← Back to Skills Marketplace
songxianqun

小红书视频深度总结

by songxianqun · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
52
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install xhs-video-summary
Description
一键分析小红书视频链接，提取文案、转录语音并深度总结视频内容。当用户提供小红书链接并要求“总结、分析、提取视频”时触发此技能。
README (SKILL.md)

小红书视频深度总结 (xhs-video-summary)

技能说明

这个技能组合了无水印视频提取、音频分离、AI语音转录和深度文本总结，实现小红书视频的一键分析。支持 Windows / macOS / Linux 跨平台运行。

工作流

当用户提供小红书视频链接时，请按照以下步骤执行：

  1. 执行自动化脚本： 运行封装好的 Python 脚本，传入用户提供的 URL。

    python skills/xhs-video-summary/scripts/run.py "\x3Cxhs_url>"

    注意：这可能需要 1-2 分钟时间，请在执行时向用户说明正在后台处理。

  2. 读取产物： 脚本执行完成后，读取提取出的元数据和语音转录稿：

    • 元数据：xhs_meta.json (包含标题、描述、点赞等数据)
    • 逐字稿：xhs_temp.txt (视频内的所有语音文字)

  3. 分析与输出总结： 根据读取到的数据，给用户输出一份结构化的深度总结，必须包含以下模块：

    • 🎬 视频基础信息 (标题、作者、互动数据)
    • 💡 视频主题 (一句话概括核心话题)
    • 📝 详细内容拆解 (按逻辑或知识点拆解详细内容)
    • 🛠 实用价值 (对观众的具体帮助)
    • 💎 关键金句 (原话摘录 2-3 句)

  4. 清理临时文件： 读取完成后，务必清理临时产物文件：

    rm xhs_temp.mp4 xhs_temp.mp3 xhs_temp.txt xhs_meta.json

    (Windows 系统下请使用 del /f xhs_temp.mp4 xhs_temp.mp3 xhs_temp.txt xhs_meta.json)

依赖要求

  • xiaohongshu-extract (需通过 clawhub 安装)
  • curl (用于下载视频)
  • ffmpeg (用于提取音频)
  • openai-whisper (用于本地语音识别)
Usage Guidance
Before installing, make sure the required tools and the separate `xiaohongshu-extract` skill come from trusted sources. Run the skill in a safe working directory because it downloads media and creates/deletes fixed temporary files.
Capability Analysis
Type: OpenClaw Skill Name: xhs-video-summary Version: 1.0.0 The skill is designed to summarize Xiaohongshu videos by extracting metadata, downloading the video, and transcribing audio. The implementation in `scripts/run.py` uses safe subprocess calls (list-based arguments) to invoke `curl`, `ffmpeg`, and `whisper`. The workflow described in `SKILL.md` is consistent with the code logic, and there are no indicators of data exfiltration, malicious prompt injection, or unauthorized system access.
Capability Assessment
✓ Purpose & Capability
The stated purpose in SKILL.md is to extract Xiaohongshu video metadata, transcribe audio, and summarize it; scripts/run.py implements that same workflow with metadata extraction, video download, audio extraction, and Whisper transcription.
✓ Instruction Scope
The skill is scoped to cases where the user provides a Xiaohongshu link and asks for summarization, analysis, or extraction; no artifact asks the agent to override user intent or ignore safety boundaries.
ℹ Install Mechanism
SKILL.md lists required local binaries and a separate `xiaohongshu-extract` dependency, while the registry has no install spec; the dependency is disclosed but its code is outside this artifact set.
ℹ Credentials
The script uses local command-line tools and writes fixed temporary outputs such as `xhs_temp.mp4`, `xhs_temp.mp3`, `xhs_temp.txt`, and `xhs_meta.json`; this is proportionate for video processing but has local disk and compute side effects.
ℹ Persistence & Privilege
No credentials, background service, or long-term persistence are shown, but temporary video/audio/transcript files may remain if processing or cleanup is interrupted.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install xhs-video-summary
  3. After installation, invoke the skill by name or use /xhs-video-summary
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
xhs-video-summary 1.0.0 - Initial release of the 小红书视频深度总结 skill. - Supports one-click extraction, transcription, and deep summarization of Xiaohongshu video links. - Provides structured output including video info, theme, content breakdown, practical value, and highlight quotes. - Automates video/audio extraction, AI speech-to-text, and detailed content analysis. - Includes support for necessary dependencies and automated file cleanup after processing.
Metadata
Slug xhs-video-summary
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is 小红书视频深度总结?

一键分析小红书视频链接，提取文案、转录语音并深度总结视频内容。当用户提供小红书链接并要求“总结、分析、提取视频”时触发此技能。 It is an AI Agent Skill for Claude Code / OpenClaw, with 52 downloads so far.

How do I install 小红书视频深度总结?

Run "/install xhs-video-summary" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 小红书视频深度总结 free?

Yes, 小红书视频深度总结 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 小红书视频深度总结 support?

小红书视频深度总结 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 小红书视频深度总结?

It is built and maintained by songxianqun (@songxianqun); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463556 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259610 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200551 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191226 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190235 · by oswalpalash

💬 Comments