openvinotoolkit
- 38 skills
- 0 followers
- 8 hours ago last updated
- ▌
- ▌ Workflow Writer · openvinotoolkitStandardize GitHub Actions workflows with minimal functional changes.
- ▌ Tokenizer Checker · openvinotoolkitValidate a HuggingFace tokenizer with OpenVINO Tokenizers and OpenVINO GenAI. Use when: checking if a tokenizer converts and works correctly, verifying tokenizer/detokenizer accuracy, testing normalization steps, checking GenAI Tokenizer compatibility.
- ▌ Tokenizer Fix Python · openvinotoolkitFix Python conversion issues in OpenVINO Tokenizers. Use when: tokenizer-diagnostics reports root_cause_location=python, unsupported types need new handlers in hf_parser.py, pipeline step mapping or merging is incorrect, tokenizer_pipeline.py step classes need fixes.
- ▌ Tokenizer Diagnostics · openvinotoolkitDiagnose tokenizer conversion issues for OpenVINO Tokenizers. Use when: tokenizer-checker reports failures, need to pinpoint root cause location (Python conversion vs C++ operation), identify which pipeline stage diverges, determine whether to use tokenizer-fix-python or tokenizer-fix-cpp skill.
- ▌ Physicalai Runtime Working With Config · openvinotoolkitWorks with physicalai.config (Config recipes, export_config, jsonargparse, YAML). Use when editing src/physicalai/config, class_path YAML, runtime or policy construction, or docs under docs/how-to/config and docs/explanation/configuration.md. Runtime owns this module; Studio imports it from physicalai.
- ▌ Physicalai Runtime Adding A Camera Backend · openvinotoolkitAdds or modifies a camera backend under physicalai.capture. Use when implementing a new Camera type, extending create_camera in src/physicalai/capture/factory.py, discovery helpers, optional pip extras for vendor SDKs, SharedCamera transport, or tests under tests/unit/capture with fake devices.
- ▌ Physicalai Runtime Running Policy On Robot · openvinotoolkitRuns exported policies on hardware with PolicyRuntime, execution modes, and physicalai run. Use when wiring PolicyRuntime, SyncExecution or RTC execution, runtime YAML configs, action queues, runtime callbacks, or docs/how-to/runtime run-policy-on-robot and execution modes.
- ▌ Physicalai Runtime Adding A Robot Integration · openvinotoolkit bundleAdds or modifies robot hardware integrations under physicalai.robot. Use when implementing the Robot protocol, SO101 or Trossen WidowX drivers, robot connect helpers, verify.py checks, optional extras so101 or trossen, or tests in tests/unit/robot.
- ▌ Physicalai Runtime Loading Exported Policies · openvinotoolkit bundleLoads and validates policies exported from Physical AI Studio for Runtime deployment. Use when working on InferenceModel, InferenceModel.from_pretrained, manifest.json, adapter auto-detection (onnx, openvino), backend/device kwargs, Hugging Face Hub policy packages, or the Runtime side of the export/load contract that Studio produces with physicalai export.
- ▌ Physicalai Runtime Configuring Inference Pipeline · openvinotoolkitConfigures preprocessors, postprocessors, and runners around InferenceModel via manifest specs and ComponentRegistry. Use when editing physicalai.inference.preprocessors or postprocessors, manifest preprocessor/postprocessor lists, instantiate_component, registered type names, or class_path init_args for inference pipeline components.
- ▌ Open Pr · openvinotoolkitOpen a pull request to openvinotoolkit/openvino.genai. Use when: submitting changes, creating PR, opening pull request, pushing work for review, finalizing a task with a PR.
- ▌ Update Docs · openvinotoolkitUpdate OpenVINO GenAI site documentation for API or feature changes. Use when: new pipelines, models, or use-cases are introduced; site docs need to reflect new capabilities.
- ▌ Model Checker · openvinotoolkit bundleValidate a newly supported optimum-intel model with OpenVINO GenAI. Use when: checking new model support, verifying model export to OpenVINO IR, running GenAI inference test with llm_bench, benchmarking model accuracy with who-what-benchmark.
