personal-data-harvester

Harvestes personal content from multiple platforms into a local SQLite database.

1|Updated May 12, 2026

Search Tags:#automation #cross-platform #sqlite #privacy #harvest #personal-data #content-history

Ready to run

npx skills add https://github.com/cocyuhao/my-ai-skills-library --skill personal-data-harvester

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: personal-data-harvester
Source: https://github.com/cocyuhao/my-ai-skills-library/tree/main/personal-data-harvester
Command: npx skills add https://github.com/cocyuhao/my-ai-skills-library --skill personal-data-harvester

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, requests, beautifulsoup4, pydantic, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Collects and organizes a user’s personal content history from multiple platforms into a local, privacy-preserving store for easy access, analysis, and offline use.

Core Features & Use Cases

Aggregates data from Chinese and international platforms (豆瓣, 小红书, B站, 微信读书, Kindle, etc.) into a single local SQLite database.
Keeps data fresh with automatic harvesting, supports syncing to an AI agent for analysis, and enables offline knowledge-base construction.
Upfront privacy: all data stays on-device unless the user explicitly opts to share.

Quick Start

Configure the skill to begin harvesting personal content history from connected platforms and store results in the local SQLite database.

Frequently Asked Questions about personal-data-harvester

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I aggregate my personal data from 豆瓣, 小红书, and B站 into a single local database?▼

This skill harvests and centralizes personal content history from multiple platforms into a local SQLite database. It applies across 豆瓣, 小红书, B站, 微信读书, and Kindle to build a privacy-preserving data pipeline for AI analysis.

What's the best way to scrape Kindle highlights and 微信读书 history for offline analysis?▼

Scraping Kindle highlights and 微信读书 history is handled by the skill's built-in scripts. It automatically harvests and centralizes this personal content history into a local SQLite database, keeping records fresh and ready for offline analysis.

Do I need Python 3.10 and Playwright to harvest cross-platform personal data?▼

Yes, Python 3.10+ and Playwright are required to harvest cross-platform personal data. The pipeline also depends on sqlite3, requests, beautifulsoup4, and pydantic to execute its initialization, scraping, and health monitoring scripts.

Is my personal data kept private when using automated cross-platform scrapers?▼

Your scraped personal data remains completely private during cross-platform harvesting. All content history stays on-device in a local SQLite database unless you explicitly opt to sync it with an AI agent for analysis.

How do I sync my local SQLite content history with an AI agent?▼

You can sync your local SQLite content history with an AI agent by explicitly opting to share the centralized database. This enables downstream AI analysis and offline knowledge-base construction using your aggregated personal data.