agentleFS
MacroMan5MacroMan5/autotrain-yolo/.claude/skills/cvat-deploy/SKILL.md

cvat-deploy

Skill8 starsChanged 8 months agoMITView on GitHub

Deploy a trained YOLO model as a Nuclio serverless function for CVAT auto-annotation.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the best model from the latest experiment, or ask the user

    line 20
  2. Very specific:

    Check experiments/summary.md for the best-performing model path

    line 21
  3. Very specific:

    Read the generated function.yaml and confirm:

    line 33
  4. Distinctive:

    Check that the function is running.

    line 48
  5. Distinctive:

    NEVER deploy without confirming class mapping matches CVAT project labels

    line 67
  6. Distinctive:

    ALWAYS verify the ONNX export succeeded before deploying

    line 68
  7. Distinctive:

    Document the deployed model version and metrics in experiments/

    line 69
  8. Distinctive:

    If deployment fails, show the Nuclio dashboard URL for debugging (http://localhost:8070)

    line 70

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Deploy Model to CVAT

Deploy a trained YOLO model as a Nuclio serverless function so CVAT users can auto-annotate images directly from the CVAT UI.

Pre-Flight Checklist

  • Trained model exists (best.pt or user-specified)
  • Nuclio is running (check port 8070)
  • yolo-project.yaml has class definitions
  • Docker is running (required for Nuclio builds)

Workflow

1. Identify the Model

  • Use the best model from the latest experiment, or ask the user
  • Check experiments/summary.md for the best-performing model path

2. Generate Nuclio Function

yolo-cvat deploy --model <path_to_model> --name <detector_name>

This generates:

  • serverless/<name>/function.yaml — Nuclio config with class spec
  • serverless/<name>/main.py — Inference handler
  • serverless/<name>/best.onnx — Exported model

3. Verify Generated Files

Read the generated function.yaml and confirm:

  • Class names match yolo-project.yaml
  • Image name is unique
  • ONNX model was exported correctly

4. Deploy to Nuclio

Provide the command for the user to run:

nuctl deploy --path ./serverless/<name> --platform local

5. Verify Deployment

nuctl get functions

Check that the function is running.

Decision Tree

Model is .pt format?
├── Yes → Export to ONNX first (yolo-export)
└── Already .onnx → Copy directly

Nuclio reachable on port 8070?
├── Yes → Ready to deploy
└── No → Warn user, suggest checking Docker and CVAT stack

Function with same name exists?
├── Yes → Ask user: overwrite or use different name?
└── No → Deploy normally

Guardrails

  • NEVER deploy without confirming class mapping matches CVAT project labels
  • ALWAYS verify the ONNX export succeeded before deploying
  • Document the deployed model version and metrics in experiments/
  • If deployment fails, show the Nuclio dashboard URL for debugging (http://localhost:8070)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.