- ▌
- ▌ Wwb Fail Analyzer · openvinotoolkitAnalyze results of WWB execution with a specific model with all possible backends. Use when: checking wwb logs, troubleshooting wwb fails.
- ▌ Generate Release Notes · openvinotoolkit bundleGenerate OpenVINO GenAI release notes from commits since the latest release. Use when: preparing release notes, summarizing a release branch, or comparing the latest release tag with the current release branch.
- ▌ LLM Bench Fail Analyzer · openvinotoolkitAnalyze failed llm_bench execution results for a model. Use when: checking llm_bench log, troubleshooting llm_bench fails.
- ▌ Ov Debug · openvinotoolkit bundleTroubleshooting all sorts of failures, crashes, exceptions and errors using debug capabilities. Analyze accuracy, performance, model compilation, or memory issues. Dump tensors and intermediate blobs. Serialize and visualize IRs, execution graphs. Enable verbose, logging. Profile execution. Compare layer outputs. Inspect, trace or dump transformations. Identify executed operations, nodes, primitives, kernels.
- ▌ Ov Gguf Enable Op · openvinotoolkitEnable a ggml operation in the OpenVINO GGUF frontend by adding or fixing an op translator. Use when conversion fails with "Translation for operation type GGML_OP_* is not implemented", when the user asks to add/implement/fix a GGUF or ggml op translator or an op_case, or when working on src/frontends/gguf/src/op/. Do NOT use for enabling a new model architecture (that is usually just a name in arch_registry.cpp), for wrong numerical output from an op that already converts, or for GGUF quantization format work.
- ▌ Ov Agentic Workflows · openvinotoolkitAuthor, edit, compile, validate, and debug any OpenVINO gh-aw agentic workflow (e.g. ci-doctor, ci-doctor-mq, and any future ones) and their shared safe-output jobs under .github/workflows/shared/agentic-workflows. Use when a user wants to create a new agentic workflow; change an existing one's prompt, triggers, tools, permissions, or safe-outputs; add or edit a shared job/step; recompile a .lock.yml; update a workflow's persisted-state JSON schemas; or test a workflow via workflow_dispatch. Do NOT use for regular (non-agentic) GitHub Actions workflows, plugin/runtime code, or diagnosing a specific live CI failure.
- ▌ Ov Github Actions CI · openvinotoolkitAuthor, edit, debug, and review the OpenVINO GitHub Actions CI infrastructure — regular (non-agentic) workflows under .github/workflows, reusable job_*.yml workflows, custom composite actions under .github/actions, CI helper scripts under .github/scripts, Dockerfiles under .github/dockerfiles, and the Smart CI / labeler / components configuration. Use when a user wants to add or change a build/test job or step, create or modify a reusable workflow, write or fix a custom action, adjust runners/containers/caches, wire up Smart CI for a component, pin action versions, fix workflow permissions/security, or debug a failing CI workflow's YAML. Do NOT use for gh-aw agentic workflows (*.md with gh-aw frontmatter — use ov-agentic-workflows), for diagnosing a specific product/test failure's root cause in C++/Python code, or for non-CI GitHub configuration.
- ▌ Ov Debug Matcher Pass · openvinotoolkit bundleDebug why an OpenVINO MatcherPass transformation is not firing. Use this skill immediately when a user says a transformation is "not applied", a "pass has no effect", a "matcher never triggers", a pattern "doesn't match", a "callback never fires", "WrapType predicate is too strict", a subgraph "not fused" despite the pass being registered, or they see "END: PATTERN DIDN'T MATCH" in matcher logs. Also trigger when a MatcherPass works on one model but silently skips another, when the user wants to add a reproducer test for a transformation that should fire but doesn't, or when they suspect an opset version mismatch preventing a match. Do NOT trigger for: writing a new MatcherPass from scratch, debugging a pass that fires but produces wrong numerical results, crashes in pass registration, or general questions about what MatcherPass is.
- ▌ Ov Ensure Coding Style · openvinotoolkitDetect and fix clang-format, clang-tidy, and copyright header violations in an OpenVINO C++ codebase. Use when the user complains about code style or formatting, asks to clean up changes, fix linting, add a copyright header, or when a style check or linting CI job is failing. Do not use for build errors, compilation failures, linker errors, test failures, runtime crashes, accuracy issues, or CMake config problems.
