Jarmck-Cai/xhs
skills/xhs/SKILL.md
Capture and archive Xiaohongshu (小红书/RED) posts including videos, images, and text. Use when user shares a xiaohongshu.com link and wants to save, archive, analyze, or summarize the content. Supports video analysis via Gemini (optional). Triggers on phrases like "save this XHS link", "archive this xiaohongshu post", "analyze this video from xiaohongshu", or when a xiaohongshu.com URL is shared.
$ install --global
skillsauthnpx skillsauth add Jarmck-Cai/clawdbot-skill-xhs xhsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 5:51 PM134.0s4 files scanned
SKILL.md
- name:
- xhs
- description:
- Capture and archive Xiaohongshu (小红书/RED) posts including videos, images, and text. Use when user shares a xiaohongshu.com link and wants to save, archive, analyze, or summarize the content. Supports video analysis via Gemini (optional). Triggers on phrases like "save this XHS link", "archive this xiaohongshu post", "analyze this video from xiaohongshu", or when a xiaohongshu.com URL is shared.
Xiaohongshu (XHS) Capture Skill
Extracts and archives content from Xiaohongshu posts with a "Triple-Level Archive" strategy.
Quick Start
# Working directory:
# Run these commands from a directory where `skills/xhs/` exists (i.e., `ls skills/xhs` works).
# 0. Load Config (Important!)
# Create a .env file with XHS_COOKIE='...' and XHS_OUTPUT_DIR='...'
# then load it:
source skills/xhs/.env
# 1. Extract data from URL
python3 skills/xhs/scripts/xhs_bridge.py "https://www.xiaohongshu.com/explore/..."
# This writes `xhs_last_run.json` to your current working directory.
# 2. Archive (download media + create note)
python3 skills/xhs/scripts/xhs_archive.py xhs_last_run.json
# 3. With video analysis (requires GEMINI_API_KEY)
python3 skills/xhs/scripts/xhs_archive.py xhs_last_run.json --analyze
Environment Variables
| Variable | Required | Description |
| :--- | :--- | :--- |
| XHS_COOKIE | Yes | Cookie string from logged-in browser session |
| XHS_OUTPUT_DIR | No | Base output directory (default: ./xhs_captures) |
| XHS_NOTES_DIR | No | Override notes directory (advanced) |
| XHS_MEDIA_DIR | No | Override media directory (advanced) |
| GEMINI_API_KEY | No | Enables video analysis via Gemini |
Workflow
- Trigger: User shares
xiaohongshu.comlink - Extract: Run
xhs_bridge.py→ outputsxhs_last_run.json - Archive: Run
xhs_archive.py→ downloads media, creates note - Analyze (optional): If user asks to "analyze the video" and
GEMINI_API_KEYis set, append Gemini analysis
Output Structure
# Default layout (public-friendly)
{XHS_OUTPUT_DIR}/
├── notes/
│ └── YYYY-MM-DD_Title.md # Insight note
└── media/
└── YYYY-MM/
├── ..._video.mp4 # Raw video
├── ..._img1.jpg # Images
└── ..._raw.json # Full metadata
# Advanced: override with XHS_NOTES_DIR + XHS_MEDIA_DIR
Analysis Modes
| Mode | Trigger Phrase | Requirement | | :--- | :--- | :--- | | Basic | "save this", "archive this" | XHS_COOKIE only | | Full | "analyze this video", "what does this say" | XHS_COOKIE + GEMINI_API_KEY |
If GEMINI_API_KEY is not set, provide text-based analysis from the description/comments.
Cookie Setup
- Log in to xiaohongshu.com in browser
- Open DevTools (F12) → Network tab
- Refresh page, click any request
- Copy the
Cookieheader value - Set:
export XHS_COOKIE="..."
Related Skills
steipete/summarize
content-media
VerifiedTrustedCommunity
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
356,423SKILL.mdUpdated Apr 13, 2026
steipete/qqbot-media
content-media
VerifiedTrustedCommunity
QQBot 富媒体收发能力。使用 <qqmedia> 标签，系统根据文件扩展名自动识别类型（图片/语音/视频/文件）。
356,423SKILL.mdUpdated Apr 13, 2026
openclaw/summarize
content-media
VerifiedTrustedCommunity
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
353,662SKILL.mdUpdated Apr 10, 2026
openclaw/qqbot-media
content-media
VerifiedTrustedCommunity
QQBot 富媒体收发能力。使用 <qqmedia> 标签，系统根据文件扩展名自动识别类型（图片/语音/视频/文件）。
353,662SKILL.mdUpdated Apr 10, 2026