← Back to Skills Marketplace
chegangan

Daily-EnglishNews-Reader

by 赖余轩 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
238
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install daily-englishnews-reader
Description
单次生成符合i+1学习法的英语阅读材料,自动适配CEFR难度,生成飞书云文档
README (SKILL.md)

English Daily Reader Skill for OpenClaw

功能说明

单次生成符合i+1学习法的英语阅读材料,解决两个核心痛点:

  1. 自动搜索最新全球高质量文章,内容覆盖全球新闻、经济、科技、科学文化,学英语的同时了解行业资讯
  2. 自动适配CEFR英语难度等级(A1/A2/B1/B2/C1),提供刚好匹配水平的学习语料

核心特性

✅ 每次调用从4个已经指定的分类RSS源各选1篇高质量文章(全球政治、经济、科技、科学文化) ✅ 改写为指定难度与字数的英文文章 ✅ 每篇文章提取指定数量的+1难度生词,附带英文释义和语境例句 ✅ 生成新的飞书云文档,直接返回文档链接 ✅ 自动去重,不会重复推荐已经生成过的文章

使用方法

前置检查

使用前请需要确保已安装飞书官方OpenClaw插件:

  1. 执行安装命令:npx -y @larksuite/openclaw-lark-tools install(安装出错可加sudo重试)
  2. 安装过程中选择「新建机器人」扫码创建,或「关联已有机器人」
  3. 创建完成后在飞书给机器人发任意消息激活,发送/feishu auth完成批量授权
  4. 验证安装:发送/feishu start,返回版本号即安装成功

如果没有安装插件,当用户调用本Skill时你要引导用户完成上述安装步骤。

首次使用

当用户第一次调用本Skill时,你需要询问用户以下配置信息,并修改配置文件完成配置:

  1. 阅读难度:显示默认 A2,CEFR等级(A1/A2/B1/B2/C1,难度递增)
  2. 每篇文章字数:显示默认 350 (可自定义)
  3. 每篇在文章最后讲解的可能为i+1难度的生词数量:显示默认 3 个/篇(可自定义)

配置文件

所有配置都在config目录下,每次运行前读取一次:

  • config/config.json:基础阅读配置,包含阅读难度、每篇文章字数、每篇讲解生词数量
  • config/rss_sources.json:预设RSS源,你需要从这里查找用户设置的rss源
  • config/sent_articles.json:已生成过的文章去重列表,读取过的文章你需要记录在这里,避免下次重复读取

调用方式与运行步骤

当用户发送类似意思的指令:生成英语阅读材料调用Daily-EnglishNews-Reader,你会自动完成以下步骤:

  1. 读取config/rss_sources.json配置
  2. 运行scripts/random_source_picker.py,这个脚本会随机从4个rss分类中各选一个RSS源
  3. 从每个源挑选一篇完整的且未在config/sent_articles.json中记录的高质量文章
  4. 按照用户配置的难度、字数改写文章,在不影响理解的前提下,要求用词地道,且尽量保留专业技术用语
  5. 在改写后的文章中,根据用户配置的讲解生词数量,在生成的短文中选取可能属于+1难度的生词加粗,在短文末尾列出所有加粗生词的英文释义和在短文中出现的语境例句;
  6. 生成全新的飞书云文档,写入4篇文章内容,并附上来源和文章原始URL
  7. 返回文档链接给用户
  8. 将本次生成的文章的来源、标题、URL记录到config/sent_articles.json中,避免后续重复推荐

config/config.json默认配置:

{
  "reading": {
    "difficulty": "A2",
    "words_per_article": 350,
    "words_per_article_to_explain": 3
  }
}

