← Back to Skills Marketplace
297
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install techflow-news
Description
深潮TechFlow新闻聚合爬取。爬取https://www.techflowpost.com/?lang=zh-CN当天的文章，形成表格（日期、文章、主要内容、网址），并给出一段简短总结。用于用户询问"今天有什么新闻"、"汇总今天的文章"等场景。
Usage Guidance
This skill is instruction-only and appears coherent for its purpose, but keep in mind: it will fetch content from the public TechFlow site when invoked — verify you are comfortable with the agent making outbound web requests. There are no credentials requested, but the SKILL.md depends on an external scraping tool ('extract_content_from_websites') which must exist in your agent environment; if that tool is not present the agent may fall back to other network methods. Before installing, confirm the agent's web-scraping tool respects robots.txt and rate limits and that you accept fetching and summarizing third‑party site content. Because there is no code to review, you cannot inspect implementation details; if you need stricter controls, only enable skills that declare their tooling or provide code you can audit.
Capability Analysis
Type: OpenClaw Skill
Name: techflow-news
Version: 1.0.0
The skill bundle is a news aggregator designed to scrape and summarize daily articles from techflowpost.com. The SKILL.md file provides clear instructions for an AI agent to extract content, format it into a table, and generate a summary using a standard extraction tool. No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description state: aggregate today's TechFlow (zh-CN) articles into a table and produce a short summary. The SKILL.md only requires fetching that specific URL and extracting title, date, summary, and link — all consistent with the declared purpose.
Instruction Scope
Instructions are narrowly scoped to scraping https://www.techflowpost.com/?lang=zh-CN, extracting title/date/summary/link, filtering articles published today, and distinguishing article types. The doc references an external tool 'extract_content_from_websites' (not declared in metadata) and expects date parsing and URL normalization; behavior depends on the agent's available web-scraping tooling and time-zone handling. No instructions ask for unrelated files, credentials, or broad system data.
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes disk writes and external installs. Runtime will rely on the agent's existing web access/tools.
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportionate to a simple web-scraping/news-aggregation task.
Persistence & Privilege
always:false and no special privileges requested. The skill does not ask to modify other skills or persist credentials.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install techflow-news - After installation, invoke the skill by name or use
/techflow-news - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
TechFlow 新闻聚合技能发布首个版本：
- 爬取并汇总深潮TechFlow网站当天文章，生成新闻摘要。
- 输出内容包括当日新闻的表格（日期、标题、主要内容、网址）与简短总结。
- 支持区分“深度文章”与“7x24h快讯”。
- 自动补充并输出完整文章链接。
- 适用“今天有什么新闻”等查询场景。
Metadata
Frequently Asked Questions
What is techflow-news?
深潮TechFlow新闻聚合爬取。爬取https://www.techflowpost.com/?lang=zh-CN当天的文章，形成表格（日期、文章、主要内容、网址），并给出一段简短总结。用于用户询问"今天有什么新闻"、"汇总今天的文章"等场景。 It is an AI Agent Skill for Claude Code / OpenClaw, with 297 downloads so far.
How do I install techflow-news?
Run "/install techflow-news" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is techflow-news free?
Yes, techflow-news is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does techflow-news support?
techflow-news is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created techflow-news?
It is built and maintained by yejiming (@yejiming); the current version is v1.0.0.
More Skills