Results for “html-output”

Generates a single-file HTML funnel infographic from 3-6 ordered stages with absolute values, showing conversion rates and drop-off at each step. Output is a static 9:16 vertical image with inline CSS, no JavaScript, no external dependencies.

Search the web and fetch content from URLs, returning LLM-friendly markdown.

整合智能体输出结果为结构化最终输出，支持多种格式。适用于整合分析报告、生成结构化报告

Provides patterns for robust error handling across TypeScript, Python, and Go, including typed errors, error boundaries, retries, circuit breakers, and user-facing error messages.

smart-output

Generates a high-fidelity, clickable web prototype with navigation, hero, features, and CTA sections.

Use when users need webpage scraping, structured data extraction, crawling strategy, anti-bot handling, selector design, or repeatable web data collection workflows.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

Patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages.

Provides patterns for robust error handling across TypeScript, Python, and Go, covering typed errors, error boundaries, retries, circuit breakers, and user-facing messages.

Imported skill html2pptx from anthropic

Generates a sequence of fullscreen video frames with cinematic visuals, auto-play, and metadata for Remotion/Hyperframes rendering.

Pull data from a web page. First call on a new intent prototypes the flow via $B primitives and returns JSON. Subsequent calls on a matching intent route to a codified browser-skill and return in ~200ms. Read-only — for mutating flows (form fills, clicks, submissions), use /automate. Use when asked to "scrape", "get data from", "pull", "extract from", or "what's on" a page. (gstack)

Builds a navigable knowledge graph from any folder of files, with community detection, an audit trail, and outputs including interactive HTML, GraphRAG-ready JSON, and a plain-language report.