nvidia-omniverse/usd-content-agents/content-articulation-authoring
Claude Code and agent skill by nvidia-omniverse/usd-content-agents
- community
Checking that the SKILL.md file is still in the repository.
Author only approved articulation candidates, then validate saved-stage identity and joint-graph readback. Use after agent and required human review are durably bound.
Install
npx vskill@latest install nvidia-omniverse/usd-content-agents/content-articulation-authoringSKILL.md
Approved Articulation Authoring
Continue deterministic accepted-only authoring and verify the exact saved USDZ joint graph. The workflow code, not the reasoning agent, performs mutation.
When to Use
Use only after the agent decision ledger and any configured human review receipt validate against the same candidate evidence.
Limitations
- Author exactly once and only accepted native-ready candidates.
- Do not author masses or colliders in the articulation stage.
- Render evidence cannot replace saved-stage identity and graph readback.
Prerequisites
Verify the decision ledger, reviewed candidate document, review receipt when required, and approved candidate document before continuing.
Instructions
- Let the deterministic controller build the accepted-only authoring request.
- Verify authoring result IDs match approved IDs exactly.
- Reopen the saved artifact and validate source identity and complete joint
graph readback before rendering.
- Render focused validation evidence for the authored result.
- If validation fails, retain accepted work and route only failed candidate
scope through targeted reinspection in a new run or supported refinement.
- Finalize
completedonly for exact readback; otherwise retain a conditional
result with unresolved IDs and evidence.
Command Reference
After an agent patch with requested review policy none, standalone runs use _agent-apply to continue deterministic authoring. An Asset articulation.author.v1 leaf instead re-runs its same opaque content-workflow-cli articulation agentic-leaf author --invocation ... entrypoint with the exact immutable invocation. Do not import an internal Python API or create or execute a Python helper to cross either decision pause. Human-gated runs continue with the public articulation review command.
Common Workflows
In a composed asset workflow, the outer coordinator remains the only reasoning loop and re-invokes the selected Asset leaf's opaque entrypoint; it does not substitute the standalone prepare/apply surfaces.
Output Format
Retain approved candidates, receipt, authoring request/result, saved USDZ, validation evidence, checkpoint, progress, trace, and final summary.
Troubleshooting
On graph mismatch or artifact drift, keep the run for diagnosis and do not reauthor over immutable evidence. Start a new run after correcting inputs.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingagentic/.agents/skills/content-articulation-authoring/SKILL.md
Popularity
- Repository stars
- 205
- Repository forks
- 25
- 7-day trend score
- 27
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/nvidia-omniverse/usd-content-agents/content-articulation-authoring)