X-Read Skill

When to use this skill

Inputs

• url (required): The exact permalink you want to render. Include the full https://x.com/... path so the Puppeteer browser can navigate directly.

What happens when you run it

• Puppeteer launches a sandboxed Chromium instance with a realistic user-agent and loads the URL.
• The script waits for article[data-testid="tweet"] elements, captures the main thread (tweet + up to three replies), and extracts any linked card or media attachments.
• Media is reprinted as ![](...) markdown with ALT text when available, and the main article body is appended beneath the primary tweet.
• The output is a short markdown summary listing the thread author, timestamp, text, links, and media so the Telegram chat stays readable.

Output format

## Tweet Thread Summary
Source: <url>

### **MAIN TWEET** by Display Name (@handle)
*2026-02-21T18:24:00Z*
Tweet text …

**Linked Article:** [Title](card URL)
**Media:**
- ![](media1)
- ![](media2)
---

Limitations and troubleshooting

• The skill only reads publicly available tweets. If X blocks the navigation with a login wall, you will see an error that logging in is required.
• Long-form articles sometimes use article.content; the script appends that text to the main tweet so you still get the full written piece.
• Because the skill uses a browser, it may take a few extra seconds compared to an API call—expect 5–10 seconds per URL.
• For best results, keep the thread URLs focused and don’t try to feed a feed of multiple unrelated URLs at once; run the tool per link.

Testing and safety

• The skill is read-only: it never posts, likes, DM’s, or authenticates to X.
• Review the index.js script if X changes its DOM selectors (it relies on data-testid attributes such as tweet, tweetText, User-Name, and card.wrapper).
• Run the skill manually with openclaw use x-read read_tweet --url before publishing to confirm the output is what you expect.