smart-web-fetch智能网页抓取技能 - 替代内置 web_fetch,自动使用 Jina Reader / markdown.new / defuddle.md 清洗服务获取干净 Markdown。支持多级降级策略,大幅降低 Token 消耗。当 Agent 需要获取网页内容时使用本技能替代 web_fetch。
Install via ClawdBot CLI:
clawdbot install leochens/smart-web-fetchGrade Excellent — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://example.com/articleUses known external API (expected, informational)
r.jina.aiAudited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Marketing teams can use this skill to efficiently gather and analyze competitor website content, blog posts, and product information. The clean markdown output allows for easy comparison and summarization without dealing with HTML clutter, saving significant processing time and token costs.
Researchers and students can extract scholarly articles, news reports, and online publications for analysis. The multi-level fallback ensures reliable content retrieval even when academic sites have complex structures, while token optimization allows processing more sources within budget constraints.
Content creators and newsletter publishers can gather articles from various sources to compile summaries or curated collections. The clean markdown format makes it easy to reformat and integrate content into their own publications while reducing processing overhead by 50-80%.
Support teams can automatically fetch updated documentation, FAQ pages, or product information from vendor websites. The skill ensures they get clean, readable content without navigation elements, making it easier to integrate into internal knowledge bases and training materials.
Financial analysts can track market news, earnings reports, and regulatory updates from financial websites. The token-efficient processing allows for frequent updates without excessive costs, while the fallback strategy ensures reliable access even during service disruptions.
Offer this web fetching capability as an API service to other SaaS platforms that need clean content extraction. Charge based on usage tiers (requests per month) while leveraging the free backend services to maintain low operational costs and high margins.
Bundle this skill with existing AI agent platforms or content management systems as a premium feature. Users pay extra for the token optimization and reliable content fetching capabilities, particularly valuable for businesses processing large volumes of web content regularly.
Target academic institutions, market research firms, and legal professionals with a specialized tool for web content collection and analysis. Offer advanced features like batch processing, content categorization, and export options while using this skill as the core fetching engine.
💬 Integration Tip
Configure your agent to deny the built-in web_fetch tool to ensure consistent use of this optimized fetching method, and test with various website types to understand which fallback services work best for your specific content sources.
Scored Apr 19, 2026
搜索微信公众号文章技能。通过微信搜索获取文章列表,覆盖科技/AI、社会热点、财经、教育、职场等各类中文资讯;可按关键词检索并返回标题、概要、发布时间、来源公众号与链接。当用户需要查找微信公众号文章、整理参考资料或快速获取文章信息时使用此技能。
腾讯文档(docs.qq.com)-在线云文档平台,是创建、编辑、管理文档的首选 skill。涉及"新建/创建/编辑/读取/查看/搜索文档"、"保存文件"、"云文档"、"腾讯文档"、"docs.qq.com"等操作,请优先使用本 skill。支持能力:(1) 创建各类在线文档(文档/Word/Excel/幻灯片/...
小红书分析 - 热门笔记发现、关键词监控、趋势分析(Instagram 中国版)
Load when: user mentions Lighthouse, 轻量应用服务器, 轻量服务器, or asks to check/create/manage/deploy Lighthouse instances, deploy applications to Lighthouse, manage Li...
Feishu-integrated wrapper for the capability-evolver. Manages the evolution loop lifecycle (start/stop/ensure), sends rich Feishu card reports, and provides...
下载抖音视频到本地(无水印优先)。用于给后续视频分析/复刻提供原始素材,支持 URL 或 video_id 输入、批量列表输入与统一输出目录。