Sexy-Claw is an automated AI agent skill that discovers and recommends high-value social media influencers and video content based on personalized aesthetic preferences.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install sexy-claw
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install sexy-claw using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Sexy-Claw?
Sexy-Claw is a specialized discovery agent designed to enhance your Openclaw Skills collection by automating content research across major social media platforms. By analyzing user-defined aesthetic preferences—ranging from specific styles like sweet or cool to individual creator benchmarks—this skill identifies trending influencers and high-engagement videos on Xiaohongshu, Douyin, Bilibili, and YouTube.
The skill operates with a focus on personalization and privacy, storing session data and user preferences locally. It bridges the gap between manual browsing and automated discovery by executing platform-specific search scripts and providing direct access to the most relevant visual content currently trending in the ecosystem.
Sexy-Claw Use Cases
- Discovering new influencers on Xiaohongshu or Douyin based on specific visual styles.
- Automating cross-platform content research for creative inspiration or marketing trends.
- Finding creators similar to existing favorites like habin or leeesovely across international and domestic platforms.
- Streamlining video consumption by automatically filtering for the highest-rated content in a specific niche.
How Sexy-Claw Works
- The agent captures user preferences regarding aesthetic styles and favorite creators, storing them in a local configuration file.
- It verifies and utilizes localized platform cookies (web_session, sessionid, SESSDATA) to authenticate search requests on XHS, Douyin, and Bilibili.
- Upon a search trigger, the agent runs dedicated Python scripts that query platform APIs for specific keywords or user IDs.
- Results are processed and ranked based on engagement metrics such as like counts and total views.
- The agent presents a curated list and can trigger the default system browser to open the top-performing video links immediately.
Sexy-Claw Setup
To integrate this into your Openclaw Skills workflow, ensure Python 3 is available in your environment. You must manually provide session cookies for authenticated platforms.
Extract cookies from your browser (F12 → Application → Cookies) for Xiaohongshu, Douyin, and Bilibili, then save them to references/platform_cookies.json. Use the following command structure for manual searches:
# Search Xiaohongshu for specific aesthetic tags
python3 scripts/xhs_search.py "aesthetic_keyword" 10
# Search Bilibili for specific creators
python3 scripts/bilibili_search.py "creator_name" 10
Sexy-Claw Data Schema & Taxonomy
The skill organizes its operations through two primary JSON data structures stored locally:
| File | Purpose | Primary Fields |
|---|---|---|
user_preference.json |
Aesthetic Profiling | preferred_type, favorite_creators, preferred_platforms |
platform_cookies.json |
Session Management | web_session (XHS), sessionid (Douyin), SESSDATA (B站) |
Sexy-Claw Advanced Features
- Multi-platform aggregation supporting both domestic (China) and international video services.
- Automated engagement-based ranking to filter out low-quality results.
- Local-first data persistence ensuring user preferences and session cookies never leave the host machine.
- Support for specific User ID (UID) crawling to fetch complete video histories from individual creators.
SKILL.md
Loading
Related Openclaw Skills
AI Reliability Layer
A collection of three micro-services focused on repairing broken JSON, validating response rules, and generating guaranteed structured data for AI agents.
Data Model Selector
A technical decision framework for selecting between relational, document, and graph data models based on data shape and access patterns.
Encoding Format Advisor
A technical decision-making tool for selecting data encoding formats and designing schema evolution strategies that maintain system compatibility.
High-Value Extractors
A suite of LLM-powered micro-services for extracting structured data from web pages and generating custom AI endpoints from schemas.
Universal Extractor
A multi-service content extraction tool that converts URLs, articles, and complex file formats into clean, structured text.
Expense Assistant
An intelligent reimbursement management assistant that automates receipt recognition, travel allowance calculation, and organized document filing.
Featured*
