Web Learner 1.0.0

自主上网学习技能 - 让 AI 能够主动搜索、浏览和从互联网获取知识。当用户要求了解最新信息、学习新知识、查询新闻、获取某个主题的详细信息，或需要从网络上获取数据时触发此技能。

Security Scan

Instruction-only web-browsing/search skill appears coherent with its stated purpose, but it omits declaring required credentials (Brave API key) and instructs the agent to fetch and interact with arbitrary web content (including pages behind login or anti-bot protections), which is a proportionality/visibility gap you should review before installing.

Purpose & Capability

The skill's name and description (web search, browsing, fetching) align with the SKILL.md instructions (use web_search, web_fetch, browser). Behavior described (search, fetch, render JS pages) is coherent with the claimed purpose.

Instruction Scope

Instructions are limited to web search/fetch/browser flows and include sensible error handling and source attribution. They also instruct extracting page text/markdown and interacting with pages (screenshots, UI interaction). This is expected for a web-browsing skill, but such actions can touch pages requiring authentication or interactivity—there's no guidance about handling user credentials or private data, which is a possible privacy gap.

Install Mechanism

No install spec or code is included (instruction-only), so nothing is written to disk and there is no direct install risk.

Credentials

SKILL.md states that web_search requires a Brave API Key and browser requires a browser service, but the skill declares no required environment variables or primary credential. The absence of an explicit requirement for the Brave API key (or other credentials) is an incoherence: the skill will need external credentials/tools that are not declared in metadata.

Persistence & Privilege

The skill is not always-on and is user-invocable; it does not request persistent system presence or modify other skills' configs. Autonomous invocation is allowed by default (normal), but not combined with other high-risk factors here.

What to consider before installing

This skill is instruction-only and its behavior (searching, fetching, and using a headless browser) matches its description, but there are a few things to check before installing: - The SKILL.md says web_search needs a Brave API Key, yet the skill metadata does not declare any required env vars or credentials. Confirm where and how that API key will be provided and stored if you install this skill. - The skill will fetch arbitrary web pages and may interact with pages that require login or have anti-bot protections. Do not provide personal account credentials unless you trust the skill and the hosting platform's secret storage policy. - Using a browser service may expose screenshots or page contents; consider privacy implications for pages containing sensitive data. - Verify that your platform provides the referenced tools (web_search, web_fetch, browser) and understand any costs or quotas (e.g., Brave API usage). If you need higher assurance, ask the publisher for clarification on required credentials, where keys should be set, and any safeguards for handling authenticated or private pages.

Web Learner - 自主上网学习技能

概述

此技能赋予 AI 自主上网搜索和学习的能力，使其能够：

• 主动从互联网获取最新信息
• 学习新知识并整合到回答中
• 查询新闻、天气、事件等信息
• 获取特定主题的详细资料

触发场景

以下情况应激活此技能：

1. 用户询问"最新消息"、"新闻"、"今天发生了什么"
2. 用户要求"了解"、"学习"、"查询"某个主题
3. 用户要求获取某个链接的详细内容
4. 需要获取实时信息（天气、股价、赛事等）
5. 用户要求"汇报"某方面的信息
6. 需要验证或补充训练数据中没有的知识

搜索策略

1. Web Search (搜索)

使用 web_search 工具进行关键词搜索：

• 选择精确的搜索关键词
• 优先选择中文搜索结果（使用 country: "CN"）
• 使用 freshness 参数限定时间范围：pd(今天)、pw(本周)、pm(本月)

2. Web Fetch (抓取)

使用 web_fetch 工具获取页面内容：

• 提取网页的 markdown 或 text 内容
• 适用于获取文章、文档、教程等详细内容
• 注意处理页面加载失败的情况

3. Browser (浏览器)

当以上工具失败时，使用 browser 工具：

• 需要先启动浏览器服务
• 可用于处理需要 JavaScript 渲染的页面
• 支持截图和 UI 交互

学习工作流

1. 理解需求 → 确定需要什么信息
2. 选择工具 → 搜索/抓取/浏览器
3. 获取信息 → 执行查询
4. 整合加工 → 提取关键信息
5. 反馈用户 → 用中文总结呈现

常见场景处理

天气查询

• 首选 wttr.in 服务（支持城市查询）
• 备选：weather.com.cn、中国天气网

新闻获取

• 百度新闻：news.baidu.com
• 澎湃新闻：www.thepaper.cn
• 今日头条：www.toutiao.com

获取视频内容

• 使用 web_fetch 尝试获取视频页面描述
• 提取视频标题和简介
• 注意：无法直接播放或理解视频内容

获取文档内容

• 优先使用 web_fetch 提取可读内容
• 处理反爬虫和登录限制
• 提取页面主要文本内容

错误处理

当无法获取信息时：

1. 尝试备选数据源
2. 告知用户具体障碍
3. 提供手动查看的建议链接
4. 询问是否需要其他帮助

输出格式

向用户呈现信息时：

• 使用中文
• 结构清晰，分点陈述
• 注明信息来源
• 保持简洁，避免信息过载

工具可用性检查

在执行前检查工具可用性：

• web_search - 需要 Brave API Key
• web_fetch - 大部分网页可用
• browser - 需要浏览器服务运行

如遇工具不可用，尝试备选方案或告知用户。