612 skills · sorted by relevance
Build conversations and workflows with the Gemini Interactions API on Gemini Enterprise Agent Platform. Follow Python or JavaScript examples for server-stored conversation history, streaming responses, structured JSON output, function calls, and background agent tasks.
Test Slack authentication, message creation and cleanup, and OpenClaw message handling. Collect evidence from stored messages and test runs, while distinguishing what API checks prove from interactions that require observation in the actual Slack client.
Support drug discovery research by searching public databases for compound activity, molecular properties, drug interactions, and gene–disease associations. Assess drug-likeness, meaning how molecular properties fit established rules for potential oral medicines.
Design and implement interface responses such as button feedback, loading indicators, page transitions, and swipe gestures. Use motion to communicate actions and state changes, with guidance on timing, performance, and support for people who prefer reduced animation.
Automate browser actions such as filling forms, clicking buttons, and switching tabs. Inspect page snapshots, network requests, and console messages to check website behavior, record interactions, and support work on Playwright tests.
Design and refine web animations for buttons, dialogs, menus, and gestures. The skill guides timing, changes in speed, spring motion, performance, and reduced-motion preferences so transitions fit the interaction and remain responsive.
Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.
The English summary is being prepared. Showing the original description.
Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.
The English summary is being prepared. Showing the original description.
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. This skill covers the Interactions API, the recommended way to use Gemini models and agents in Python and TypeScript.
The English summary is being prepared. Showing the original description.
Test Discord bot access, message operations, and OpenClaw responses using leased QA bots. Collect API and Gateway evidence for replies, files, threads, reactions, streaming, and typing, while identifying interactions that require manual testing.
Add an AI assistant to an existing web app so users can operate its interface with everyday instructions. Covers embedding the panel, connecting a language model, testing interactions, and protecting API keys in production.
Integrate Firecrawl browser actions into application code to retrieve content that requires clicks, form entry, or pagination. Use it for multi-step page interactions and workflows that need to preserve the browser session after scraping.
Review a site's visual quality, find inconsistent styling, awkward spacing, unclear emphasis, repetitive AI-generated design patterns, and slow interactions. Fix the source code in focused commits and verify the changes with before-and-after screenshots.
Identify and test critical workflows where APIs, services, databases, and interface components work together. Review normal behavior, important failures, and CI checks to find gaps that isolated unit tests can miss and keep those interactions continuously verified.
Measure how quickly a webpage updates after user interactions using INP, a responsiveness metric. Identify confirmed bottlenecks and improve event handlers, split long tasks, or move heavy computation to web workers.
Record website interactions with Playwright to create demo clips, app walkthroughs, and footage for Remotion videos. The guidance covers screen dimensions, action timing, visible click effects, and converting recorded WebM files to MP4.
Turn written descriptions or Mermaid code into diagrams showing processes, interactions, and data relationships. Choose a color theme and save both SVG files, which stay sharp when enlarged, and high-resolution PNG images.
Create diagrams in Artifacts that explain data flow, system interactions, and differences between options. Guides diagram structure and inline SVG, a vector image format embedded in HTML, with readable labels and support for light and dark themes.
Prepare a design handoff package for a developer using Claude Code. It documents screen layouts, visual details, interactions, and state requirements in a README.md, alongside reference files for implementation in the target app.
Plan HyperFrames videos so motion flows continuously between scenes. Match movement direction and speed across cuts, connect actions through visible causes, and verify scene boundaries while keeping each scene active through meaningful reveals or interactions.
Build Solidity contract tests with Hardhat and Foundry. Check individual functions, contract interactions, gas usage, and varied inputs, and use a local copy of mainnet state to test against existing contracts.
Write JavaScript and TypeScript tests with Jest using consistent structure, dependency mocking, and checks for asynchronous code. Includes guidance for snapshots and React components, focusing on user interactions, accessibility, and choosing appropriate assertions for expected results.
Design, refine, or review web and iOS interfaces using the product’s existing components and visual style. Consult relevant screen examples when useful, then inspect the result for layout problems, inaccessible controls, and broken interactions.
Rebuild existing web pages as working, editable local code using their actual content and assets. Inspect desktop and mobile layouts, reproduce interactions and animations, then compare rendered pages and fix visible or functional differences.