sm-saver（短信保护程序）

SM Saver

Extracts, summarizes, and logs resources from social media posts or direct URLs.

Output log

Append all saved entries to ~/workspace/resources.md (create if missing).

Workflow

1. Detect source type

2. Fetch content

Twitter/X — use xurl:

{
  "tool": "exec",
  "command": "xurl read <tweet_url>"
}

Parse the JSON response:

• Extract data.text (tweet body)
• Extract data.entities.urls[].expanded_url (linked resources, skip t.co self-references and pic.twitter.com)
• Extract data.author_id or author handle if available

LinkedIn / Direct URL — skip to step 3 directly with the URL itself as the resource.

3. Summarize each resource

For each extracted URL (or the URL itself if direct):

{
  "tool": "exec",
  "command": "summarize \"<url>\" --length short"
}

If summarize is not installed, fall back to:

{
  "tool": "exec",
  "command": "python3 -c \"\
import urllib.request, sys\
req = urllib.request.Request('<url>', headers={'User-Agent': 'Mozilla/5.0'})\
with urllib.request.urlopen(req, timeout=10) as r:\
    html = r.read().decode('utf-8', errors='ignore')\
import re\
title = re.search(r'<title>(.*?)</title>', html, re.I)\
print(title.group(1).strip() if title else '<url>')\
\""
}

If a URL is inaccessible (auth wall, timeout), note it as [inaccessible] and continue.

4. Append to resources.md

Format — strict, no deviation:

## {YYYY-MM-DD} · {source_label}
> {tweet text or first sentence of post — max 120 chars, truncate with …}

{For each resource:}
- [{title}]({url}) — {1-line summary, max 80 chars}

---

source_label:

• Twitter: @{handle} if extractable, else X
• LinkedIn: LinkedIn
• Direct: domain name (e.g. github.com)

5. Confirm to user

Respond with exactly:

💾 {N} resource(s) saved · {source_label}
{title of first resource, truncated to 60 chars}

If nothing was extractable: ⚠️ No resources found in this link.

Examples