← 返回 Skills 市场
changsheng0804

content-tracker

作者 changsheng0804 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
119
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install content-tracker
功能描述
内容追踪技能。高时效性话题追踪、链接更新监控、第三方热点聚合。 USE FOR: - "追踪AI行业动态", "追踪某某话题最新进展" - "监控这个链接的更新", "这个网站有新内容吗" - "今天的热点", "最新新闻" - 定期简报生成(配合日程使用)
使用说明 (SKILL.md)

内容追踪技能

高时效性内容追踪工具,支持话题搜索、链接监控、热点聚合。

核心能力

1. 话题追踪

  • 智能搜索接口,过滤高时效性内容
  • 按事件主体去重,避免重复推送
  • 支持首次/非首次执行模式

2. 链接追踪

  • 监控指定URL的内容更新
  • 自动识别新增内容
  • 生成更新简报

3. 第三方数据源

  • 微博热搜 (weibo_hot)
  • 36氪 (thirty_six_kr)
  • 腾讯新闻 (tencent_news)
  • 华尔街见闻 (wallstreet_cn)
  • 每日热点汇总 (daily_report)

使用场景

适用

  • 行业动态追踪(AI、金融、科技等)
  • 竞品/新闻监控
  • 定期简报生成
  • 链接更新通知

不适用

  • 需要登录的内容
  • 动态JS渲染的页面
  • 视频为主的页面

输出格式

所有追踪结果保存为 Markdown 简报:

./我的追踪/{yyyy_mm_dd}/{话题名称}.md

简报内容:

  • 来源标题(引用链接)
  • 核心内容总结
  • 时效性标注

快速开始

用户:追踪一下AI Agent行业的最新动态
AI:[执行话题追踪] → 生成简报 → 返回链接

配合日程使用

可创建重复日程,自动定期追踪:

场景 频率 建议
行业动态 每日 下午3点执行
热点追踪 每日 早晚各一次
链接监控 每周 周一执行

依赖

  • 技能:topic_tracking(需预先安装)
  • 环境:Python3 + requests

注意事项

  • 首次执行使用 --is-first-time true 参数
  • 无结果表示确实没有新内容,不会重复推送
  • 内容来源于原文总结,不做推断或编造
安全使用建议
This skill appears coherent for tracking topics and saving Markdown reports, but verify a few practical points before installing: 1) Ensure the runtime has Python3 and the 'requests' package (the SKILL.md expects requests but there is no install step). 2) Confirm why 'bash' is listed as a required binary (the docs only describe Python usage); if you run in a constrained environment, test the skill in an isolated workspace first. 3) The skill depends on another skill 'topic_tracking'—inspect that skill's code/permissions before enabling. 4) Outputs are written to ./我的追踪/... on the agent host—avoid running on machines with sensitive data or expose those report files unintentionally. 5) Be aware of scraping and site terms of service for sources like Weibo/36Kr/Tencent; the skill excludes login and JS-heavy pages but may still trigger rate limits or blocking. If you need stronger assurance, ask the publisher for an install spec or the topic_tracking implementation to review.
功能分析
Type: OpenClaw Skill Name: content-tracker Version: 1.0.0 The content-tracker skill is a standard news and topic aggregation tool designed to monitor specific URLs and third-party news sources (e.g., Weibo, 36Kr). Analysis of SKILL.md and _meta.json reveals no evidence of malicious intent, data exfiltration, or harmful prompt injection; the described behavior is consistent with its stated purpose of generating Markdown-based news reports.
能力评估
Purpose & Capability
The name/description (topic/link/news tracking and periodic briefs) matches the declared runtime expectations (uses Python3, saves Markdown reports, depends on a separate topic_tracking skill). Required binaries (python3) are appropriate for the stated purpose. The declared dependency on the topic_tracking skill is reasonable for modular design.
Instruction Scope
SKILL.md limits behavior to fetching/filtering third-party content, generating summaries, and writing Markdown reports under ./我的追踪/{date}/. It explicitly excludes login-only content and JS-heavy pages. It does not instruct reading unrelated system files or secret env vars.
Install Mechanism
There is no install spec (instruction-only), so nothing is downloaded or written during install. This is the lowest-risk model and consistent with the skill's description.
Credentials
No credentials or config paths are requested, which is appropriate. Minor inconsistencies: the metadata lists bash and python3 as required binaries but the doc only describes Python + requests (no explicit use of bash explained). The SKILL.md mentions the Python 'requests' library but does not declare how it will be provided — the skill assumes the runtime already has that dependency. These are documentation/packaging gaps rather than direct security red flags.
Persistence & Privilege
always is false and the skill does not request system-wide changes or other skills' configs. It writes outputs to a local relative path (./我的追踪/...), which is normal for report generation.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install content-tracker
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /content-tracker 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
content-tracker v1.0.0 - 首发版本,提供高时效性话题追踪、链接更新监控及第三方热点聚合功能 - 支持智能去重、内容更新检测、简报生成(Markdown格式) - 集成微博热搜、36氪、腾讯新闻、华尔街见闻等数据源 - 适用于行业动态追踪、新闻监控、定期简报生成等场景 - 依赖 topic_tracking 技能与 Python3 环境
元数据
Slug content-tracker
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

content-tracker 是什么?

内容追踪技能。高时效性话题追踪、链接更新监控、第三方热点聚合。 USE FOR: - "追踪AI行业动态", "追踪某某话题最新进展" - "监控这个链接的更新", "这个网站有新内容吗" - "今天的热点", "最新新闻" - 定期简报生成(配合日程使用). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 119 次。

如何安装 content-tracker?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install content-tracker」即可一键安装,无需额外配置。

content-tracker 是免费的吗?

是的,content-tracker 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

content-tracker 支持哪些平台?

content-tracker 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 content-tracker?

由 changsheng0804(@changsheng0804)开发并维护,当前版本 v1.0.0。

💬 留言讨论