Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Work on N.E.K.O plugins end to end. Use when the user asks to create, modify, review, run, debug, inspect, document, validate, package, or reason about N.E.K.O plugins, plugin.toml, plugin SDK usage, plugin UI surfaces, plugin CLI tooling, plugin runtime behavior, or plugin system contracts.
Generate PR descriptions for Dynamo that align with the team template section names and order. Use this skill whenever writing a pull request description, cleaning up a PR body, or generating a review-ready summary from a diff in the Dynamo repo. Also use when the user says "write a PR", "PR description", or "prep this for review."
Scaffolds a new Dynamo package repo that hosts a view extension with a WebView2-embedded React frontend. Use when setting up a new repo following the Switchboard pattern — Dynamo package structure, build pipeline, system tests, and bidirectional C#/TypeScript messaging.
Consumer-side guide for integrating @lodev09/react-native-true-sheet into a React Native app. Use this skill whenever the user wants to add, configure, control, or debug a bottom sheet using TrueSheet — including ref-based sheets, named global sheets, web support with TrueSheetProvider/useTrueSheet, React Navigation or Expo Router sheet flows, Reanimated-driven animations, scrolling content, stacking, headers/footers, detents, side sheets, keyboard handling, dimming, liquid glass, and Jest testing. Also use when the user is migrating from v2 to v3, troubleshooting layout or gesture issues, or asking about any TrueSheet prop, event, or method — even if they don't mention "TrueSheet" by name but describe a bottom sheet in a React Native context.
Best-practice guide for authoring a Muxy extension — how it should look and behave so it reads as a native part of the app. Covers theming (follow the theme, never hardcode colors), the sizing scale, and which surface to use. Mechanics (manifest fields, permissions, the window.muxy API) live in the linked docs.
Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend. Use when the user wants to adapt a pre-trained DPA3 model to a new downstream dataset. Supports fine-tuning from a self-trained DPA3 model (.pt checkpoint), from a multi-task pre-trained model, or from a built-in pretrained model downloaded via `dp pretrained download` (e.g., DPA-3.1-3M, DPA-3.2-5M, DPA-3.3-1M). Covers single-task and multi-task fine-tuning workflows.
Train DeePMD-kit models with progressive disclosure. Use when the user wants to train a DeePMD-kit potential, prepare an input.json, choose between model families such as se_e2_a/DeepPot-SE and DPA3, run `dp train`, monitor learning curves, freeze checkpoints, or test trained models. Start with model selection and read only the selected model reference under `models/` when model-specific configuration is needed.
Guides through adding a new descriptor type to deepmd-kit. Covers implementing in dpmodel (array-API-compatible), wrapping for JAX/pt_expt backends, hard-coding for PT/PD, registering arguments, and writing all required tests.
Compile PHP.wasm main modules and side modules (dynamic extensions) for Node.js and web platforms. Use when recompiling PHP, adding Emscripten flags, modifying Dockerfiles, building extensions as SIDE_MODULE, upgrading Emscripten, or troubleshooting compilation failures.
V8-based lightweight edge functions on EdgeOne Makers. Covers routing, KV storage access, request/response handling, and environment variables at the edge.