Run any Skill in Manus with one click

$pwd:

deploy-collection

Name: Deploy Collection
Author: NVIDIA-Omniverse

// Deploy the full Content Agents package with a provider-neutral, endpoint-driven, multi-instance strategy. Use when the user asks to deploy all content agents, deploy material/physics/texture together, configure shared OVRTX rendering, choose VLM/LLM/image-gen/embedding endpoints, test the full package, or use Brev as an optional self-hosted dependency provider.

Run Skill in Manus

$ git log --oneline --stat

stars:124

forks:13

updated:May 27, 2026 at 18:59

File Explorer

6 files

SKILL.md

readonly

name	deploy-collection
description	Deploy the full Content Agents package with a provider-neutral, endpoint-driven, multi-instance strategy. Use when the user asks to deploy all content agents, deploy material/physics/texture together, configure shared OVRTX rendering, choose VLM/LLM/image-gen/embedding endpoints, test the full package, or use Brev as an optional self-hosted dependency provider.
version	0.1.0
author	NVIDIA Content Agents
tags	["content-agents","collection","deployment","brev"]
tools	["Shell","Docker","Python","Filesystem"]
compatibility	Requires the repo Python environment, Docker Compose, endpoint URLs for shared dependencies, optional Brev CLI access for self-hosted dependency nodes, and provider credentials in the repo-root .env.

Deploy Content Agents Collection

When to Use

Use this skill to deploy the whole Content Agents package without Helm and without a single monolithic Compose stack.

Limitations

Keep provider credentials in the repo-root .env; never print or commit secrets.
Use Brev only when the user asks for self-hosted dependencies or a full validation topology.
Use service-specific deploy skills when debugging one agent or dependency in isolation.

Prerequisites

Repo Python environment available for deploy/collection/deploy.py.
Docker Compose available for local CPU-only service startup.
Endpoint URLs or Brev deployment plans for OVRTX, VLM/LLM, image generation, and embedding dependencies selected by the user.

Core Model

Material, Physics, and Texture Agent services are CPU-only.
OVRTX rendering is a shared GPU dependency required by Material and Physics.
VLM, LLM, image generation, and embeddings are optional model dependencies.
Dependencies are configured by endpoint URL.
Brev is optional. Use it only when the user asks for Brev or wants a full self-hosted validation topology.

Instructions

Inspect deploy/collection/collection.yaml.
Ask for missing endpoint choices only if they cannot be inferred safely.
Keep secrets in the repo-root .env; never write API keys into YAML.
Run:

./deploy/collection/deploy.py plan

If the plan is valid, start the CPU-only agents:

./deploy/collection/deploy.py up

Check status or smoke:

./deploy/collection/deploy.py status
./deploy/collection/deploy.py smoke

Commit and push coherent checkpoints when making implementation changes.

When To Read References

For env vars and endpoint wiring, read references/env-contract.md.
For choosing a topology, read references/topologies.md.
For Brev-hosted dependencies, read references/brev.md.

Existing Skills To Reuse

Use deploy-ovrtx-docker when starting or debugging a standalone OVRTX renderer.
Use deploy-qwen-vlm-brev when the user asks for a Brev-hosted Qwen VLM.
Use deploy-image-gen-brev when the user asks for a Brev-hosted FLUX image-generation endpoint.
Use deploy-embeddings-brev when the user asks for a Brev-hosted embedding endpoint for Material Agent prim clustering.
Use brev-cli when creating, listing, accessing, port-forwarding, or cleaning up Brev instances.
Use service-specific Docker skills only when debugging one agent in isolation.

Do not use Helm skills for this workflow unless the user explicitly changes the deployment target to Kubernetes/Helm.

Validation

Minimum validation for code changes:

source .venv/bin/activate
python -m py_compile deploy/collection/deploy.py
./deploy/collection/deploy.py plan
./deploy/collection/deploy.py render-env
docker compose --env-file deploy/collection/.collection.generated.env \
  -f deploy/collection/docker-compose.agents.yml config --quiet

Run Docker/Brev smoke tests only when the requested topology and credentials are available.

