Skill Claude CodeCodex
Use when building, enhancing, or testing the NPA chat agent backend — grounded-first routing, cost-aware Token Factory model selection, the embedded-backend mechanism, and cheap-token test tiers.
Skill Claude CodeCodex
Use when collecting NPA agent work for fine-tuning or evaluation so every goal-level episode emits a sanitized, outcome-linked trajectory to an append-only S3 dataset in an operator-specified Nebius tenant and bucket.
Skill Claude CodeCodex
Use when the NPA agent should describe or critique the current viewer (Rerun, video, image, or data) via the Describe this control or multimodal chat.
Skill Claude CodeCodex
Use for Claude Code architectural review of the Nebius Physical AI platform, workbench layer, orchestrator choices, and partner model.
Skill Codex
Reconcile NPA container-image catalogs and related documentation whenever a workbench image or solution is added, removed, renamed, retagged, republished, reclassified, or materially changed. Use for docs/workbench/container-image-catalog.md drift, public-release inventory checks, and image or solution onboarding.
Skill Claude CodeCodex
Use when building, tagging, validating, or publishing NPA workbench container images through immutable full-SHA public development tags and digest-identical supported GHCR releases.
Skill Claude CodeCodex
Use when navigating the Cosmos3 integration in NPA or locating upstream Cosmos3 framework files, defaults, scripts, configs, recipes, and docs.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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 reasons, and the resume-vs-cancel decision.
Skill Claude CodeCodex
Use when discovering or loading run artifacts in npa agent without workflow/type/path allowlists.
Skill Codex
Track typed GPU placement failures in the NPA agent and offer a consent-gated on-demand-to-preemptible fallback after repeated failures or deterministic preflight. Use when quota, capacity, Unschedulable GPU, or compatible-product placement blocks an allocation.
Skill Claude CodeCodex
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 keep hosted-inference options framed as what they are, rather than as ways to avoid GPUs.
Skill Claude CodeCodex
Use when choosing or reviewing GPU targets for NPA workbench tools, training, rendering, inference, or workflow YAML resources.
Skill Claude CodeCodex
Use when a guardrail test or CI gate in npa fails and you need to map the failure to its cause and fix rather than reverse-engineering the assertion.
Skill Claude CodeCodex
Use before any deploy, image build, or GPU submit to prove credentials and gated-model access up front with npa workbench health preflight and npa workbench health access, instead of discovering a missing token mid-run.
Skill Claude CodeCodex
Use when writing or modifying npa CLI commands or SDK functions — registration, option naming, path contract, output format, error handling, exit codes, the decorators that are easy to forget, and config/credential access.
Skill Claude CodeCodex
Use for Claude Code reviews that need robotics, simulation, GPU-routing, sim-to-real, or BDD100K pipeline domain context.
Skill Codex
Use when preparing commits, documentation, reports, examples, tests, pull-request bodies, issues, or live-validation handoffs involving Nebius, to prevent concrete live infrastructure details or credentials from reaching Git or public collaboration surfaces.
Skill Claude CodeCodex
Use when authoring or reviewing an NPA workbench pipeline/blueprint that advertises specific components (Cosmos Transfer, Cosmos Evaluator, Cosmos Curator, FiftyOne, VLM eval, etc.) — ensure every advertised stage invokes the REAL component, not an echo/manifest stub masquerading as real work.
Skill Claude CodeCodex
Use during Claude Code reviews to classify API, IAM, cleanup, exception, concurrency, config, temp-file, and version-pin risks.
Skill Codex
Use whenever an NPA container image is built, tagged, pushed, copied, or promoted, including public full-SHA development builds, release publication, build scripts, and image-producing GitHub Actions workflows. Enforce mandatory safety gates and refuse insecure or restricted publication.
Skill Claude CodeCodex
Use when adding, onboarding, or repackaging any solution, tool, container image, model, weights, dataset, or runtime cache; classify each artifact separately, keep restricted weights out of images, design safe runtime caching, and record redistribution decisions where guards enforce them.
Skill Claude CodeCodex
Use when submitting, validating, or debugging NPA SkyPilot workflow YAMLs and workflow runner paths.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: