An advanced retrieval and synthesis skill that connects AI agents to curated knowledge bases for grounded, source-backed answers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ragora
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 ragora 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 Ragora?
The Ragora skill provides a powerful bridge between AI agents and structured knowledge collections, enabling high-fidelity retrieval-augmented generation. By leveraging the Openclaw Skills ecosystem, developers can integrate Ragora using either the Model Context Protocol (MCP) or a traditional REST API. This skill is designed for scenarios where accuracy is paramount, allowing agents to search through curated documents, extract semantic chunks, and provide answers that are fully grounded in verified data. Ragora manages complex data structures including versioned documentation, custom tags, and metadata filters, ensuring that agents can access precisely the information they need.
Whether you are building internal tools for employee support or research agents that crawl marketplace data, this skill offers a robust framework for evidence-based synthesis. It includes built-in mechanisms for source attribution, confidence scoring, and usage tracking. Using Ragora within Openclaw Skills ensures that your AI coding agents have a reliable source of truth, reducing hallucinations and providing clear citations for every claim made during the conversation.
Ragora Use Cases
- Researching complex technical topics across multiple internal or external knowledge bases.
- Comparing information, such as SLA terms or policy changes, across different document versions or collections.
- Performing automated due diligence and security posture assessments using marketplace data products.
- Providing source-backed answers for HR, legal, or compliance inquiries within a corporate environment.
How Ragora Works
- The agent starts by discovering available knowledge collections using either MCP tools or REST API endpoints.
- When a user asks a question, the agent identifies the most relevant collections based on descriptions and metadata provided by Openclaw Skills.
- The skill performs a semantic search across selected collections, retrieving optimized text chunks and associated metadata.
- The agent synthesizes the retrieved evidence, resolving any conflicting information by prioritizing recency and relevance scores.
- A final response is generated containing the direct answer, bulleted evidence with source citations, and confidence indicators.
Ragora Setup
To get started, you must obtain a Ragora API key and set it as an environment variable. Follow these steps to integrate with Openclaw Skills:
- Create an API key at
https://app.ragora.app/settings/api-keys. - Set the environment variable in your system:
export RAGORA_API_KEY='sk_live_your_uuid_here'
- Configure your agent using the MCP gateway URL:
name: ragora
type: http
url: https://mcp.ragora.app/mcp
headers:
Authorization: Bearer ${RAGORA_API_KEY}
- Verify the connection by running a health check command:
curl -s https://api.ragora.app/v1/health
Ragora Data Schema & Taxonomy
Ragora organizes data into a hierarchical structure to facilitate precise retrieval within Openclaw Skills:
| Level | Description |
|---|---|
| Collection | A curated knowledge base (e.g., 'Employee Handbook') identified by a unique slug. |
| Document | Individual files or pages within a collection, such as PDFs or Markdown files. |
| Chunk | Small passages of text optimized for semantic search and context windows. |
| Version | Supports multiple iterations of documentation (e.g., v1.0, v2.0) for historical or API tracking. |
| Metadata | Custom tags and key-value filters used to constrain searches to specific regions, departments, or categories. |
Ragora Advanced Features
- Dynamic Tool Generation: The skill automatically exposes collection-specific tools like search_{slug} based on user permissions.
- Multi-Pass Retrieval: Supports iterative querying to refine broad research tasks into specific factual lookups.
- Version Scoping: Specifically target documentation versions to compare changes over time or maintain legacy support.
- Cross-Collection Comparison: Native prompts designed to synthesize and compare data points between disparate knowledge bases.
- Usage Monitoring: Integrated billing and balance checks to manage credits for pay-per-use marketplace data.
SKILL.md
Loading
Related Openclaw Skills
Agent Ethos
A conceptual framework of mental models and behavioral principles designed to refine AI agent personality and decision-making integrity.
Token Unlock Pro
A professional-grade token unlock alert and analysis system providing real-time monitoring and historical price trend predictions.
Smart Money Tracker
A comprehensive on-chain intelligence system for tracking large transactions, whale movements, and institutional fund flows across multiple blockchains.
River Autotrader
A real-time cryptocurrency information tracker and analysis tool for the River ($RIVER) token ecosystem.
AWS Lambda
A comprehensive tool for managing AWS Lambda serverless functions, including deployment, invocation, and real-time log monitoring.
Evernote Skill
A powerful integration for programmatically managing Evernote notes, notebooks, and tags through a standardized API interface.
Featured*