- ▌ Ov Gguf Debug Accuracy · openvinotoolkitDebug wrong or degraded output from a GGUF model running through the OpenVINO GGUF frontend or the ggml-openvino backend. Use when a GGUF model converts but produces garbage, repeated or drifting tokens, a cosine-similarity cliff between layers, output that diverges from llama.cpp CPU, or a broadcast/shape crash that appears only at decode or only for one architecture. Do NOT use for ops that fail to convert at all ("Translation for operation type ... is not implemented"), or for build and CMake failures.
- ▌ Ov Transformation Tests · openvinotoolkitWrite unit tests for OpenVINO ov::Model graph transformations (passes). Use when the user asks to write, add, or refactor tests for a transformation pass (MatcherPass, ModelPass), or to modernize legacy transformation tests.
- ▌ Ov Gguf Add Architecture · openvinotoolkitEnable a new model architecture/family in the OpenVINO GGUF frontend's native .gguf builder, or check whether a GGUF model is supported. Use when the user asks to enable, support or bring up a GGUF/llama.cpp model (llama, qwen, phi, gemma, MoE and similar decoder-only families), when a .gguf file is rejected as an unsupported architecture, or when working on arch_registry / DecoderBuilder in src/frontends/gguf/src/builder/. Do NOT use for adding a single ggml op translator or for debugging wrong output from an already-supported model.
- ▌ Ov Update Pytorch Version · openvinotoolkitUpgrade the PyTorch version used by OpenVINO tests (torch / torchvision / torchaudio) and resolve fallout — missing operator translators, new functionalized `*_copy` aten ops, decomposition changes, FX-only tests failing in TorchScript mode, and accuracy regressions caused by stricter typing. Use when the user asks to "bump torch", "update pytorch to X.Y", "upgrade torch tests", or when pytorch_tests / model_hub pytorch tests fail after a torch version change. Do not use for: enabling a single new PyTorch operator unrelated to a version bump, GenAI / Optimum upgrades, or plugin-level numerical bugs unrelated to the frontend.
- ▌ Add Fe Op · openvinotoolkit bundleAdds a new operation to OpenVINO Frontend pipelines with translator updates, registration, and tests.
- ▌ Add Cpu Op · openvinotoolkit bundleAdd a new operation to the OpenVINO CPU plugin — node registration, JIT/oneDNN executors (AVX2/AVX-512/AMX), and functional tests.
- ▌ Add Gpu Op · openvinotoolkit bundleAdd a new operation to the OpenVINO GPU plugin — OpenCL kernel design, oneDNN-backed paths, sub-group/LWS tuning, and functional tests.
- ▌ Add Core Op · openvinotoolkit bundleAdds a core operator to the OpenVINO toolkit. Use when asked to implement a new operation into OpenVINO.
- ▌ Submit Draft Pr · openvinotoolkitOptionally create a draft PR to the upstream repo from a local source directory. Used by coding agents when a local source path is available in the context file.
- ▌ Python Bootstrap · openvinotoolkitInstall Python dependencies before running verification or test steps. Choose the correct path depending on whether the agent builds OpenVINO from source or not.
- ▌ Conversion Issues · openvinotoolkit bundleInvestigate and fix model conversion issues in OpenVINO Frontends (ONNX, PyTorch) — triage, debugging, accuracy comparison, and pre-submission verification.
- ▌ Verify Conversion · openvinotoolkitE2E gate — verifies that applied patches produce a working, numerically sane end-to-end inference through the OpenVINO plugin. Handles HuggingFace/optimum-intel, native OV conversion (ovc/convert_model), and ONNX. Used by orchestrators as the mandatory gate before any PR is published.
- ▌ Analyze And Convert · openvinotoolkit bundleAnalyze a HuggingFace model and attempt OpenVINO conversion — probe properties, run strategy matrix, classify failures, and produce a structured routing report.
- ▌ Add Fusion Transformation · openvinotoolkit bundleAdds a new OpenVINO fusion transformation (subgraph to one or several operations) and corresponding tests.