Output Format

Return the selected topology, generated endpoint configuration, validation commands run, service URLs or pending dependencies, and any cleanup commands.

Troubleshooting

If planning fails, report the invalid field and the config file to edit.
If Docker config or smoke checks fail, include the failing command, relevant log tail, and the next retry or cleanup command.

related-skills.json

same repository

brev-cli.md

from "NVIDIA-Omniverse/content-agents"

Manage Brev instances safely from the Brev CLI. Use when a workflow needs to list, create, access, copy to, execute on, port-forward, stop, or delete Brev instances for Content Agents dependency endpoints.

2026-05-27124

deploy-embeddings-brev.md

from "NVIDIA-Omniverse/content-agents"

Deploy or smoke-test a Brev-hosted NVIDIA embedding NIM endpoint for Content Agents. Use when the user asks to deploy embeddings on Brev, host the llama-nemotron-embed-vl model, enable Material Agent prim clustering embeddings, test embedding sidecars, or create a Brev embedding endpoint for the collection deployment.

2026-05-27124

deploy-image-gen-brev.md

from "NVIDIA-Omniverse/content-agents"

Deploy or smoke-test a Brev-hosted FLUX image-generation NIM endpoint for Content Agents. Use when the user asks to deploy image generation on Brev, host FLUX.2 Klein for Texture Agent, enable image-gen sidecars, test image-gen endpoints, or create a Brev image-gen endpoint for the collection deployment.

2026-05-27124

deploy-material-agent-brev.md

from "NVIDIA-Omniverse/content-agents"

Deploy or smoke-test the Material Agent with Brev-hosted dependency endpoints. Use when the user asks to test material agent on Brev, deploy material agent with Brev, use RTX/L40S for rendering and A100/H100-grade GPU for VLM, run a Brev hybrid material-agent test, or recreate the Brev material-agent deployment. This workflow keeps the main pipeline local and uses Brev port-forwards to reach OVRTX and Qwen-family VLM endpoints.

2026-05-27124

deploy-material-agent-docker.md

from "NVIDIA-Omniverse/content-agents"

Deploy the material-agent-service locally using Docker Compose with OVRTX rendering. Use when user wants to run material agent with docker, docker compose, set up local deployment, run the service locally with GPU rendering, start material agent containers, or configure VLM provider for docker deployment. Trigger phrases include "docker compose", "docker deploy", "run locally with docker", "start material agent docker", "docker up", "local deployment", "compose up".

2026-05-27124

deploy-ovrtx-docker.md

from "NVIDIA-Omniverse/content-agents"

Deploy just the OVRTX rendering API standalone via Docker Compose so one or more agent CLIs / services can point at it as a shared rendering endpoint. Use when user wants to run OVRTX standalone, deploy a shared rendering service, separate the rendering endpoint from an agent service, expose OVRTX to multiple callers, or set RENDER_ENDPOINT to a dedicated render host. Trigger phrases include "deploy ovrtx", "run ovrtx standalone", "shared rendering service", "ovrtx rendering docker", "render endpoint deploy", "ovrtx docker compose", "standalone rendering".

2026-05-27124

package.json

"author": "NVIDIA-Omniverse"

"repository": "NVIDIA-Omniverse/content-agents"

View GitHub Repository View Creator Repositories

$ install --global

$ download --local

Run Skill in Manus

$ useful --forSOC

Software DevelopersComputer and Mathematical Occupations15-1252L4

name	deploy-collection
description	Deploy the full Content Agents package with a provider-neutral, endpoint-driven, multi-instance strategy. Use when the user asks to deploy all content agents, deploy material/physics/texture together, configure shared OVRTX rendering, choose VLM/LLM/image-gen/embedding endpoints, test the full package, or use Brev as an optional self-hosted dependency provider.
version	0.1.0
author	NVIDIA Content Agents
tags	["content-agents","collection","deployment","brev"]
tools	["Shell","Docker","Python","Filesystem"]
compatibility	Requires the repo Python environment, Docker Compose, endpoint URLs for shared dependencies, optional Brev CLI access for self-hosted dependency nodes, and provider credentials in the repo-root .env.

