Ce Agent Native Architecture

Routes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.

Build web interfaces with genuine design quality, not AI slop. Use for any frontend work - landing pages, web apps, dashboards, admin panels, components, interactive experiences. Activates for both greenfield builds and modifications to existing applications. Detects existing design systems and respects them. Covers composition, typography, color, motion, and copy. Verifies results via screenshots before declaring done.

Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a developer needs to save a cuPyNumeric array to an .h5/.hdf5 file, load an HDF5 dataset into a distributed cuPyNumeric array, read a large HDF5 dataset in chunks, hand arrays to an HPC pipeline as a single file, or accelerate HDF5 disk I/O with GPUDirect Storage (GDS). Do not use it for Parquet/cuDF/raw-binary or other sharded/custom layouts (see the cupynumeric-parallel-data-load skill), Zarr or object-store/S3 output, .npz or pickled archives, plain h5py without cuPyNumeric, or pure array compute such as FFT, matmul, or reductions.

Estimate the intrinsic value of a public company using DCF, relative (peer multiple) and sum-of-parts (SOTP) methods, then triangulate to an implied share price with upside/downside versus the current market price. Use this skill whenever the user asks: "what is AAPL worth", "valuation of NVDA", "fair value of TSLA", "intrinsic value", "DCF for MSFT", "build a DCF", "discounted cash flow", "WACC", "terminal value", "implied share price", "upside to fair value", "is X overvalued/undervalued", "relative valuation", "peer comparison valuation", "EV/EBITDA target", "SOTP", "sum of the parts", "how much is [company] worth", "price target from fundamentals", "value this company", or any ticker in the context of computing intrinsic or relative valuation. Default to running ALL three methods (DCF + relative + SOTP-if-applicable) and presenting a blended implied price with a sensitivity table. Do not answer valuation questions from memory — always run the workflow.

Recommend or run the exact `dotnet test` command. ALWAYS use when the user asks to run, filter, or troubleshoot .NET tests or wants the precise command, flags, or argument order — the right syntax depends on the test platform (VSTest vs Microsoft.Testing.Platform) and SDK version and is easy to get wrong from memory. USE FOR: running all tests or a subset (a specific class, category, or trait) via filters; a single framework in a multi-TFM project (`--framework`); TRX reports; crash or hang dumps; whether MTP args need the `--` separator (SDK 8/9) or pass directly (SDK 10+); diagnosing why `dotnet test` fails or uses wrong argument syntax. Detects the platform (VSTest vs MTP) and framework (MSTest/xUnit/NUnit/TUnit), then picks the matching command and filter flag (--filter, --filter-class, --filter-trait, --filter-query, --treenode-filter). DO NOT USE FOR: writing test code (use code-testing-agent), iterating on failing tests without rebuilding (use mtp-hot-reload), CI/CD config, or d

React Native and Expo development guide covering components, styling, animations, navigation, state management, forms, networking, performance optimization, testing, native capabilities, and engineering (project structure, deployment, SDK upgrades, CI/CD). Use when: building React Native or Expo apps, implementing animations or native UI, managing state, fetching data, writing tests, optimizing performance, deploying to App Store/Play Store, setting up CI/CD, upgrading Expo SDK, or configuring Tailwind/NativeWind.