// Analyze a HuggingFace model and attempt OpenVINO conversion — probe properties, run strategy matrix, classify failures, and produce a structured routing report.
| name | analyze-and-convert |
| description | Analyze a HuggingFace model and attempt OpenVINO conversion — probe properties, run strategy matrix, classify failures, and produce a structured routing report. |
When you have a model ID (or local path) and need to determine whether it converts to OpenVINO IR, identify why it fails, and emit routing signals for the next agent in the pipeline.
Execute in strict order — each step produces files consumed by the next.
| Step | File | Purpose |
|---|---|---|
| 1 | probe-model.md | Gather model profile (architecture, task, op types) without downloading weights |
| 2 | try-conversion.md | Run conversion strategy matrix (optimum-cli / ovc / convert_model), capture all outputs |
| 3 | classify-failure.md | Map errors to taxonomy, extract missing_op / shape_inference / accuracy signals (skip on full success) |
| 4 | build-report.md | Assemble structured report, emit <!-- agent-result --> marker for orchestrator |
Adds a core operator to the OpenVINO toolkit. Use when asked to implement a new operation into OpenVINO.
Add a new operation to the OpenVINO CPU plugin — node registration, JIT/oneDNN executors (AVX2/AVX-512/AMX), and functional tests.
Adds a new operation to OpenVINO Frontend pipelines with translator updates, registration, and tests.
Adds a new OpenVINO fusion transformation (subgraph to one or several operations) and corresponding tests.
Add a new operation to the OpenVINO GPU plugin — OpenCL kernel design, oneDNN-backed paths, sub-group/LWS tuning, and functional tests.
Investigate and fix model conversion issues in OpenVINO Frontends (ONNX, PyTorch) — triage, debugging, accuracy comparison, and pre-submission verification.