architecture
Use for Claude Code architectural review of the Nebius Physical AI platform, workbench layer, orchestrator choices, and partner model.
Skill by nebius
Chalk Labs
Need help deploying architecture?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/nebius-architecture
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/architecture
What's inside
- Skill name
architecture- Description
- Use for Claude Code architectural review of the Nebius Physical AI platform, workbench layer, orchestrator choices, and partner model.
- License
- Apache-2.0
- Instructions
- 41 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Architecture Context Detailed rationale and the preserved May 2026 architecture snapshot live in `docs/architecture/contributor-context.md`. The platform progression is: 1. Tools: Workbench. 2. Composition: Platform. 3. Intelligence: agentic layer. The current phase is Workbench, the Tools layer: marketplace model, pay per use, `npa` CLI/SDK/agents. The May 2026 snapshot covers LeRobot, FiftyOne, Genesis, Isaac Lab, Cosmos, LanceDB, GR00T, and SONIC. It is historical context, not the current tool count or proof that a newly built image works. Resolve current capabilities from the workflow catalog and `skills/index.yaml`; resolve image validation and publication from `npa/src/npa/deploy/images.py` and `docs/workbench/container-image-catalog.md`. New source and replacement digests need their own real capability and artifact evidence. SkyPilot is the sole orchestrator. Argo is deprecated. Partner model: partners listed in the ecosystem must run workloads on Nebius infrastructure when accessed through the platform. LeRobot connects data generation to robot policy training and is the default training framework for robot policy workflows. The sim-to-real gap is the most important and least-tooled layer. Existing approaches are either deeply custom or unproductized. ## OSS and container packaging - OSS onboarding ladder (BYOF → workflow → first-class tool): `docs/architecture/oss-onboarding-ladder.md` - Container packaging tiers and security baseline: `docs/workbench/container-packaging.md` - Machine-readable packaging contract: `npa/docker/workbench/packaging-contract.yaml` - Generic BYOF operator skill: `skills/workflows/byof-onboard/SKILL.md` (`npa workbench byof`, `npa.sdk.workbench.byof`, `workbench.byof.repo`)
From nebius/nebius-physical-ai, Apache-2.0.
More from nebius/nebius-physical-ai
- 0.666score
curobo
nebius
Use when running, validating or reviewing NVIDIA cuRobo V2 Franka pose planning and complete MotionBenchMaker/MPiNets benchmarks on CUDA, with factual…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
gpu-first-guidance
nebius
Use when recommending how to run a workbench workload, writing user-facing docs, or answering "what should I run first?" — lead with the Nebius GPU path and…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
cosmos
nebius
Use when working on Cosmos world model serving, inference, serverless training smoke validation, backend selection, or rendering limitations.
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
embodiedgen
nebius
Use when running or reviewing the operator-private EmbodiedGen V2 image-to-rigid-object workflow with upstream TRELLIS generation, URDF export, collision…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
gpu-selection
nebius
Use when choosing or reviewing GPU targets for NPA workbench tools, training, rendering, inference, or workflow YAML resources.
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
toolref-argv-contract
nebius
Use when adding or changing an npa.workflow toolRef argv template, or when changing a CLI option that a toolRef already passes — the contract that stops a…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
debug-failed-run
nebius
Use when a workflow run failed, hung, or produced no artifacts — an ordered triage from run id to root cause across status, stage logs, S3 evidence, pod-level…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
agent-development
nebius
Use when building, enhancing, or testing the NPA chat agent backend — grounded-first routing, cost-aware Token Factory model selection, the embedded-backend…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
gpu-allocation-fallback
nebius
Track typed GPU placement failures in the NPA agent and offer a consent-gated on-demand-to-preemptible fallback after repeated failures or deterministic…
SkillAFreshness: A★ 60Claude Code +9 - 0.665score
submit-workflow
nebius
Use when submitting, validating, or debugging NPA SkyPilot workflow YAMLs and workflow runner paths.
SkillAFreshness: A★ 60Claude Code +9 - 0.663score
cosmos-data-factory-setup
nebius
Prepare the shared NPA runtime, storage, credentials, and private compatibility images for Cosmos Data Factory IAA or EVG workflows on Nebius and SkyPilot.
SkillAFreshness: A★ 60Claude Code +9 - 0.663score
physical-ai-image-attribute-augmentation
nebius
Author, run, or inspect the NPA Cosmos Data Factory IAA workflow for person-image clothing, color, and footwear augmentation with attribute verification and…
SkillAFreshness: A★ 60Claude Code +9
Signals
- Stars
- 60
- Forks
- 19
- Open issues
- 10
- Last commit (this folder)
- Sep 6, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/nebius/nebius-physical-ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from nebius
- 0.666score
gpu-allocation-fallback
nebius
Track typed GPU placement failures in the NPA agent and offer a consent-gated on-demand-to-preemptible fallback after repeated failures or deterministic…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
toolref-argv-contract
nebius
Use when adding or changing an npa.workflow toolRef argv template, or when changing a CLI option that a toolRef already passes — the contract that stops a…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
agent-development
nebius
Use when building, enhancing, or testing the NPA chat agent backend — grounded-first routing, cost-aware Token Factory model selection, the embedded-backend…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
debug-failed-run
nebius
Use when a workflow run failed, hung, or produced no artifacts — an ordered triage from run id to root cause across status, stage logs, S3 evidence, pod-level…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
gpu-first-guidance
nebius
Use when recommending how to run a workbench workload, writing user-facing docs, or answering "what should I run first?" — lead with the Nebius GPU path and…
SkillAFreshness: A★ 60Claude Code +9 - 0.666score
cosmos
nebius
Use when working on Cosmos world model serving, inference, serverless training smoke validation, backend selection, or rendering limitations.
SkillAFreshness: A★ 60Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get architecture running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
architecture skill. Agent Mart. https://agentmart.dev/skills/nebius-architecture (last updated 2026-10-24)