191 skills ・ Official · Google · sorted by popularity
Create and update shared design rules in Stitch, including colors, fonts, and corner shapes, then apply them to existing screens. Keep a DESIGN.md file and project metadata alongside the design system.
Create walkthrough videos from Stitch app screens using Remotion. Arrange screenshots in sequence, add fades, slides, zoom effects, and explanatory text, then preview the timing and render a video such as an MP4.
Turn Stitch HTML designs into React Native screens and reusable components, or update existing components to match newer designs. Extract shared style values, implement layouts with StyleSheet, and organize navigation, data, and interaction logic.
Turn site requirements or existing content into a SITE.md project guide for the Stitch Build Loop. It records the site's purpose, visual direction, navigation, file structure, and prioritized tasks to guide successive development rounds.
Convert an existing frontend into a Stitch design by extracting a standalone HTML file and shared design rules, then uploading both to a project so you can revise the interface in Stitch.
Upload local images, HTML pages, and Markdown design documents to a Stitch project. The included Python script sends files directly over HTTP, avoiding the text output limits that can interrupt transfers through MCP tools.
Analyze existing Stitch screens and document their colors, typography, components, and layout in DESIGN.md. The resulting design reference combines plain visual descriptions with precise color values to guide requests for new screens.
Build a website one page at a time with Stitch. Each round reads a task file, generates and integrates a page, updates the site plan, and leaves instructions for the next round.
Create and refine screen designs in Stitch from text descriptions or images. The skill clarifies layout requirements, edits existing screens, explores alternative designs, and saves HTML and screenshots for review.
Turn a rough interface idea into a structured prompt for Stitch, with clear page sections, colors, and component details. When available, existing design rules are included to guide consistent screens or focused edits.
Save a rendered web application view as static HTML with embedded styles and images. Capture a specific page or interface state for sharing or Stitch upload, using Puppeteer or an interactive browser capture workflow.
Turn Stitch designs into React and Vite dashboards with reusable components and asynchronous data fetching. It applies shared design settings from DESIGN.md, includes accessibility checks, and supports optional blockchain data reads.
Evaluate AI agents by preparing test cases, scoring responses and tool use, investigating failures, and comparing results after changes. Supports built-in checks and custom scoring rules, including evaluations performed by a language model.
Guide development of a LangChain or LangGraph project created with agents-cli. It explains tool additions, local runs, evaluation, and serving while identifying the required graph structure and commands that differ from ADK projects.
Find API patterns and examples for coding agents with ADK, the Agent Development Kit. Covers tools, state, callbacks, multi-agent coordination, and graph workflows, with Python and Go references plus guidance on studying existing implementations.
Guide AI agent development from requirements and project setup through implementation, behavior evaluation, deployment, and monitoring. Provides coding rules, debugging steps, and links to specialized skills so each phase follows a defined process.
Register a deployed agent with Gemini, choose the appropriate registration method, and troubleshoot setup problems. Also covers managing agents and registering MCP servers, which expose tools to agents, in Google Cloud Agent Registry.
Plan and carry out agent deployments on Google Cloud using agents-cli. The guide covers deployment targets, permissions, secrets, automated build and deployment pipelines, verification, and recovery procedures for agents built with supported frameworks.
Set up monitoring for deployed agents to inspect execution paths, latency, and model interactions. It explains Cloud Trace, prompt and response logging, BigQuery analytics, and external monitoring integrations, with checks for missing data and unwanted content capture.
Create starter projects for AI agents, add deployment configuration and automated build and release pipelines to existing projects, or update generated project files. Supports Python and Go ADK templates and a prototype-first approach.
Build applications that exchange live audio, video, and text with the Gemini Live API. Covers voice conversations, streaming transcription and translation, session recovery, authentication, and migration from older Live models in Python or JavaScript/TypeScript.
Implement Gemini API applications in Python or TypeScript for text, image, video, and speech generation. Covers ongoing conversations, external tool calls, structured responses, background research, managed agents, and migration from the older generateContent API.
Generate videos from text or images, edit existing clips, and extend scenes with Gemini Omni 1.1 Flash. Includes scripts for preparing source footage, regenerating audio, refining previous results, and processing multiple video jobs.