A sophisticated content ingestion engine that turns articles and notes into structured Markdown with automated syncing to Obsidian, Feishu, and Tencent IMA.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install knowledge-organizer
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 knowledge-organizer 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 Knowledge Organizer?
Knowledge Organizer is a high-performance utility designed for the modern researcher and developer. It serves as a bridge between fragmented web content and structured personal knowledge bases. By leveraging Openclaw Skills, this tool automates the tedious process of normalizing data from WeChat, Xiaohongshu, and general web pages into clean Markdown, complete with YAML frontmatter, verified tags, and AI-generated summaries.
Beyond mere extraction, it provides a robust synchronization layer. Whether you prefer the local-first approach of Obsidian or the collaborative environments of Feishu and Tencent IMA, Knowledge Organizer ensures your data is deduplicated, formatted correctly, and enriched with related-note suggestions. It effectively eliminates manual entry, allowing you to focus on synthesis rather than organization.
Knowledge Organizer Use Cases
- Automatically convert WeChat public account articles and Xiaohongshu posts into structured notes.
- Synchronize a centralized knowledge base across Obsidian, Feishu Wiki, and Tencent IMA simultaneously.
- Perform automated duplicate detection to maintain a clean, high-quality knowledge repository.
- Generate SEO-friendly summaries and linkable related-note suggestions for better PKM navigation.
- Archive web content with full image localizing, preserving remote assets into a local assets folder.
How Knowledge Organizer Works
- Content Acquisition: Fetches raw data using specialized extractors like xiaohongshu-mcp for social posts or browser-based tools for WeChat articles.
- Normalization: Processes the source through internal models to create a standardized ImportDraft, handling images and relative references.
- Deduplication: Runs a multi-factor check (URL, hash, and title similarity) to ensure no redundant content is added to the database.
- Enrichment: Validates tags against a predefined contract and generates metadata including summaries and importance ratings.
- Orchestration: Dispatches the processed note to selected destinations (Obsidian, Feishu, or IMA) based on user configuration.
- Final Write/Sync: Writes directly to the local filesystem for Obsidian or interacts with Openclaw Skills plugins for cloud-based API syncing.
Knowledge Organizer Setup
To get started with this skill, ensure you have the required environment variables configured for your target platforms:
# Set your knowledge base root
export OPENCLAW_KB_ROOT="/path/to/your/vault"
# For Tencent IMA integration
export IMA_OPENAPI_CLIENTID="your_client_id"
export IMA_OPENAPI_APIKEY="your_api_key"
# Install the skill via Openclaw
openclaw skills install knowledge-organizer
For Feishu synchronization, ensure the openclaw-lark plugin is active in your environment.
Knowledge Organizer Data Schema & Taxonomy
The skill enforces a strict data contract for every note to ensure long-term maintainability within your Openclaw Skills ecosystem:
| Field | Description |
|---|---|
| Frontmatter | Includes title, aliases, tags, source_url, and canonical_hash. |
| Tags | Requires at least 1 domain tag and 1 type tag (5-10 total). |
| Assets | Remote images are downloaded to assets/ with relative Markdown linking. |
| Sync State | Uses a .sync-state.json file to track content hashes and avoid redundant API calls. |
| Payloads | Obsidian uses raw Markdown; Feishu/IMA use specialized JSON payloads for API ingestion. |
Knowledge Organizer Advanced Features
- Multi-mode synchronization: Choose between
mode=oncefor imports ormode=syncfor delta updates. - Flexible image handling: Supports
srcset,data-src, and responsive image candidates during extraction. - Custom transport overrides: Use
FEISHU_IMPORT_ENDPOINTfor specialized enterprise routing. - Seamless MCP integration: Native support for
xiaohongshu-mcpfor high-fidelity social media extraction. - Dry-run validation: Test your sync logic and tag validation without writing to the final destination.
SKILL.md
Loading
Related Openclaw Skills
PDFMonkey
A high-performance skill for automating PDF document generation from dynamic templates using the PDFMonkey API and Membrane protocol.
Book Sum
A powerful utility to generate non-truncated, comprehensive book summaries including deep-dive narratives on key concepts.
Talend Integration for AI Agents
A powerful data management skill that enables AI agents to orchestrate Talend jobs, pipelines, and connections through the Membrane framework.
Tavily Search Skill for OpenClaw
A high-performance search integration that provides OpenClaw agents with AI-optimized web research and real-time information retrieval.
Email Sequence Skill
An AI-powered copywriting engine designed to architect and write multi-stage email marketing campaigns with strategic timing and mobile-first formatting.
AgentMemory Skill
A persistent memory framework that allows AI agents to remember facts, track entities, and learn from past experiences across sessions.
Featured*
