ワンクリックでManusで任意のスキルを実行

rss-reader

スター8,290

フォーク1,414

更新日2026年6月25日 16:10

Discover the RSS/Atom feed URL for a website, then run the fetch-rss.mjs script to retrieve and parse articles from the feed.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

TeamWiseFlow

TeamWiseFlow/xiaobei

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

ファイルエクスプローラー

3 ファイル

SKILL.md

readonly

name	rss-reader
description	Discover the RSS/Atom feed URL for a website, then run the fetch-rss.mjs script to retrieve and parse articles from the feed.
metadata	{"openclaw":{"emoji":"📡","always":false,"requires":{"bins":["node"]}}}

RSS / Atom Feed Reader

Use this skill when:

The user wants to monitor or retrieve updates from a website
The user provides an RSS or Atom feed URL directly
You need to efficiently collect multiple articles from one source without visiting each page

📍 全局技能路径提示：文中所有 ./scripts/ 路径均相对于本技能所在目录（即 <skill> 标签 location 属性所指目录），不是工作区目录。执行时按本技能实际安装路径拼接。

Step 1 — Discover the feed URL

If you already have an RSS/Atom URL, skip to Step 2.

Method A — page source Navigate to the website, take a snapshot, and look for <link rel="alternate"> tags in <head>:

<link rel="alternate" type="application/rss+xml" href="/feed">
<link rel="alternate" type="application/atom+xml" href="/atom.xml">

Method B — common paths (try one at a time until one returns XML)

/feed  /feed.xml  /rss  /rss.xml  /atom.xml  /index.xml
/?feed=rss2  /feeds/posts/default

Method C — look for RSS icons 🟠 or links labelled "RSS", "Subscribe", "Feed".

A valid feed URL returns XML starting with <rss, <feed, or <rdf:RDF.

Step 2 — Run the script

node /path/to/wiseflow/skills/rss-reader/scripts/fetch-rss.mjs <feed_url> [--limit N] [--skip url1,url2,...]

Option	Description
`--limit N`	Max entries to return (default: 20)
`--skip url1,url2,...`	Skip entries whose URLs are already processed (deduplication)

Output is markdown with two sections:

Full-content articles — entries where the feed includes the complete article body (>200 chars). Process these directly; no need to visit the article URL.
Summary-only links — entries with only a short snippet. Visit each URL to retrieve the full content.

Step 3 — Handle results

For full-content articles: extract title, author, date, and content directly from the script output.
For summary-only links: use browser.navigate(url) to fetch each article page.
Pass the script output directly to the user or to your processing pipeline.

Edge cases

Situation	Action
Feed returns 404	Try alternative paths from Step 1
Feed requires login	Follow the browser-guide skill
Script error "Failed to parse feed"	Feed XML may be malformed; report the URL to the user
Empty feed	Report: "This RSS feed has no entries."

このリポジトリの他の Skills

同じリポジトリ

bilibili-publish

TeamWiseFlow/xiaobei

Publish videos to Bilibili (B站) via Open Platform API (OAuth2). Supports chunked video upload, cover image, tags, and partition selection. Requires BILIBILI_APP_ID and BILIBILI_APP_SECRET environment variables.

2026-06-258.3k

content-calibrator

TeamWiseFlow/xiaobei

内容校准预测循环——打分 → 盲预测 → T+3d复盘 → 进化 rubric。按平台独立迭代，每个平台拥有自己的 rubric、校准池、预测日志、受众画像。本技能负责打分（blind sub-agent + score-only.sh + 阈值门 + 流程 1A）与校准闭环；发布记录与数据采集由 published-track 统一管理。

2026-06-258.3k

de-mouth

TeamWiseFlow/xiaobei

口播视频去口误。自动识别并删除静音、语气词、卡顿词、重复句、残句等，输出干净视频+字幕+剪映草稿。触发词：去口误、剪口播、de-mouth、去除口误

2026-06-258.3k

generate-wenyan-theme

TeamWiseFlow/xiaobei

Generate custom WeChat CSS themes from natural language descriptions, WeChat article URLs, or recent articles from a WeChat Official Account. Produces a valid CSS file conforming to wenyan and ready for wx-mp-publisher.

2026-06-258.3k

video-product

TeamWiseFlow/xiaobei

一站式短视频制作。支持文章链接、追爆报告、文字主题等多种输入，用 gen.py 直连火山 Seedance / 阿里云百炼 Wan2.7-HappyHorse 端点生成视频素材（声画同出），FFmpeg 组装成片。

2026-06-258.3k

wechat-channels-publish

TeamWiseFlow/xiaobei

通过浏览器自动化发布视频到微信视频号。处理 wujie shadow DOM，支持视频上传、标题描述填写、即时发布。

2026-06-258.3k

name	rss-reader
description	Discover the RSS/Atom feed URL for a website, then run the fetch-rss.mjs script to retrieve and parse articles from the feed.
metadata	{"openclaw":{"emoji":"📡","always":false,"requires":{"bins":["node"]}}}

RSS / Atom Feed Reader

Use this skill when:

The user wants to monitor or retrieve updates from a website
The user provides an RSS or Atom feed URL directly
You need to efficiently collect multiple articles from one source without visiting each page

📍 全局技能路径提示：文中所有 ./scripts/ 路径均相对于本技能所在目录（即 <skill> 标签 location 属性所指目录），不是工作区目录。执行时按本技能实际安装路径拼接。

Step 1 — Discover the feed URL

If you already have an RSS/Atom URL, skip to Step 2.

Method A — page source Navigate to the website, take a snapshot, and look for <link rel="alternate"> tags in <head>:

<link rel="alternate" type="application/rss+xml" href="/feed">
<link rel="alternate" type="application/atom+xml" href="/atom.xml">

Method B — common paths (try one at a time until one returns XML)

/feed  /feed.xml  /rss  /rss.xml  /atom.xml  /index.xml
/?feed=rss2  /feeds/posts/default

Method C — look for RSS icons 🟠 or links labelled "RSS", "Subscribe", "Feed".

A valid feed URL returns XML starting with <rss, <feed, or <rdf:RDF.

Step 2 — Run the script

node /path/to/wiseflow/skills/rss-reader/scripts/fetch-rss.mjs <feed_url> [--limit N] [--skip url1,url2,...]

Option	Description
`--limit N`	Max entries to return (default: 20)
`--skip url1,url2,...`	Skip entries whose URLs are already processed (deduplication)

Output is markdown with two sections:

Full-content articles — entries where the feed includes the complete article body (>200 chars). Process these directly; no need to visit the article URL.
Summary-only links — entries with only a short snippet. Visit each URL to retrieve the full content.

Step 3 — Handle results

For full-content articles: extract title, author, date, and content directly from the script output.
For summary-only links: use browser.navigate(url) to fetch each article page.
Pass the script output directly to the user or to your processing pipeline.

Edge cases

Situation	Action
Feed returns 404	Try alternative paths from Step 1
Feed requires login	Follow the browser-guide skill
Script error "Failed to parse feed"	Feed XML may be malformed; report the URL to the user
Empty feed	Report: "This RSS feed has no entries."