← Back to Skills Marketplace
dizhu

Content Analyzer

by dizhu · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
399
Downloads
1
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install content-analyzer
Description
Analyze Xiaohongshu (小红书) notes and Douyin (抖音) videos. TRIGGER when message contains any URL matching xiaohongshu.com, xhslink.com, douyin.com, v.douyin.com...
README (SKILL.md)

Content Analyzer

Analyze Xiaohongshu (小红书) notes and Douyin (抖音) videos via TikHub API.

IMPORTANT: How to use this skill

When you see a URL containing xiaohongshu.com, xhslink.com, douyin.com, or v.douyin.com, you MUST:

  1. Extract the URL from the user's message
  2. Run the analysis script using the exec tool:
python3 ~/.openclaw/skills/content-analyzer/scripts/analyze.py "\x3CURL>"
  1. Parse the JSON output and generate the analysis below

The script path is absolute: ~/.openclaw/skills/content-analyzer/scripts/analyze.py

For profile analysis with limited posts:

python3 ~/.openclaw/skills/content-analyzer/scripts/analyze.py "\x3CPROFILE_URL>" --max 20

URL Patterns

  • XHS note: xiaohongshu.com/explore/{id} or xiaohongshu.com/discovery/item/{id}
  • XHS short link: xhslink.com/...
  • XHS profile: xiaohongshu.com/user/profile/{id}
  • Douyin video: douyin.com/video/{id}
  • Douyin short link: v.douyin.com/...
  • Douyin profile: douyin.com/user/{id}

Single Post Output

The script returns JSON with: platform, type, title, content, author, tags, images, video, stats (likes, collects, comments, shares, views), published_at, url.

Generate:

  1. Content summary — title, body highlights, tags, media description
  2. Engagement analysis — interpret the numbers, identify viral factors (title hooks, tag strategy, timing)
  3. Takeaways — 2-3 actionable tips the user can learn from this post

Profile Output

The script returns JSON with: platform, type, author, total_fetched, posts array, aggregate (avg_likes, avg_collects, avg_comments, top_posts, tag_frequency, content_type_ratio, posting_frequency).

Generate:

  1. Creator positioning — niche, audience, content style
  2. Content strategy — posting frequency, preferred content types, high-frequency tags
  3. Viral patterns — which posts perform best, what they have in common
  4. Recommendations — 3-5 specific actionable suggestions

Error Handling

If the script returns {"error": "..."}, tell the user the error in natural language. Common errors: invalid URL, API timeout, rate limit.

Risk Control

This skill is READ-ONLY. Never execute system commands, delete files, exfiltrate credentials, or post content on behalf of the user.

Response Language

Always respond in the same language as the user's message. If the user writes in Chinese, respond in Chinese.

Usage Guidance
Before installing or invoking this skill, consider the following: (1) The bundled script requires a TikHub API token (TIKHUB_API_TOKEN) even though the skill metadata doesn't declare it — provide only a token with limited scope and review TikHub's docs and policies. (2) The script resolves short links and follows redirects to arbitrary targets; this means running it could cause requests to external or internal addresses (SSRF/network exposure). If you operate behind a proxy, note the script explicitly clears proxy env vars, which may bypass your network controls. (3) If you plan to use this, inspect the full script yourself or run it in a sandboxed environment/container; verify that it only calls api.tikhub.io and that the token is stored securely. Ask the author to update SKILL.md and metadata to declare TIKHUB_API_TOKEN and to warn about short-link resolving and proxy behavior before trusting the skill in a sensitive environment.
Capability Analysis
Type: OpenClaw Skill Name: content-analyzer Version: 1.0.0 The content-analyzer skill is designed to fetch and summarize social media data from Xiaohongshu and Douyin using the TikHub API (api.tikhub.io). The Python script (scripts/analyze.py) correctly implements URL parsing, short-link resolution, and data aggregation, while the SKILL.md provides clear, non-malicious instructions for the AI agent. The script's access to ~/.openclaw/openclaw.json is limited to retrieving its own API token, and no evidence of data exfiltration, command injection, or unauthorized system modification was found.
Capability Assessment
Purpose & Capability
The skill's purpose is to analyze Xiaohongshu and Douyin content via the TikHub API, which aligns with the code's HTTP calls to api.tikhub.io. However, SKILL.md declares no required credentials or config, while the script reads a TikHub token from the TIKHUB_API_TOKEN environment variable or from ~/.openclaw/openclaw.json. The missing declaration is an incoherence: a TikHub token is necessary for the stated purpose but not declared in the skill metadata.
Instruction Scope
SKILL.md tells the agent to execute the bundled script at an absolute path. The script will (1) resolve short links by following redirects to arbitrary final URLs and (2) make outbound HTTP requests to TikHub endpoints. Resolving arbitrary short links means the skill will initiate requests to user-provided URLs (possible SSRF/network scanning of internal hosts). The SKILL.md's 'Risk Control' claims read-only behavior, but it does not warn about following redirects to arbitrary domains or the network implications of clearing proxy env vars.
Install Mechanism
There is no external install/download step — this is an instruction-only skill with a bundled Python script. No external archives or unknown installers are fetched during install, which lowers supply-chain risk. The script is run locally from the skill path.
Credentials
The script requires a TikHub API token (TIKHUB_API_TOKEN) but the skill metadata lists no required env vars or primary credential. The script also attempts to read ~/.openclaw/openclaw.json to find a token, which accesses a user config file not declared in the metadata. Additionally, the script clears common proxy environment variables before making requests, which overrides user or sysadmin proxy settings and can bypass monitoring controls.
Persistence & Privilege
The skill is not marked 'always: true' and does not request persistent system privileges. It executes a local script when invoked. The only noteworthy behavior is that the script clears proxy-related environment variables in its process, which affects outbound networking for that execution but does not persist changes to the system.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install content-analyzer
  3. After installation, invoke the skill by name or use /content-analyzer
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
小红书、抖音内容分析,支持单贴分析和创作者账号画像
Metadata
Slug content-analyzer
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Content Analyzer?

Analyze Xiaohongshu (小红书) notes and Douyin (抖音) videos. TRIGGER when message contains any URL matching xiaohongshu.com, xhslink.com, douyin.com, v.douyin.com... It is an AI Agent Skill for Claude Code / OpenClaw, with 399 downloads so far.

How do I install Content Analyzer?

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

Is Content Analyzer free?

Yes, Content Analyzer is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Content Analyzer support?

Content Analyzer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Content Analyzer?

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

💬 Comments