ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified productivity Safety 4/5

knowledge-base-collector

Collect and organize a personal knowledge base from URLs (web/X/WeChat) and screenshots. Use when the user says they want to save an URL, ingest a link, archive content to KB, tag/classify notes, store screenshots, or search their saved knowledge in Telegram. Supports WeChat via a connected macOS node when cloud fetch is blocked.

Why use this skill?

Seamlessly archive web links, WeChat posts, and screenshots into your private knowledge base with automatic tagging and searchable indexing for OpenClaw.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/reed1898/knowledge-base-collector
Or

What This Skill Does

The knowledge-base-collector is an advanced ingestion and archival agent skill designed to bridge the gap between ephemeral online content and a persistent, searchable personal knowledge base. It streamlines the capture of URLs (Web, X, WeChat) and visual information (screenshots) into a structured local filesystem. By storing data in a consistent format with content.md and meta.json pairs, it ensures that your digital footprint is organized, tagged, and ready for retrieval through the OpenClaw ecosystem.

Installation

To integrate this skill, run the following command in your terminal: clawhub install openclaw/skills/skills/reed1898/knowledge-base-collector Ensure your local environment has Python 3 installed and the /home/ubuntu/.openclaw/kb directory is writable for the agent.

Use Cases

  • Unified Archiving: Save interesting web articles, threads from X, or WeChat official account posts directly into your knowledge base for future reading.
  • Visual Knowledge Management: Ingest screenshots of UI flows, code snippets, or diagrams by piping them through an OCR workflow to ensure they are full-text searchable.
  • Knowledge Retrieval: Leverage the built-in search tool to query your collected archives via Telegram, enabling quick access to saved insights without leaving your messaging app.
  • WeChat Resilience: Overcome common cloud-based crawling blocks by utilizing linked macOS nodes to bypass network restrictions for popular Chinese social media content.

Example Prompts

  1. "Save this X post to my KB and add the tag #ai-trends so I can find it later."
  2. "Search my knowledge base for any saved notes related to 'mcp' or 'coding-agent' from the last 7 days."
  3. "I just sent a screenshot of a pricing chart; please ingest this into my knowledge base and tag it as #pricing."

Tips & Limitations

  • Sensitivity Filtering: Always ensure screenshots containing API keys or private tokens are sanitized before ingestion. The tool supports manual oversight to replace sensitive data with REDACTED.
  • WeChat Handling: If the cloud-based fetch returns a verification error, the tool automatically creates a placeholder with the #needs-manual tag. When a macOS node is connected, it will attempt to sync these entries automatically.
  • Tagging Strategy: Use descriptive, hierarchical tags (e.g., #database, #security) to make your index.jsonl more effective during complex searches.

Metadata

Author@reed1898
Stars1171
Views2
Updated2026-02-19
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-reed1898-knowledge-base-collector": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#knowledge-base#archiving#productivity#ocr#wechat
Safety Score: 4/5

Flags: network-access, file-write, file-read, data-collection, code-execution