Deploy Content Agents Collection

When to Use

Use this skill to deploy the whole Content Agents package without Helm and without a single monolithic Compose stack.

Limitations

Keep provider credentials in the repo-root .env; never print or commit secrets.
Use Brev only when the user asks for self-hosted dependencies or a full validation topology.
Use service-specific deploy skills when debugging one agent or dependency in isolation.

Prerequisites

Repo Python environment available for deploy/collection/deploy.py.
Docker Compose available for local CPU-only service startup.
Endpoint URLs or Brev deployment plans for OVRTX, VLM/LLM, image generation, and embedding dependencies selected by the user.

Core Model

Material, Physics, and Texture Agent services are CPU-only.
OVRTX rendering is a shared GPU dependency required by Material and Physics.
VLM, LLM, image generation, and embeddings are optional model dependencies.
Dependencies are configured by endpoint URL.
Brev is optional. Use it only when the user asks for Brev or wants a full self-hosted validation topology.

Instructions

Inspect deploy/collection/collection.yaml.
Ask for missing endpoint choices only if they cannot be inferred safely.
Keep secrets in the repo-root .env; never write API keys into YAML.
Run:

./deploy/collection/deploy.py plan

If the plan is valid, start the CPU-only agents:

./deploy/collection/deploy.py up

Check status or smoke:

./deploy/collection/deploy.py status
./deploy/collection/deploy.py smoke

Commit and push coherent checkpoints when making implementation changes.

When To Read References

For env vars and endpoint wiring, read references/env-contract.md.
For choosing a topology, read references/topologies.md.
For Brev-hosted dependencies, read references/brev.md.

Existing Skills To Reuse

Use deploy-ovrtx-docker when starting or debugging a standalone OVRTX renderer.
Use deploy-qwen-vlm-brev when the user asks for a Brev-hosted Qwen VLM.
Use deploy-image-gen-brev when the user asks for a Brev-hosted FLUX image-generation endpoint.
Use deploy-embeddings-brev when the user asks for a Brev-hosted embedding endpoint for Material Agent prim clustering.
Use brev-cli when creating, listing, accessing, port-forwarding, or cleaning up Brev instances.
Use service-specific Docker skills only when debugging one agent in isolation.

Do not use Helm skills for this workflow unless the user explicitly changes the deployment target to Kubernetes/Helm.

Validation

Minimum validation for code changes:

source .venv/bin/activate
python -m py_compile deploy/collection/deploy.py
./deploy/collection/deploy.py plan
./deploy/collection/deploy.py render-env
docker compose --env-file deploy/collection/.collection.generated.env \
  -f deploy/collection/docker-compose.agents.yml config --quiet

Run Docker/Brev smoke tests only when the requested topology and credentials are available.

Output Format

Return the selected topology, generated endpoint configuration, validation commands run, service URLs or pending dependencies, and any cleanup commands.

Troubleshooting

If planning fails, report the invalid field and the config file to edit.
If Docker config or smoke checks fail, include the failing command, relevant log tail, and the next retry or cleanup command.

deploy-collection

Deploy Content Agents Collection

When to Use

Limitations

Prerequisites

Core Model

Instructions

When To Read References

Existing Skills To Reuse

Validation

Output Format

Troubleshooting

More from this repository

Deploy Content Agents Collection

When to Use

Limitations

Prerequisites

Core Model

Instructions

When To Read References

Existing Skills To Reuse

Validation

Output Format

Troubleshooting

More from this repository