Skill Parser API

The Skill Parser API supports PDF and DOCX file formats for document-based skill extraction, covering the vast majority of resume and job description formats used in professional settings. You can upload these files directly via multipart form data to the /v1/skills/upload endpoint. Additionally, the API accepts plain text input through the /v1/skills/text endpoint, enabling you to extract skills from any text source including job postings, LinkedIn profiles, or project descriptions that you have already converted to string format. This flexibility means you can integrate the API into diverse workflows regardless of how your source documents are stored or transmitted.

Skills Gap Analysis compares the skills found in a source document (typically a resume) against the requirements in a target document (typically a job description) to produce a comprehensive compatibility assessment. The API returns a match percentage score, a list of matched skills with confidence levels, missing skills ranked by importance to the role, additional skills the candidate possesses beyond the requirements, and actionable recommendations for closing identified gaps. This feature is invaluable for recruiters who need to quickly assess candidate-role fit across high volumes of applicants, and equally useful for job seekers who want to understand exactly which skills they need to develop for their target positions.

Our AI-driven categorization system organizes extracted skills into four primary categories: technical skills (programming languages, frameworks, tools), soft skills (communication, leadership, problem-solving), domain-specific skills (industry knowledge, regulatory expertise, specialized methodologies), and certifications (professional credentials, licenses, formal qualifications). The classification model draws on a knowledge base of over 10,000 skills mapped across industries and roles, and it continually improves through machine learning as it processes new documents. Each skill is assigned a confidence score indicating the model's certainty in both the extraction and categorization, allowing you to set thresholds appropriate for your use case.

Yes, the API currently supports five languages: English, Spanish, French, German, and Portuguese, with automatic language detection that requires no configuration on your part. The system identifies the document language during processing and applies language-specific NLP models optimized for skill terminology and professional vocabulary in each supported language. This is particularly valuable for multinational organizations processing resumes and job descriptions across different markets and offices. Cross-language skill matching is also supported, meaning a Spanish-language resume can be compared against an English-language job description with skills mapped and normalized across both languages.

API Codex uses one credit-based subscription that covers all 40 APIs. The Free plan includes 1,000 credits per month, ideal for testing and small-scale projects. Starter ($29.99/month) includes 50,000 credits and Pro ($99.99/month) includes 250,000. Each parsing request costs 25 credits, which translates to roughly 40 requests per month on Free, 2,000 on Starter and 10,000 on Pro, and each request processes one document. Only successful (2xx) responses consume credits. Enterprise volumes are available on request.

The Skill Parser API uses contextual analysis and natural language processing to infer skill proficiency levels from surrounding text. It analyzes factors such as years of experience mentioned, project complexity described, leadership or teaching roles involving the skill, and certification or formal training references. The API assigns confidence scores to each extracted skill and experience level, helping you understand the reliability of the assessment. For example, if a resume states 'Led a team of 5 developers building React applications for 3 years,' the API would extract React as a skill with high proficiency and 3 years of experience with high confidence.