personal-data-harvester

Collect personal content history from Chinese and international platforms into a local SQLite database.

14|4|Updated Mar 31, 2026
One-click install
npx skills add https://github.com/zephyrwang6/allSkills --skill personal-data-harvester-zephyrwang6
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: personal-data-harvester
Source: https://github.com/zephyrwang6/allSkills/tree/main/personal-data-harvester
Command: npx skills add https://github.com/zephyrwang6/allSkills --skill personal-data-harvester-zephyrwang6

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the manual pain of gathering a user's reading, watching, collecting, and note-taking history from multiple platforms and turning it into a consistent local knowledge base.

Core Features & Use Cases

  • Cross-platform harvesting: Collect data from Douban, B站, 小红书, 微信读书, 抖音, Kindle, and related sources.
  • Flexible intake methods: Use browser automation, local cache parsing, or share-sheet link intake depending on the platform.
  • Structured storage: Write items into a local SQLite database with unified fields for titles, creators, tags, ratings, notes, and timestamps.
  • Continuous syncing: Support repeatable harvesting, health checks, and scheduled updates so the dataset stays fresh.
  • Use Case: A user wants to import their Douban book history, sync 微信读书 progress, and preserve Kindle highlights in one place for later AI analysis.

Quick Start

Ask the assistant to harvest your personal content history from the platforms you use most and store it in a local SQLite database.

Frequently Asked Questions about personal-data-harvester

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

FAQPage Schema
Can I use browser automation to extract my WeChat Reading and Douban highlights automatically?

Browser automation can be used to automatically extract personal data such as WeChat Reading progress and Douban highlights. The Skill applies Playwright-based browser automation alongside local file parsing and share-sheet intake to capture content from various platforms.

Can I use browser automation to extract my WeChat Reading and Douban highlights automatically?

Browser automation can be used to automatically extract personal data such as WeChat Reading progress and Douban highlights. The Skill applies Playwright-based browser automation alongside local file parsing and share-sheet intake to capture content from various platforms.

Does personal data harvesting support local SQLite storage for Kindle highlights and Xiaohongshu favorites?

Personal data harvesting supports local SQLite storage for Kindle highlights and Xiaohongshu favorites. Structured storage writes items into a local SQLite database with unified fields for titles, creators, tags, ratings, notes, and timestamps.

What is the best way to sync personal content history across Douban, B站, and Kindle continuously?

The best way to sync personal content history continuously is through repeatable harvesting with health checks and scheduled updates. This keeps your local SQLite dataset fresh by regularly re-ingesting records from platforms like Douban, B站, and Kindle.

What platforms are supported for cross-platform ingestion of personal notes and favorites?

Cross-platform ingestion supports Douban, B站, Xiaohongshu, WeChat Reading, Douyin, and Kindle. Data harvesting applies platform-specific fallbacks to collect reading records, watching history, favorites, highlights, and notes into a consistent local database.