parse-cv

Pre-process a CV/profile file (PDF, DOCX, ODT, RTF) into plain text BEFORE feeding it to the LLM context. Reduces token cost by 5-10x on long CVs and yields more reliable extraction than reading binary PDFs directly via multimodal vision. The Assistente calls this skill on every uploaded document in `$JHT_HOME/profile/sources/` before populating `candidate_…

Independent GitHub snapshot · Automated classification · Original documentation governs