585 skills · sorted by relevance
Capture UI journeys in Daytona as labeled screenshots and optional video clips. Organize them into a browsable HTML page for PR presentations, helping reviewers follow user actions and compare behavior before and after a change.
Build applications that use Polymarket market data and trading APIs. The skill guides live monitoring through WebSocket connections, which receive ongoing updates, including trades, orders, market comments, and cryptocurrency prices.
Build Python applications that collect live cryptocurrency prices, trades, and order books with Cryptofeed. Covers consistent data formats across exchanges, price comparisons, and writing incoming data to storage systems for monitoring and analysis.
Reserve remote Android devices on Google's Developer Device Platform and connect through ADB, Android's device control tool. Check session status and expiration, extend usage time, or cancel sessions and release resources.
Generate PDF documents from JSON definitions with headings, tables, images, and page numbers. Use file, in-memory, or streaming output, and extend document layouts with custom components and externally managed application state.
Receive live Lark/Feishu updates for messages, approvals, tasks, meetings, and more. Stream them as NDJSON, one JSON record per line, with filtering and time or event limits for bots and automated event processing.
Build charts with TradingView's lightweight-charts, including candlesticks, lines, live updates, scales, and annotations. Guidance checks installed types and v5 APIs to support chart integration, framework lifecycle handling, and troubleshooting of common data and display issues.
Start, inspect, and stop a CARLA UE 5.8 server. Choose an editor-based server, packaged build, or full editor; configure headless operation and ports; and enable native ROS 2 integration when the build supports it.
Inspect a vehicle or another object in a running CARLA simulation. Read position, speed, and acceleration from the same simulation frame, check vehicle controls and steering angle, or stream the object's state over time.
Build workflows that extract structured data from LLM responses, check field types and values with Pydantic, and retry failed extractions. Includes examples for nested data, classification, and receiving results as they are generated.
Build data processing pipelines for machine learning, from preprocessing to batch predictions. Uses Ray Data to handle datasets larger than memory, distribute work across CPUs and GPUs, and feed data into training frameworks.
Implement Mamba, a model architecture that processes sequences through an internal state with computation scaling linearly with input length. Covers pretrained text generation, Mamba-1 and Mamba-2 configuration, speed comparisons with Transformers, and GPU memory troubleshooting.
Guides you through setting up RWKV, generating text, processing long documents in chunks, and fine-tuning models. Explains how to carry context between steps and compare memory use with Transformer models.
Build Next.js 14+ applications with App Router, server-rendered components, and form actions. Produces routes, page layouts, data fetching, loading and error states, and SEO metadata, while supporting performance optimization and deployment preparation.
Run builds, tests, and other long commands in the background while continuing other work. Explains how to read new log output, check completion, send input, and stop processes using the available platform controls.
Plan and review new Omnigent harness integrations, the adapters connecting agent runtimes to the platform. Compare SDK and subprocess approaches with native interface wrappers, using capability matrices and checklists for implementation and testing.
Connect stock data to an application using Finnhub Stock API. The skill covers current quotes, company profiles, historical prices, and market news, with server-side request handling to protect API keys and manage cached responses.
Guides development of apps for viewing USD, a 3D scene format. Selects browser streaming or local implementation references, covering rendering, camera controls, selection, interface layout, and validation while keeping users’ scene files unchanged.
Build AI agents on Cloudflare Workers with the Agents SDK. Implement persistent state, real-time chat, scheduled tasks, multi-step background workflows, and MCP servers, using current Cloudflare documentation to guide implementation.
Write and review Cloudflare Workers code using current official guidance. Check configuration, asynchronous tasks, large response handling, secrets, and service connections, with findings supported by documentation, code locations, or validation results.
Design live monitoring dashboards with clear priorities, linked charts, and predictable update behavior. Covers mobile interactions, connection failures, and rendering performance so users can scan current conditions, spot anomalies, and explore details as data changes.
Document and validate Daytona interface workflows with labeled screenshots in a browsable HTML page. Add short videos when motion matters, check that evidence shows the claimed behavior, and share it for pull request review.
Launch the real iPolloWork app on Daytona or locally and run scripted end-to-end tests through its debugging connection. Collect machine-checkable assertions, validated screenshots, and reports as evidence of the tested behavior.
Integrate Pyth Network price feeds into Solana applications. Fetch or stream market prices, use them in on-chain programs, and check data freshness and uncertainty. Examples also cover moving averages that smooth short-term price changes.