← Back to Skills Marketplace
4471
Downloads
21
Stars
35
Active Installs
3
Versions
Install in OpenClaw
/install docstrange
Description
Document extraction API by Nanonets. Convert PDFs and images to markdown, JSON, or CSV with confidence scoring. Use when you need to OCR documents, extract invoice fields, parse receipts, or convert tables to structured data.
Usage Guidance
Before installing, confirm you are comfortable sending selected documents to Nanonets and store the API key in an environment variable or other secret manager. Avoid using it on documents containing highly sensitive information unless your Nanonets account and data-handling terms meet your requirements.
Capability Analysis
Type: OpenClaw Skill
Name: docstrange
Version: 1.0.2
The skill bundle is benign. It provides clear documentation for integrating with the Nanonets document extraction API, using standard and secure practices for API key handling (recommending environment variables and warning against insecure storage). All network interactions are explicitly directed to the documented Nanonets API endpoint (`https://extraction-api.nanonets.com`). The `SKILL.md` includes extensive security and privacy guidance for users, demonstrating a commitment to responsible development. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, obfuscation, or prompt injection attempts against the OpenClaw agent.
Capability Assessment
Purpose & Capability
The stated purpose is document extraction through Nanonets, and the described capability is limited to guiding API calls to the documented Nanonets extraction endpoint.
Instruction Scope
No SkillSpector issues were reported, and the supplied telemetry describes explicit API-key handling guidance rather than prompt overrides, hidden instructions, or unrelated data use.
Install Mechanism
No install-time scripts, package hooks, or automatic execution behavior were identified in the supplied scan context.
Credentials
The skill likely requires a Nanonets API key and sends user-selected documents to Nanonets, which is proportionate for document extraction but should be considered for sensitive documents.
Persistence & Privilege
No persistence mechanism, privilege escalation, background worker, local credential harvesting, or broad local indexing was reported.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install docstrange - After installation, invoke the skill by name or use
/docstrange - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Added detailed recommendations to use environment variables for API key management, with security precautions for storing keys in configuration files.
- Introduced a new Security & Privacy section covering data handling, privacy policy review, PII guidance, API key handling, compliance, and operational safeguards.
- Included best practices for limiting permissions, rotating API keys, and monitoring usage.
- Documented file size limits and advice on endpoint usage for large documents.
- Updated and expanded instructions and notes for improved security and operational rigor.
- No functional changes to the API or code itself; documentation and instructions only.
v1.0.1
- Major documentation overhaul: SKILL.md rewritten for clarity and conciseness.
- Simplified setup and quick start instructions.
- Added "Common Tasks" section with focused examples for Markdown, JSON, CSV, and async extraction.
- Clearly listed advanced features such as bounding boxes, hierarchy output, and custom instructions.
- Included schema templates for invoices and receipts.
- Added "When to Use," best practices, troubleshooting guidance, and reference links.
v1.0.0
DocStrange 1.0.0 initial release
- Introduces AI-powered document extraction via the Nanonets API.
- Supports converting PDFs, images, Word, and Excel to markdown, JSON (with confidence scoring), CSV, or HTML.
- OCR capabilities included for scanned documents and images.
- Offers sync extraction for small documents (≤5 pages) and async extraction for larger files.
- Provides setup instructions, usage examples, and integration options for OpenClaw.
- Enables structured data extraction, field parsing (with optional confidence scores), and table-to-CSV export.
Metadata
Frequently Asked Questions
What is Nanonets OCR?
Document extraction API by Nanonets. Convert PDFs and images to markdown, JSON, or CSV with confidence scoring. Use when you need to OCR documents, extract invoice fields, parse receipts, or convert tables to structured data. It is an AI Agent Skill for Claude Code / OpenClaw, with 4471 downloads so far.
How do I install Nanonets OCR?
Run "/install docstrange" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Nanonets OCR free?
Yes, Nanonets OCR is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Nanonets OCR support?
Nanonets OCR is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Nanonets OCR?
It is built and maintained by shhdwi (@shhdwi); the current version is v1.0.2.
More Skills