A seamless utility for scraping web content, performing high-quality translations, and importing formatted Markdown files directly into an Obsidian vault.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install web-to-obsidian
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 web-to-obsidian 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 Web to Obsidian Content Capture?
The Web to Obsidian skill is a comprehensive tool designed for researchers and knowledge workers who want to bridge the gap between web browsing and personal knowledge management. As part of the Openclaw Skills ecosystem, it automates the extraction of clean Markdown from any URL, handles technical translations for multi-lingual research, and organizes the data with rich metadata.
By integrating directly with your local Obsidian environment, it eliminates manual copy-pasting and formatting. The skill ensures that every saved article includes structured YAML frontmatter, relevant tags, and concise summaries, making your knowledge base instantly searchable and well-organized.
Web to Obsidian Content Capture Use Cases
- Archiving technical documentation or blog posts for offline reading within Obsidian.
- Automatically translating foreign language research papers while preserving technical terminology.
- Building a curated knowledge base by batch-importing multiple web URLs.
- Streamlining the capture of web-based tutorials into specific Obsidian folders.
How Web to Obsidian Content Capture Works
- The system triggers a fetch script to extract clean Markdown content from a provided URL.
- It detects the source language and performs a context-aware translation if necessary, ensuring technical terms remain accurate.
- Content analysis is performed to generate a title, tags, and a 100-200 word summary.
- A temporary Markdown file is constructed featuring a full YAML frontmatter header.
- The obsidian-cli tool is invoked to create the note within the user's specified vault and folder.
- Temporary files are purged to maintain a clean workspace environment.
Web to Obsidian Content Capture Setup
To begin using this skill within the Openclaw Skills framework, ensure you have Python 3 and the obsidian-cli installed. Your Obsidian application must be running during the import process.
# Test the fetch utility
python3 scripts/fetch.py "<URL>" --json
# Import to Obsidian via CLI
obsidian create name="Article Title" content="$(cat temp.md)"
Web to Obsidian Content Capture Data Schema & Taxonomy
The skill generates structured Markdown files compatible with Obsidian's internal linking and tagging systems. The data is organized as follows:
| Field | Description | Type |
|---|---|---|
| title | The extracted or generated article headline | String |
| source | The original source URL | URL |
| tags | 3-7 relevant keywords for PKM organization | Array |
| summary | A concise overview of the article content | String |
| translated | Boolean flag indicating if translation was applied | Boolean |
All files include a YAML frontmatter block at the top for metadata indexing.
Web to Obsidian Content Capture Advanced Features
- Technical Translation Engine: High-fidelity translation that preserves code blocks, industry standard terminology, and original formatting.
- Batch Capture: Ability to process multiple URLs in a single command for rapid knowledge base building.
- Custom Folder Routing: Support for organizing imports into specific vault subdirectories using folder path parameters.
- Automatic Metadata Generation: Uses AI to identify core themes and article types for automated tagging within the Openclaw Skills workflow.
SKILL.md
Loading
Related Openclaw Skills
Prompt Engineer
An advanced engineering skill for designing, optimizing, and diagnosing system prompts for autonomous agents and advisory AI using a three-layer architecture.
openclaw-notion-api
A powerful integration for programmatically managing Notion pages, data sources, and media uploads using the latest API specifications.
Daily Oracle
A local-only background agent that generates daily life predictions by analyzing your calendar, messages, and social signals.
Zhihu Content Publisher
An automated tool to publish articles and thoughts on Zhihu using Chrome Browser Relay for seamless browser control.
Groq Voice Transcriber
A high-performance speech-to-text skill that transcribes Telegram voice messages using the Groq Whisper API for lightning-fast AI processing.
XcodeBuildMCP
A robust toolset for managing Xcode builds, test execution, simulator automation, and device debugging through an AI-ready interface.