Skills for “ui”

…SQL calls fail with auth/config errors. No MCP install…

Build AIDP agents in high-code Python with aidputils + LangGraph (the code-first alternative to the low-code agent-flow canvas). Use when the user wants to write an agent in Python, use LangGraph / create_react_agent /…

…DDL replay works around AIDP's per-statement-discard quirk. Use BEFORE aidp-migrate-job — schemas must exist before notebook…

…BEFORE you spend Pass-2 cluster time. Use after aidp-build-dag and before aidp-migrate-job, especially the first time you migrate against a target…

Build a migration manifest (the execution DAG) from a Databricks workspace path or workflow ID. Walks %run dependency chains, captures dbutils.notebook.run invocations, and emits reports/<job>_manifest.json — the input…

…Cloud workbooks from natural-language analysis requirements. It authors deterministic, template-first workbook JSON, validates visualization runtime semantics, uses governed datasource metadata when Oracle…

Guide the governed manual OAC AIDP connection and dataset checkpoint, then verify the result through OAC MCP. Use after dataset advice, when creating or reusing an OAC dataset, or before workbook authoring.

…serve a business goal and a new medallion node is…

Guide Oracle Fusion ERP, HCM, or SCM ingestion into AIDP bronze, silver, and gold layers and onward to OAC analytics. Use when the user asks where to start, wants the full bundle workflow, or needs the correct focused…

…are normal unless NVIDIA is prohibited. Exclude required cross-vendor or CPU-only deployment, vendor-lowered dense or NN layers, general Warp API questions, and already-selected Warp kernels. Contribution…

…make that leap. Not for forward-only Warp work, build/install problems, or autograd issues in other frameworks without…

…Not for steady-state kernel runtime, memory, correctness, building Warp itself from source, or nvcc/C++ build…

…through a customizable, self-contained vision stack built on the NVIDIA VSS Blueprint. Use this skill when a developer or agent wants to give their app vision: pick capabilities via guided intake ("build a vision…

…prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers`…

…(ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting,…

…Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type…

…instance, and panoptic masks) with occupancy completion. Built on a VGGT backbone with a Mask2Former-style head and 3D frustum reconstruction. Use when training, evaluating, exporting, or running inference for a TAO…

…with a mask-prediction head for open-set segmentation guided by text prompts. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Mask-Grounding-DINO model. Trigger phrases include…

…detection with a BERT text encoder for language-guided detection — detects objects described by text prompts without a fixed class vocabulary. Use when training, evaluating, exporting, quantizing, or running…

…tao_automl, bayesian search, hyperband, ASHA, LLM-guided search, autoresearch, or wants to tune train/evaluate/inference/distill/prune/quantize for a TAO network. Model actions use the resolved image; venv…