Shelv converts complex PDF documents into structured, searchable Markdown filesystems that can be navigated using standard Unix tools.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install shelv
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 shelv 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 Shelv?
Shelv is a powerful utility designed to bridge the gap between static PDF documents and actionable developer workspaces. By leveraging Openclaw Skills, it processes contracts, research papers, and technical manuals into organized Markdown structures.
This tool allows developers and AI agents to interact with document content using familiar commands like ls, grep, and find, making deep-text analysis seamless within a coding environment. By converting non-structured data into a filesystem, Shelv enables better context management for AI-driven workflows.
Shelv Use Cases
- Converting legal contracts into categorized Markdown clauses for rapid legal review.
- Transforming academic papers into structured files for enhanced AI-assisted research.
- Automating the ingestion of technical documentation into a local development workspace.
- Searching through massive PDF sets using standard command-line tools after workspace hydration.
How Shelv Works
- Upload a PDF document via the API or provided shell scripts to initialize a new shelf.
- The system initiates an asynchronous pipeline that moves through parsing, structuring, and verifying stages.
- Poll the shelf status using the provided scripts until it reaches a ready or review state.
- Hydrate the workspace by downloading and extracting the processed Markdown archive into a local directory.
- Explore the structured content using standard terminal utilities like cat and grep for immediate data retrieval.
Shelv Setup
To get started with this skill, you must first obtain an API key from shelv.dev. Configure your environment and ensure the necessary dependencies are met:
# Set your API key
export SHELV_API_KEY='your_api_key_here'
# Ensure binary dependencies are installed
# Requires: curl, tar, jq, shasum
# Upload a document to start processing
SHELF_ID=$(./scripts/shelv-upload.sh /path/to/document.pdf --name "Research-Paper")
Shelv Data Schema & Taxonomy
Shelv organizes processed documents into a predictable directory structure within the local workspace. Data is stored at ~/.openclaw/workspace/shelves/{name}/.
| Attribute | Description |
|---|---|
publicId |
The unique identifier for the shelf (e.g., shf_...) |
status |
Current lifecycle state: uploading, parsing, structuring, verifying, ready, or failed |
template |
The structural logic applied (book, legal-contract, or academic-paper) |
files |
A flat JSON map or physical directory of Markdown files |
README.md |
An auto-generated summary and table of contents for the processed document |
Shelv Advanced Features
- Review Mode: Enables a manual intervention step where users can approve or regenerate the document structure before finalization.
- Structural Templating: Use specialized templates for legal contracts or academic papers to ensure domain-specific parsing accuracy.
- Status-Gated Endpoints: Integrated logic that prevents file access until the processing reaches a stable ready state.
- Force Hydration: Overwrite existing local shelf directories to ensure your workspace reflects the latest document version.
- Direct File Lookups: Retrieve individual Markdown files via API without needing to download the entire document archive.
SKILL.md
Loading
Related Openclaw Skills
Reeflux Skill
The Reeflux Skill is a specialized tool for visual observation and ambient exploration of the Reeflux web environment.
TinyTalkingTodos CLI
A powerful command-line interface for TinyTalkingTodos that enables real-time task synchronization and batch management.
OpenWeather
A Python-powered skill for retrieving global weather data, including current conditions and multi-day forecasts for AI agents.
PR + Commit Workflow
A specialized skill designed to enforce high-signal, human-verified commit and pull request workflows within AI-driven development environments.
Dokploy Deployment Management
A comprehensive interface to programmatically manage Dokploy projects, deployments, and infrastructure through its native API.
Pi Health Monitor
A lightweight diagnostics script to monitor thermal performance, power stability, and resource usage on Raspberry Pi hardware.
Featured*
