Toutiao

检索并摘要今日头条公开文章、视频和话题，提供标题、作者、发布时间及互动数据的轻量分析和提醒。

Security Scan

The skill's requirements and instructions align with its stated purpose of summarizing public Toutiao pages; it is an instruction-only skill that does not request extra credentials or install anything.

Purpose & Capability

Name/description (summarize public Toutiao articles/videos/topics) match the SKILL.md: it describes visiting public pages, extracting titles/author/time/interaction counts and providing lightweight analysis. No unrelated env vars, binaries, or install steps are requested.

Instruction Scope

SKILL.md stays within the stated boundary (public pages, no reverse-engineering, no bulk scraping, no video downloads). It asks agents to 'visit' and 'parse' pages and recommends manual open for dynamic rendering. This is coherent, but vague: how dynamic content is rendered/executed depends on the agent's browsing tooling — that could enable scraping if misused. The skill itself does not instruct reading unrelated files or exfiltrating data.

Install Mechanism

No install spec and no code files — lowest-risk instruction-only skill; nothing is downloaded or written to disk by the skill package.

Credentials

No required environment variables, credentials, or config paths are declared. Requested data fields (public metadata and interaction counts) are appropriate for the stated function.

Persistence & Privilege

always is false and model invocation is allowed (platform default). The skill does not request elevated or persistent privileges or modify other skills' configs.

Assessment

This skill is internally consistent and doesn't ask for credentials or install anything. Before enabling it, confirm how your agent will access web pages (browser plugin, headless renderer, or manual steps). If the agent has autonomous browsing, set rate limits and explicit rules to prevent bulk scraping or downloading video content (the SKILL.md forbids bulk scraping, but enforcement depends on agent policies). Also verify the agent won't forward scraped content to external endpoints you don't control, and ensure use complies with Toutiao's terms of service and copyright rules.

今日头条

用途与边界

• 面向公开文章/视频/话题页的检索与内容摘要
• 不提供接口逆向或批量抓取能力
• 仅用于公开页面的轻量分析与提醒

关键入口

• 主页：https://www.toutiao.com/
• 热点/视频频道：频道入口
• 搜索入口：https://www.toutiao.com/search

常见任务

• 指定关键词的文章/视频集合摘要（标题、作者、发布时间、互动）
• 热点频道的条目分布与题材统计
• 视频内容的标题与简介摘要

数据字段

• 标题、作者、来源、发布时间、正文摘要/简介、标签、链接
• 互动指标（评论/点赞/收藏/分享，如公开展示）
• 频道名称、采集时间、来源链接

自动化要点

• 动态渲染与反爬，建议人工打开后触发解析
• 频率控制，不进行批量抓取；结果标注采集时间
• 视频页解析仅获取公开元信息，不进行下载

示例流程

• 关键词摘要：输入关键词 → 搜索 → 抽取条目 → 输出摘要清单
• 频道统计：访问频道 → 抽取条目 → 题材分布与来源统计
• 视频摘要：访问视频页 → 解析标题/简介/互动 → 输出摘要

合规提示

• 遵守平台规则，不进行接口调用或批量采集
• 不进行视频下载或去水印