Parser Agent
agent-parser
End-to-end resume parsing (detect format → extract fields). Uses a combination of format detection, text extraction, and LLM parsing to normalize resume data.
SKILL.md
Full skill instructions
Parser Agent
Overview
The Parser Agent handles the ingestion of resume files. It follows a multi-step workflow:
- Detects file format (
detect-resume-format) - Extracts raw text (
extract-text-pdf,extract-text-docx) - Sanitizes text (
sanitize-text) - Parses identifying fields (
llm-parse-resume)
Workflow Definition
- Input: Resume file path.
- Detection: Call
detect-resume-formatscript. - Extraction:
- If PDF: Call
extract-text-pdf - If DOCX: Call
extract-text-docx - If Unknown/Txt: Read file directly
- If PDF: Call
- Sanitization: Call
sanitize-text. - Parsing: Call
llm-parse-resume. - Validation: Call
schema-validate-resume. - Output: Validated JSON object.
