发现优质的 AI Agent 技能

This document provides essential information for AI agents and developers working on the `vision-sandbox` repository. It covers environment setup, build commands, testing procedures, and code style guidelines to ensure consistency and quality.

**Version:** 1.1 **Status:** Production-soaked since 2026-02-07 **Target:** Upstream submission to openclaw/openclaw

来自 openclaw/skills 技能

Use this skill to convert public URLs into LLM-ready Markdown via [markdown.new](https://markdown.new).

Summarize any URL or block of text using [Kagi's Universal Summarizer API](https://help.kagi.com/kagi/api/summarizer.html). Handles articles, papers, PDFs, video transcripts, forum threads, and more. Supports multiple summarization engines and can translate output to 28 languages.

Keep a living project state document updated after each commit, so any agent (or future session) can instantly understand where things stand.

Render markdown tables as PNG images for messaging platforms that don't support markdown tables.

当用户要获取网页内容、正文提取、把网页转成 markdown/text、抓取文章主体时，优先使用此技能。

当用户要获取网页内容、正文提取、把网页转成 markdown/text、抓取文章主体时，优先使用此技能。

当用户要获取网页内容、正文提取、把网页转成 markdown/text、抓取文章主体时，优先使用此技能。

This document explains how to use the prepper skill effectively by combining uncensored ollama knowledge with Claude validation.

This document maps documented CLI features to their corresponding FileWave API endpoints.