依赖工具

  • python3 用于RSS源随机选择
  • 飞书官方OpenClaw插件:@larksuite/openclaw-lark-tools
Usage Guidance
This skill appears coherent and does what it claims: fetch RSS articles, rewrite them to a chosen CEFR level, and publish them as a Feishu cloud document. Before installing/use, consider the following: - Installing the Feishu plugin uses `npx @larksuite/openclaw-lark-tools install`. npx runs code from the npm package at install time — only proceed if you trust the @larksuite package source. - The RSS feeds in config/rss_sources.json are fetched via a third-party RSS→JSON proxy (morss.it). That means article content is routed through morss.it rather than fetched directly; review/replace those URLs if you prefer direct fetching. - The skill requires you to create/authorize a Feishu robot (scan QR / grant permissions). That robot (and the plugin) will have the permission to create/edit cloud documents in your Feishu workspace — grant only if you are comfortable with that scope. - The skill will write/read files under its config directory (config/sent_articles.json) to record which articles were used. If you want to preserve records, back up that file before use. - If you have security concerns, run the skill in a restricted/sandboxed environment first or inspect the installed @larksuite package source before granting Feishu authorization.
Capability Analysis
Type: OpenClaw Skill Name: daily-englishnews-reader Version: 1.0.0 The skill is a legitimate tool designed to fetch news from RSS feeds, rewrite them for English learners using an AI agent, and export the results to Lark/Feishu cloud documents. The Python script (scripts/random_source_picker.py) performs basic selection and connectivity testing of RSS sources defined in the configuration, and the installation steps in SKILL.md use standard package managers for documented dependencies (@larksuite/openclaw-lark-tools and feedparser). No evidence of malicious intent, data exfiltration, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description (generate leveled English reading material and publish to Feishu) matches what is present: a small helper Python script, RSS source config, and instructions to install the Feishu OpenClaw plugin and Python deps. Required binaries (python3, pip3) and the declared dependency on the Feishu plugin are proportionate.
Instruction Scope
SKILL.md stays within the stated purpose (read rss_sources.json, run scripts/random_source_picker.py, fetch articles, rewrite via the model, publish to Feishu, update sent_articles.json). One operational point to note: the README and SKILL.md require installing and authorizing a Feishu robot (interactive user steps) — this is necessary for creating cloud documents but grants the plugin/robot the ability to create/edit Feishu docs. Users should be aware of that scope before consenting.
Install Mechanism
No packaged install spec in the registry, but metadata instructs running `npx -y @larksuite/openclaw-lark-tools install` and `pip3 install requests feedparser`. pip installs are expected. The npx install executes an npm package installer — expected for integrating Feishu, but running npx pulls and runs code from the npm package at install time, so users should trust the @larksuite package. Also the RSS feed URLs in config use a third‑party RSS-to-JSON proxy (morss.it), which means article content is routed through that service rather than fetched directly.
Credentials
The skill requests no environment variables or secrets in its manifest. The only credential step is user-driven Feishu robot creation/authorization via the plugin (interactive), which is appropriate for the described ability to create cloud documents. There are no hidden env variables or config paths required beyond the local config directory used for de-duplication (config/sent_articles.json).
Persistence & Privilege
The skill is not marked always:true. It writes/reads its own config files under the skill's config directory (config/sent_articles.json, config/config.json), which matches the de-duplication feature described. It does not request or modify other skills' configs or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install daily-englishnews-reader
  3. After installation, invoke the skill by name or use /daily-englishnews-reader
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
完美运行
Metadata
Slug daily-englishnews-reader
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Daily-EnglishNews-Reader?

单次生成符合i+1学习法的英语阅读材料,自动适配CEFR难度,生成飞书云文档. It is an AI Agent Skill for Claude Code / OpenClaw, with 238 downloads so far.

How do I install Daily-EnglishNews-Reader?

Run "/install daily-englishnews-reader" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Daily-EnglishNews-Reader free?

Yes, Daily-EnglishNews-Reader is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Daily-EnglishNews-Reader support?

Daily-EnglishNews-Reader is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Daily-EnglishNews-Reader?

It is built and maintained by 赖余轩 (@chegangan); the current version is v1.0.0.

💬 Comments