← Back to Skills Marketplace
social-parser
by
AIconductor
· GitHub ↗
· v1.0.1
· MIT-0
92
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install social-parser
Description
解析抖音视频和小红书笔记，提取标题、封面、描述、标签、作者等核心信息。当用户想解析、获取、抓取、提取抖音视频数据、小红书笔记内容，或粘贴了抖音/小红书链接希望查看内容详情时调用。常见表达：'帮我解析这个抖音链接'、'获取小红书笔记内容'、'抓取视频信息'、'提取这条小红书的标题标签'、'分析这个视频'。
Usage Guidance
This skill is internally consistent: it tells the agent to use a third‑party CLI to fetch and parse Douyin/Xiaohongshu content and does not ask for unrelated credentials. Before installing or running it, verify the gnomic-cli package/repo (review source, maintainer, recent changes) because the SKILL.md suggests installing it from npm/GitHub — npm packages run code on your machine. Prefer installing in a sandbox or running the CLI manually and pasting results to the agent if you are unsure. Also consider legal/ToS implications of scraping platform content and be cautious about handling private or copyrighted material.
Capability Analysis
Type: OpenClaw Skill
Name: social-parser
Version: 1.0.1
The skill instructions in SKILL.md direct the AI agent to perform a global software installation (npm install -g gnomic-cli) if the tool is missing. This pattern is risky as it allows for the execution of arbitrary code during the installation process via npm post-install scripts. While the tool's stated purpose is parsing social media links from Douyin and Xiaohongshu, the requirement to install unverified third-party software from a personal GitHub repository (https://github.com/huyi9531/gnomic_cli) introduces a potential supply chain risk.
Capability Assessment
Purpose & Capability
Name/description match the runtime instructions: the SKILL.md tells the agent to run a CLI (gnomic) to parse Douyin and Xiaohongshu links and extract title, cover, text, tags, author, and media URLs. No unrelated env vars, binaries, or config paths are requested.
Instruction Scope
Instructions are narrowly scoped to (1) detect link type, (2) run `gnomic social dy-video <url>` or `gnomic social xhs-note <url>`, and (3) parse/display returned JSON. They explicitly state remote API calls will be made and provide a text output flag. The SKILL.md does not instruct reading arbitrary local files or unrelated env vars.
Install Mechanism
There is no formal install spec in the metadata, but the SKILL.md recommends `npm install -g gnomic-cli` and points to a GitHub repo. That means at runtime the agent or user may download and run third‑party code from npm/GitHub. Installing global npm packages executes remote code and can modify your system; verify the package and its maintainer before installing.
Credentials
The skill declares no required environment variables, credentials, or config paths. That is proportionate to the described functionality. Note: the external gnomic CLI or the remote APIs it calls might have their own requirements (not declared here).
Persistence & Privilege
The skill is not always-on and does not request elevated privileges or to modify other skills or system-wide agent settings. Autonomous invocation is allowed by default but is not combined here with other high-risk features.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install social-parser - After installation, invoke the skill by name or use
/social-parser - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
No file changes detected in this version.
- No code or documentation updates were made.
- Version number was incremented without any detected modifications.
v1.0.0
Initial release of social-parser.
- Supports parsing Douyin video and Xiaohongshu note links, extracting core info like title, cover, description, tags, author, and more.
- Provides CLI commands: gnomic social dy-video <url> for Douyin; gnomic social xhs-note <url> for Xiaohongshu.
- Outputs structured JSON with extracted data for both platforms.
- Offers a -f text option for human-readable results.
- Includes guidelines for link type recognition and handling different formats (shortlinks, share texts).
- Details platform-specific output fields and known limitations (e.g., Xiaohongshu does not return interaction data or author info).
Metadata
Frequently Asked Questions
What is social-parser?
解析抖音视频和小红书笔记，提取标题、封面、描述、标签、作者等核心信息。当用户想解析、获取、抓取、提取抖音视频数据、小红书笔记内容，或粘贴了抖音/小红书链接希望查看内容详情时调用。常见表达：'帮我解析这个抖音链接'、'获取小红书笔记内容'、'抓取视频信息'、'提取这条小红书的标题标签'、'分析这个视频'。 It is an AI Agent Skill for Claude Code / OpenClaw, with 92 downloads so far.
How do I install social-parser?
Run "/install social-parser" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is social-parser free?
Yes, social-parser is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does social-parser support?
social-parser is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created social-parser?
It is built and maintained by AIconductor (@huyi9531); the current version is v1.0.1.
More Skills