技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
reference-and-backend-tests【数据与研究】Guides ONNX ReferenceEvaluator usage, reference-op behavior, backend test corpus, and bounded backend-data generation.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Use this sub-skill when a task needs to execute ONNX with the pure-Python ReferenceEvaluator, compare outputs against expected NumPy values, inspect reference operator behavior, work with the backend test corpus, or generate small backend-test data sets.
ReferenceEvaluator when you need a local execution baseline that follows ONNX semantics rather than a framework runtime.onnx[reference] only when image-decoder/reference workflows need Pillow.references/reference-evaluator.md for ReferenceEvaluator and debugging details.references/backend-test-workflows.md for backend-interface concepts and test-data generation patterns.references/troubleshooting.md before retrying a missing-op, optional-dependency, or download-based backend issue.scripts/reference_eval_smoke.py --help to see the safe tiny-model smoke options.scripts/generate_backend_test_subset.py --help to see the bounded backend-data generator options.model-authoring for creating or saving models and fixtures.validation-and-conversion for checker, parser/printer, shape inference, and opset conversion.operator-spec-maintenance when the task changes the reference operator implementations or backend node tests themselves.