Token导航 LogoToken导航TokenDH.com
效率敏感数据clawhub未标认证来源可访问clear审计提醒

tech-news-bulletin科技新闻公告

Agent Skill

tech-news-bulletin 用于辅助测试设计、自动化测试和回归验证,适合在 OpenClaw 中需要补充测试、分析失败日志或验证功能改动时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

2,987

周安装

122

GitHub Stars

公开资料未说明

下载量

966
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:tech-news-bulletin(科技新闻公告)
来源仓库:https://github.com/juniarto-samsudin/tech-news-bulletin
安装命令:
openclaw skills install tech-news-bulletin
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install tech-news-bulletin

简介

从 RSS 源和 TLDR.tech AI 时事通讯中收集最新技术和 AI 新闻,将它们合并成统一的每日摘要,并通过电子邮件发送。

SKILL.md

name
tech-news-bulletin
description
Collect latest technology and AI news from RSS feeds AND the TLDR.tech AI newsletter, merge them into a unified daily digest, and send via email.
metadata

Tech News Bulletin

Collect the latest technology and AI news from two sources:

  1. RSS feeds — e.g., TechCrunch, Wired AI, Google AI Blog
  2. TLDR.tech AI Newsletter — yesterday's edition, fetched and sanitized automatically

Merge both into a single deduplicated digest and send it to a list of email addresses.

When to use (trigger phrases)

Use this skill immediately when the user asks any of:

  • "tech news bulletin"
  • "daily tech bulletin"
  • "send tech bulletin"
  • "run tech bulletin"
  • "create tech bulletin"

Workflow

  1. Fetch RSS feeds from configured sources
  2. Fetch TLDR.tech AI newsletter for the previous day (https://tldr.tech/ai/YYYY-MM-DD)
  3. Sanitize TLDR HTML — extract article title, canonical link, and summary; strip sponsor blocks, navigation, footers
  4. Merge & deduplicate all articles by URL
  5. Sort by date (newest first) and limit to MAX_ARTICLES
  6. Summarize each article via Ollama (falls back to the description snippet if unavailable)
  7. Build HTML digest with per-article source badges (RSS source name vs. "TLDR AI")
  8. Send digest to all configured email addresses via SMTP

Installation

Install required Python packages:

pip install feedparser requests beautifulsoup4

Ensure environment variables are set:

export SMTP_EMAIL="your-email@example.com"
export SMTP_PASSWORD="your-app-password"

Configuration

Edit scripts/bulletin.py to customize:

  • RSS_FEEDS — list of RSS URL endpoints
  • EMAIL_ADDRESSES — recipients for the bulletin
  • MAX_ARTICLES — maximum articles in the combined digest (default 15)
  • TLDR_BASE_URL — base URL for the TLDR newsletter (default https://tldr.tech/ai/)

The Ollama endpoint is http://172.20.86.203:11434 with model glm-4.7-flash:latest.

Usage

To run the bulletin now:

python3 /home/juniarto/.openclaw/workspace/skills/tech-news-bulletin/scripts/bulletin.py

Check the log output:

tail -f /tmp/openclaw-debug.log

Or let the skill handle it automatically via cron:

openclaw cron add --job='{
  "name": "daily-tech-bulletin",
  "schedule": { "kind": "every", "everyMs": 86400000, "anchorMs": 42000000 },
  "payload": { "kind": "systemEvent", "text": "run-tech-news-bulletin" },
  "sessionTarget": "isolated",
  "enabled": true
}'

Digest Format

Subject: Daily Tech & AI News Bulletin

Body (HTML):

  • Header with date and source attribution
  • Per article:

- Linked title - Source badge (RSS feed name or "TLDR AI") - 1–5 sentence summary

Differences from tech-news-digest

Featuretech-news-digesttech-news-bulletin
RSS feeds
TLDR.tech AI newsletter
Source badges in digest
HTML sanitizer (inline)
Combined deduplication

Rules

  • Send emails via the SMTP credentials in the environment (SMTP_EMAIL, SMTP_PASSWORD)
  • Keep each article summary to 1–5 sentences
  • Strip sponsor articles from TLDR content
  • Total digest should be readable within ~5 minutes
  • TLDR date is always computed as today - 1 day at runtime, so no manual date config is needed

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

81.05%
按下载量换算783

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills