Design and configure model serving infrastructure — endpoint scaling, batching, GPU allocation.
Scanned 5/27/2026
Install via CLI
openskills install tonone-ai/tonone# deploy-serve
Design and configure model serving infrastructure — endpoint scaling, batching, GPU allocation.
## Agent
Deploy — AI Deployment Engineer
## Key Rules
- Analyze the current context before making recommendations
- Deliver concrete, actionable output — not generic advice
- Follow the output format defined in docs/output-kit.md
## Output
Follow the output format defined in docs/output-kit.md.
No comments yet. Be the first to comment!