yuyanghu06
11 verified skills
cuyamaca-code-generation
Build the code generation and diff review workflow for Cuyamaca — the code model generates Arduino sketches from manifests, displays them with highlighted diffs, and synthesizes tool definitions from the sketch. Use this skill whenever the user wants to implement sketch generation, build the code view with diffs, add the approve/reject workflow, implement tool synthesis, add sketch upload support, or references "phase 4", "code generation", "sketch generation", "code view", "diff view", "approve flash", "tool synthesis", "code model integration", or "sketch upload". Also trigger when the user asks about prompting the LLM for Arduino code, structured diff display, or generating tools.json from a sketch. This skill assumes Phase 3 is complete (project system, manifest editor, component library).
tools
cuyamaca-frontend
Design and build frontend interfaces for the Cuyamaca project using its exact design language: warm white liquid glass surfaces, sunset color palette drawn from Mt. Cuyamaca (amber gold, dusty rose, violet-slate, deep sky blue, granite white), and an industrial-technical aesthetic softened by warm natural light. Use this skill whenever building or styling any Cuyamaca UI component, view, or artifact — including the project editor, runtime window, parts panel, code view, serial monitor, settings, or any new surface. Also trigger when the user asks about Cuyamaca's color scheme, design tokens, glass treatment, or visual language. ALWAYS consult this skill before writing any Cuyamaca CSS, Tailwind classes, or component markup.
development
cuyamaca-installer
Build the native installers (macOS .dmg, Windows .exe/.msi) and the in-app first-run dependency installation wizard for Cuyamaca, the Tauri v2 Arduino control app. Use this skill whenever the user asks to build installers, set up distribution, create a .dmg or .msi, implement the first-run experience, auto-install Ollama or arduino-cli, build a setup wizard, handle dependency detection, manage child processes for Ollama, or anything related to packaging, bundling, or distributing Cuyamaca. Also trigger for "first launch", "onboarding flow", "dependency check", "auto-install", "process lifecycle", or "app distribution". This skill covers both the Tauri bundler configuration for producing native installers AND the Rust/React code for the in-app dependency wizard that runs on first launch.
tools
cuyamaca-project-manifest
Build the project system and manifest editor for Cuyamaca — project CRUD, the manifest data model, the parts editor UI with component picker, and pin assignment editing. Use this skill whenever the user wants to create the project system, build the manifest editor, implement the parts panel, add the component picker, set up the hardware definition workflow, or references "phase 3", "project system", "manifest", "parts editor", "component picker", "hardware definition", "pin assignment", or "add component". Also trigger when the user asks about the manifest JSON schema, component types, project file structure, or how to define board configurations. This skill assumes Phase 2 is complete (LLM abstraction layer with provider trait and model slots).
development
cuyamaca-readme
Write the user-facing README.md for the Cuyamaca Tauri v2 desktop app (natural language Arduino/robotics control). Use this skill whenever the user asks to create, write, draft, or update the README for Cuyamaca, or mentions "readme", "documentation", "project description", "repo docs", or "GitHub page" in the context of Cuyamaca. Also trigger when the user asks about what to put in the README, how to describe the project publicly, installation instructions for end users, or setup guides. This skill produces a polished, user-facing README — not developer docs or architecture specs.
development
cuyamaca-scaffold
Scaffold a Tauri v2 desktop app for the Cuyamaca project — an Arduino robotics controller with natural language control. Use this skill whenever the user wants to initialize the Cuyamaca project, set up the Tauri v2 scaffold, create the base layout and warm-white liquid glass UI theme, verify the IPC bridge, or references "phase 1", "scaffold", "project setup", "initialize Cuyamaca", "create the app skeleton", or "base layout". Also trigger when the user asks about Cuyamaca's three-panel layout, the warm-white glass design language, or setting up the Tauri project structure from scratch.
testing
cuyamaca-settings-polish
Build the Settings view and apply final polish to Cuyamaca — model configuration UI, API key management, process health monitoring, accessibility improvements, responsive refinements, and overall UX tightening. Use this skill whenever the user wants to build the settings view, configure model providers in the UI, add API key entry, polish the app's responsiveness, improve accessibility, refine animations, add keyboard navigation, or references "phase 8", "settings", "settings view", "API key management", "model configuration", "accessibility", "polish", "keyboard navigation", or "responsive refinement". Also trigger when the user asks about WCAG compliance for glass effects, reduce transparency mode, or the settings UI for Cuyamaca. This skill assumes Phase 7 is complete (runtime agent loop, all core functionality working).
development
cuyamaca-serial-sensors
Build serial communication, structured output parsing, sensor state management, and sensor visualization rendering for Cuyamaca. Use this skill whenever the user wants to implement serial port reading/writing, parse structured sensor output, build the sensor state panel, render sensor visualization images, manage the serial connection lifecycle, or references "phase 6", "serial communication", "serial port", "sensor parsing", "sensor state", "sensor visualization", "structured output", "serial monitor", or "serial reader". Also trigger when the user asks about the SENSOR_ID:VALUE protocol, concurrent serial read/write, sensor image rendering, or real-time state updates. This skill assumes Phase 5 is complete (arduino-cli integration, compile and flash working).
tools
cuyamaca-runtime-agent
Build the runtime agent loop for Cuyamaca — the agentic control loop where the runtime model reads sensor context, decides tool calls, writes serial commands, and iterates until the user stops it. Use this skill whenever the user wants to implement the runtime window, build the agent loop, assemble multimodal context for the runtime model, implement tool call dispatch via serial, add the kill button, or references "phase 7", "runtime agent", "agent loop", "runtime window", "runtime model", "tool calling", "kill button", "agentic loop", "multimodal context", or "control loop". Also trigger when the user asks about feeding sensor data to a vision model, executing tool calls as serial commands, or the observe-decide-act cycle. This skill assumes Phase 6 is complete (serial communication, sensor parsing, sensor visualization).
tools
cuyamaca-llm-abstraction
Build the multi-provider LLM abstraction layer for Cuyamaca with two independent model slots — a code model and a runtime model. Use this skill whenever the user wants to add LLM provider support, integrate Ollama or external APIs (OpenAI, Anthropic, Google, Mistral), set up the two-model-slot architecture, implement streaming chat with multiple providers, or references "phase 2", "LLM abstraction", "model providers", "code model", "runtime model", "multi-provider", or "Ollama integration" in the context of Cuyamaca. Also trigger when the user asks about supporting multiple LLM backends, API key storage in OS keychain, or model selection logic. This skill assumes Phase 1 is complete (Tauri v2 scaffold, IPC bridge verified, three-panel layout).
development
cuyamaca-arduino-flash
Integrate arduino-cli into Cuyamaca for compiling and flashing Arduino sketches to boards. Use this skill whenever the user wants to add board flashing, integrate arduino-cli, implement the compile and upload workflow, detect connected boards, manage arduino-cli as a child process, or references "phase 5", "arduino-cli", "flash", "compile", "upload sketch", "board detection", or "flashing workflow". Also trigger when the user asks about arduino-cli commands, board FQBN strings, core installation, or the compile-flash pipeline. This skill assumes Phase 4 is complete (code generation, sketch approval, tools.json).
tools