A highly precise visual and semantic resume parsing tool that converts complex CV layouts into structured, validation-ready JSON data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install deepread-resume-parser
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 deepread-resume-parser 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 DeepRead Resume Parser?
DeepRead Resume Parser is a robust integration designed for Openclaw Skills to automate the extraction of candidate information from resumes, CVs, and portfolios. Unlike traditional template-based parsers that break on multi-column layouts or creative designs, this skill uses multi-model consensus to interpret documents visually and semantically, much like a human recruiter would. It processes PDFs, scanned images, and Word files, producing clean JSON payloads containing contact info, work history, education, skills, and calculated years of experience.
By leveraging this parser, developers can construct frictionless recruitment pipelines. It explicitly marks ambiguous fields with a review flag, allowing your Application Tracking System (ATS) to seamlessly ingest reliable data while isolating edge cases for human recruiters. Combined with other Openclaw Skills, it helps build end-to-end automated HR workflows.
DeepRead Resume Parser Use Cases
- ATS Ingestion: Seamlessly parse and auto-populate candidate profiles directly from uploaded resume files, eliminating manual data entry error.
- Bulk Talent Sourcing: Process folders of CVs from job portals to build a structured, searchable talent database.
- Standardized Candidate Screening: Normalize unstructured, creative, and multi-column CVs into a single unified schema for objective evaluation.
- Skills Matching: Programmatically extract skills and tools arrays to cross-reference candidates against open role requisites.
- Unbiased Hiring: Redact personal identifiable information (PII) before resumes reach hiring managers to support fair, anonymized review workflows.
How DeepRead Resume Parser Works
- Document Submission: The user or AI agent posts a resume PDF or scanned image to the DeepRead processor via the API.
- Visual & Semantic Analysis: DeepRead applies multi-model consensus to parse standard fields and complex multi-column structures visually and contextually.
- Extraction & Validation: The processor extracts structured data conforming to your target schema, calculating total experience and listing chronological roles.
- Confidence Tagging: Each output field is assessed, and any ambiguous information (e.g. overlapping roles) is flagged with a
needs_review: truemarker. - Job Completion & Polling: The system polls the job endpoint and returns the fully formed, structured JSON payload ready for database ingestion.
DeepRead Resume Parser Setup
To start parsing resumes with this skill, configure your DeepRead API key as an environment variable.
# Open the DeepRead dashboard to sign up and get your API key
open "https://www.deepread.tech/dashboard/?utm_source=clawhub"
# Export your API key
export DEEPREAD_API_KEY="sk_live_your_key_here"
Alternatively, you can automate authentication with Openclaw Skills using the device setup agent:
clawhub install uday390/deepread-agent-setup
DeepRead Resume Parser Data Schema & Taxonomy
Extracted JSON Payload Fields
| Field Key | Data Type | Description | Flagged Properties |
|---|---|---|---|
full_name |
String | Candidate's complete name | needs_review (Boolean) |
email |
String | Null | Contact email address | needs_review (Boolean) |
phone |
String | Null | Contact telephone number | needs_review (Boolean) |
location |
String | Null | City and region of residence | needs_review (Boolean) |
headline |
String | Null | Professional headline or current role | needs_review (Boolean) |
years_experience |
Number | Null | Automatically computed total professional experience | needs_review (Boolean), review_reason |
work_history |
Array | Chronological employment history (Employer, Title, Dates, Location) | needs_review (Boolean) |
education |
Array | History of academic degrees, institutions, and graduation years | needs_review (Boolean) |
skills |
Array [String] | Extracted key skills and technologies | needs_review (Boolean) |
Output Format Example
{
"schema_version": "dp02",
"status": "completed",
"extraction": {
"fields": [
{
"key": "full_name",
"value": "Priya Nair",
"needs_review": false,
"location": { "page": 1 }
},
{
"key": "years_experience",
"value": 7,
"needs_review": true,
"review_reason": "Computed from overlapping roles",
"location": { "page": 1 }
}
]
}
}
DeepRead Resume Parser Advanced Features
- PII Redaction Engine: Automatically strip names, photos, physical locations, and other sensitive metrics prior to reviewer assessment to enforce blind screening policies.
- Bring Your Own Key (BYOK): Connect your custom LLM provider credentials (OpenAI, Google Gemini, OpenRouter) to bypass standard page quotas and benefit from zero processing overhead.
- Confidence Flag Optimization: Access field-level flags and computed reasoning to route only low-confidence variables to humans for verification.
- Dashboard Optimizer: Build tailored layout blueprints in the web interface to yield a 20% to 30% performance boost on high-volume, repetitive templates.
- Agentic Interoperability: Seamlessly chain with complementary Openclaw Skills like
deepread-ocranddeepread-form-fillto orchestrate end-to-end recruitment pipelines.
SKILL.md
Loading
Related Openclaw Skills
Overcoming Male Depression (I Don't Want to Talk About It)
An AI coding agent skill designed to help users explore, understand, and apply Terrence Real's clinical framework for identifying and overcoming covert male depression.
Go FS MCP Skill
A Go-based Model Context Protocol (MCP) skill that allows AI agents to securely perform local file system operations such as directory listing, reading, and writing.
Chukonu Patent Search
An MCP-powered patent search skill for retrieving and analyzing Chinese (CNIPA) and European (EPO) patents directly within your AI workflow.
I Have a Dream - Rhetoric & Civil Rights
An interactive AI agent skill designed to analyze, teach, and guide users through the rhetorical brilliance, moral philosophy, and historical context of Dr. Martin Luther King Jr.'s historic speech.
Omni-Competitor Intelligence
An advanced, multi-platform competitive intelligence agent designed to automate e-commerce scraping, sentiment analysis, pricing tracking, and strategic report generation.
Feishu Enterprise Intelligence Hub (飞书企业智能中枢)
An enterprise-grade orchestration and automation hub designed to convert the entire Feishu (Lark) suite into an intelligent, automated operational command center.
Featured*
