deepread-form-fill
AI-powered PDF form filling. Upload any PDF form and your data as JSON — AI detects fields visually, maps your data semantically, fills the form with quality checks, and returns a completed PDF. Works with scanned forms, handwritten templates, and any PDF — no AcroForm fields required.
Why use this skill?
Use DeepRead AI to automatically fill any PDF form—scanned or digital—using JSON data. Eliminate manual data entry and template configuration.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/deepread001/deepread-form-fillWhat This Skill Does
The deepread-form-fill skill is an advanced AI agent capability designed to automate the traditionally tedious process of filling out static, scanned, or non-interactive PDF forms. Unlike standard OCR tools that require rigid templates, coordinate mapping, or AcroForm definitions, this skill utilizes sophisticated computer vision and semantic mapping to understand the document layout visually.
When you provide the agent with a blank PDF and a set of JSON data, the skill identifies field labels and boxes, intelligently maps your data points to the correct locations, and performs a comprehensive quality check. This makes it an ideal solution for processing government documents, insurance applications, scanned medical forms, and custom business templates that were never designed for digital input. The output is a completed, flattened PDF ready for signature or submission.
Installation
To add this skill to your OpenClaw agent environment, use the command-line interface to execute the following command:
clawhub install openclaw/skills/skills/deepread001/deepread-form-fill
Once installed, you must configure your credentials by setting the DEEPREAD_API_KEY environment variable in your project settings. You can obtain a free tier API key by registering at the DeepRead dashboard.
Use Cases
- HR Onboarding: Automatically populate new hire tax forms, benefit enrollment documents, and employee agreements from a centralized employee database.
- Healthcare Intake: Digitally transcribe patient registration data into legacy, non-digitized intake forms, reducing administrative burden for clinical staff.
- Financial Services: Extract data from CRM systems to pre-fill loan applications, mortgage documents, or complex compliance forms.
- Legal Operations: Populate standard legal templates or court documents using data extracted from client case files.
Example Prompts
- "Look at the 'new_employee_packet.pdf' in my downloads folder and fill it out using the candidate details stored in 'candidate_data.json'. Notify me when the result is ready."
- "I need to file these insurance claims. Use the claim data provided in this chat to fill out the attached claim form and save the resulting PDF to my project directory."
- "Upload the tax form template and map the fields using the JSON data I sent yesterday. Make sure to double-check that the SSN and date of birth fields are populated correctly."
Tips & Limitations
- Field Clarity: While the AI is highly intelligent, handwritten forms should be written in clear, block capital letters to maximize accuracy.
- Asynchronous Processing: The skill operates via an asynchronous API. Always design your workflows to handle the job ID polling or configure a webhook URL for real-time notifications once processing completes.
- Data Security: Ensure that your JSON payloads containing sensitive PII (Personally Identifiable Information) are handled within secure environment variables or encrypted memory states when instructing the agent.
- Quality Report: Always review the quality report provided in the job response to identify fields that the AI marked for human review if the source PDF was particularly low-resolution or illegible.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-deepread001-deepread-form-fill": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write, external-api
Related Skills
deepread-agent-setup
Authenticate AI agents with the DeepRead OCR API using OAuth device flow. The agent displays a code, the user approves it in their browser, and the agent receives a DEEPREAD_API_KEY stored as an environment variable.
deepread
AI-native OCR platform that turns documents into high-accuracy data in minutes. Using multi-model consensus, DeepRead achieves 97%+ accuracy and flags only uncertain fields for Human-in-the-Loop (HIL) review—reducing manual work from 100% to 5-10%. Zero prompt engineering required.