipes, and training internals.
When adding docs or tests, reference SKILL.md artifacts as repository files, not as commands.