SkillHub

x-reader

v0.2.0

获取、转录并分析多平台URL、文件或文本,提供个性化多维洞察。

Sourced from ClawHub, Authored by Yujun

Installation

Please help me install the skill `x-reader` from SkillHub official store. npx skills add lifecn/x-reader

x-readernnUniversal content reader — fetch, transcribe, and digest content from any platform.nn## TriggernnWhen user sends content (URL, text, or transcript) with analysis intent:n- 「analyze [URL]》n- "Analyze this article"n- "What are the key takeaways?"n- Auto-triggered after video/podcast transcription (from video skill)nn## Pipelinenn### Step 1: Get ContentnnChoose tool based on input type:nn| Input | Tool |n|-------|------|n| Tweet URL | or Jina Reader |n| Web URL | or Jina Reader |n| Local file | Read file directly |n| Transcript from video skill | Use directly |nn### Step 2: Multi-Dimensional AnalysisnnScan content across these dimensions. Only output dimensions with actual content — skip empty ones.nnnn### Step 3: Personalized Relevance (Customizable)nnMap insights to YOUR context. Edit the dimensions below to match your own projects, interests, and systems.nnnn> Customization: Edit the dimensions in Step 2 and Step 3 to match your ownn> domain. A trader might add "Market Impact" and "Risk Assessment". A developern> might add "Architecture Patterns" and "Tech Debt". Make it yours.nn## Output Modesnn| Mode | Trigger | Output |n|------|---------|--------|n| Full (default) | | All dimensions |n| Sparse | | Only hit dimensions, skip empty |n| Brief | | Action items only |nn## Best Practicesnn1. Scan all dimensions, but don't force-fill — skip empty dimensions cleanlyn2. Actions must be specific — not "learn about X" but "read X docs chapter Y"n3. Distinguish fact from opinion — mark the author's claims vs verified factsn4. Source everything — tag where each insight comes from in the original contentn5. ROI awareness — not every action is worth doing, assess effort vs impactnn## Supported Platformsnn| Platform | Text Fetch | Video/Audio Transcript |n|----------|-----------|----------------------|n| YouTube | ✅ Jina | ✅ yt-dlp subtitles → Groq Whisper fallback |n| Bilibili (B屏) | ✅ API | ✅ via Claude Code skill |n| X / Twitter | ✅ Jina → Playwright | — |n| WeChat (微信公众号) | ✅ Jina → Playwright | — |n| Xiaohongshu (小红书) | ✅ Jina → Playwright | — |n| Telegram | ✅ Telethon | — |n| RSS | ✅ feedparser | — |n| 小宇舟 (Xiaoyuzhou) | — | ✅ via Claude Code skill |n| Apple Podcasts | — | ✅ via Claude Code skill |n| Any web page | ✅ Jina fallback | — |nn> *XHS requires a one-time login: (saves session for Playwright fallback)n>n> YouTube Whisper transcription requires — get a free key from Groqnn## Dependenciesnn- Python package (provides core content fetching)n- Optional: for Whisper transcriptionn- Optional: + for Telegram supportn- Optional: Playwright for browser-based scrapingnn## Source & Issuesnn- Source: https://github.com/runesleo/x-readern- Issues: https://github.com/runesleo/x-reader/issuesn- Author:* @runes_leo