Add V2 model integration agent skill

[jmccaffrey-nv]

Summary

• add a reusable agent skill for adding or migrating model integrations to the V2 APIs
• document PR Initial (simple) Threading Model + UI + Auxiliary Fixes #506 application, session, loop, input, presentation, and modality boundaries
• codify staged CPU/GPU, parity, WebRTC, reproducibility, and cleanup validation
• limit this PR to skills/integrate-a-model-v2/SKILL.md

Validation

• skill-creator quick_validate.py
• pytest tests/test_agent_skills.py -q (3 passed)
• git diff --check origin/main...HEAD

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[greptile-apps]

Greptile Summary

The PR adds a reusable agent skill for integrating or migrating models onto FlashDreams V2.

• Documents model-core reuse, checkpoint remapping, V2 application/session/loop boundaries, and packaging.
• Defines staged CPU, GPU, parity, WebRTC, media-output, reproducibility, and cleanup validation.

Confidence Score: 5/5

The PR appears safe to merge because no blocking failure remains.

No blocking failure remains.

Important Files Changed

Filename	Overview
skills/integrate-a-model-v2/SKILL.md	Adds the V2 model-integration workflow and validation checklist; no follow-up-eligible issue was identified.

_{Reviews (2): Last reviewed commit: "Add synchronized media integration guida..." | Re-trigger Greptile}

[jmccaffrey-nv]

/ok to test 3789872