Knowledge for Openclaw

A unified system for capturing, organizing, and retrieving URLs, research, and media extracts through a file-based structure.

ianderrington
v1.0.0
Feb 27, 2026
1
3.1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install agent-knowledge

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install agent-knowledge 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?

The Knowledge skill provides a robust framework for managing external information and agent-generated research. By utilizing a file-based storage system with an auto-maintained index, it ensures that valuable data—from video summaries to research papers—is never lost in temporary memory. This skill is essential for users of Openclaw Skills who need a structured way to answer "where did we store that?" during complex development or research workflows, providing a permanent home for everything worth re-finding later.

Knowledge Use Cases

  • Bookmarking and summarizing URLs for persistent reference.
  • Capturing extracts and summaries from videos, articles, and academic papers.
  • Saving agent-generated research outputs for long-term project access.
  • Tracking sourced claims and social media content like threads and posts.
  • Maintaining a searchable and tidy library of technical documentation.

How Knowledge Works

  1. Install the skill via the CLI to set up the toolset and default storage directories.
  2. Capture content using specific commands for different media types like URLs, videos, or research outputs.
  3. The skill generates a Markdown file with structured YAML frontmatter and automatically updates a global INDEX.md file.
  4. Users search for information using keyword queries or filter the library by specific tags.
  5. Automated maintenance scripts audit the knowledge base to normalize tags and fix organization issues.

Knowledge Setup

Install the skill using the following command:

clawhub install knowledge

To ensure easy access, add the script to your PATH or use the full path:

~/.openclaw/skills/knowledge/scripts/know

You can configure the storage directory by setting the KNOWLEDGE_DIR environment variable.

Knowledge Data Schema & Taxonomy

The skill organizes data in a hierarchical folder structure under ~/.soulshare/agent/knowledge/. Each entry consists of a Markdown file with specific YAML metadata fields.

Directory Content Type
urls/ Bookmarked website links
extracts/ Summaries of videos, articles, and papers
posts/ Social media content and threads
research/ Outputs from agent research tasks

Frontmatter Schema:

  • type: The entry category (url, extract, post, or research).
  • tags: An array of strings for categorization.
  • source_url: The original link for the information.
  • summary: A concise one-line description.

Knowledge Advanced Features

  • Intelligent tidy --fix command to automatically normalize tags and repair misplaced files.
  • Full integration with QMD for advanced collection indexing and semantic searching.
  • Automated rebuilding of the INDEX.md file for rapid manual browsing.
  • Support for custom storage locations via environment variables or configuration files.
  • Validation tools to ensure all entries adhere to the required metadata schema.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*