Tmtpost Daily

v2.3.0

钛媒体每日资讯聚合技能。用于获取钛媒体当天的最新新闻、快报和热门榜单,支持关键词搜索。当用户说"钛媒日报"、"今日资讯"、"钛媒体搜索"或需要查看/搜索科技行业动态时触发。

2· 137·0 current·0 all-time
byVivian@vivian8725118

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for vivian8725118/tmtpost-daily.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Tmtpost Daily" (vivian8725118/tmtpost-daily) from ClawHub.
Skill page: https://clawhub.ai/vivian8725118/tmtpost-daily
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install tmtpost-daily

ClawHub CLI

Package manager switcher

npx clawhub@latest install tmtpost-daily
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Skill name/description (daily aggregation and search of 钛媒体/Tmtpost) matches the declared behavior: fetching RSS and webpages from tmtpost.com and extracting article lists. It does not request unrelated credentials, binaries, or config paths.
Instruction Scope
SKILL.md explicitly instructs the agent to fetch RSS and specific tmtpost pages and to extract links (including /nictation/ IDs from the homepage). This stays within the stated purpose. Note: it relies on a web_fetch tool (network fetch and HTML parsing); SKILL.md acknowledges dynamic JS-rendered pages and specifies fallback behavior. The skill does not instruct reading local files, environment secrets, or posting data to third-party endpoints.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk install profile (nothing written to disk by the skill itself).
Credentials
Skill declares no environment variables, credentials, or config paths. That is proportionate for a web-scraping/news-aggregation skill.
Persistence & Privilege
always:false and default model invocation are used. The skill does not request permanent/system-level privileges or to modify other skills. Autonomous invocation is allowed by platform default (not elevated here).
Assessment
This skill is internally coherent and only performs web requests to tmtpost.com (RSS and HTML). Before installing, consider: (1) the agent will make outbound HTTP requests when invoked — ensure you are comfortable with that network access; (2) the skill may be affected by site layout changes or rate-limiting and it explicitly cannot render JS-heavy pages (it uses homepage fallbacks); (3) there are no credentials requested, so there is no apparent secret-exfiltration risk from this skill itself. If you want stronger guarantees, verify the agent platform's web_fetch implementation (what headers it sends, whether it exposes client metadata) and confirm you accept any legal/TOU considerations for scraping the target site.

Like a lobster shell, security has layers — review code before you run it.

latestvk971mqptcawjxbjjpt0j61s08184dpng
137downloads
2stars
6versions
Updated 3w ago
v2.3.0
MIT-0

钛媒体每日资讯

抓取钛媒体最新内容,聚合输出当日科技行业要闻,支持智能搜索。

🆕 首次使用引导

当用户触发 skill 但意图模糊时(如只说"钛媒体"、"能做什么"),先展示以下引导菜单:

📰 钛媒体资讯助手

我可以帮你:

1️⃣ 钛媒日报 - 获取今日最新资讯汇总
   说"今日资讯"或"钛媒日报"

2️⃣ 热门榜单 - 查看当前最热的文章排行
   说"热门榜单"或"钛媒体热门"

3️⃣ 关键词搜索 - 搜索你感兴趣的科技话题
   说"搜一下AI手机"或"搜索比亚迪"

---
直接说你想做什么,或者让我帮你搜索!

注意:如果用户已有明确意图(如说"钛媒日报"),直接执行,不显示此菜单。

内容来源

板块URL数据来源
首页最新https://www.tmtpost.com/feedRSS(优先)/ 网页(回退)
快报频道https://www.tmtpost.com/网页(从首页提取)
热门榜单https://www.tmtpost.com/hot网页
搜索https://www.tmtpost.com/search?q=关键词网页

数据获取策略

  • 首页最新:优先使用 RSS(/feed),速度快且结构完整;如果 RSS 失败则回退到网页抓取
  • 热门榜单:网页抓取(无 RSS)
  • 快报资讯:从首页(/)网页提取快报链接(/nictation/数字.html),快报频道是 JS 动态渲染,无法直接抓取
  • 关键词搜索:网页抓取

核心功能

1. 钛媒日报(默认)

获取当日最新资讯汇总。

工作流程:

1.1 抓取首页最新文章

优先策略:先用 RSS

url: https://www.tmtpost.com/feed

从 RSS 中提取前10条文章的标题、URL和发布时间(RSS 的 <item> 标签)。

回退策略:如果 RSS 失败或返回格式错误,使用网页抓取

url: https://www.tmtpost.com/
extractMode: markdown
maxChars: 8000

从返回内容中提取前10条文章的标题、URL和发布时间。

1.2 抓取快报资讯

重要:快报链接不在 /nictation 页面,而是嵌入在**首页(/)**的HTML中!

使用 web_fetch 工具抓取首页,然后提取快报链接:

url: https://www.tmtpost.com/
extractMode: markdown
maxChars: 15000

提取规则:从首页内容中提取所有 /nictation/数字.html 格式的链接,结合快报标题和发布时间。

为什么不能抓 /nictation:快报频道页面使用JS动态加载,web_fetch 抓取不到链接。但首页会直接渲染快报链接。

最终输出格式

| 时间 | 标题 | 链接 |
| 16:54 | 中证指数修订... | https://www.tmtpost.com/nictation/7941080.html |

1.3 抓取热门榜单

使用 web_fetch 工具抓取热门页面:

url: https://www.tmtpost.com/hot
extractMode: markdown
maxChars: 8000

提取前10条热门文章的标题和URL。

2. 关键词搜索

当用户询问特定主题时(如"搜一下AI手机"、"钛媒体有关于新能源的文章吗"),执行搜索。

工作流程:

  1. 解析用户意图,提取关键词
  2. 构搜索URL:https://www.tmtpost.com/search?q=关键词
  3. 抓取搜索结果页面
  4. 提取匹配的文章列表(标题、URL、发布时间)
url: https://www.tmtpost.com/search?q=AI手机
extractMode: markdown
maxChars: 8000

输出格式:

🔍 搜索「关键词」结果:

1. [文章标题](URL) - 发布时间
2. ...

输出格式

钛媒日报

📰 钛媒体日报 · YYYY年MM月DD日

---

### 🔥 热门榜单
1. [标题](URL)
2. ...

### 📰 最新新闻
1. [标题](URL) - 发布时间
2. ...

### ⚡ 快报速递
1. [标题](URL) - HH:MM
2. ...

---
💡 [搜索关键词]

触发词

日报相关:

  • "钛媒日报"
  • "今日资讯"
  • "最新钛媒体"
  • "钛媒体速览"
  • "钛媒体最新"
  • "帮我看钛媒体"

搜索相关:

  • "搜一下"
  • "搜索"
  • "钛媒体有关于"
  • "找找"

错误处理

  • RSS 抓取失败时自动回退到网页抓取首页
  • 网页抓取失败时尝试 /new 页面
  • 内容为空时多抓取几次
  • 时间判断以文章发布时间为准
  • 快报链接获取:必须从首页(/)提取,不能抓 /nictation。快报频道是JS动态渲染,链接不在HTML源码中。
  • 搜索无结果时,尝试简化关键词或扩大时间范围

Comments

Loading comments...