cv-data-ingestion

Data transformation converts messy career notes, Obsidian vaults, CSV exports, and resumes into validated YAML and Markdown files organized under a content/ directory. The Skill extracts, normalizes, and structures raw inputs into standardized portfolio sections like experience, case studies, skills, and certifications with strict schema compliance.

Data ingestion supports Obsidian markdown, CSV exports, zip archives, markdown documents, resume text, and PDF files. The Skill processes these diverse formats, extracts relevant career information, and outputs clean, validated YAML and Markdown files in your portfolio content repository.

Schema validation enforces strict compliance using Zod definitions against all outputs. The Skill applies phase-driven processing—schema understanding, data discovery, and enrichment—to produce deterministic, standardized YAML and Markdown entries with explicit required fields for each portfolio section.

Yes, multi-format processing handles Obsidian markdown vaults, LinkedIn exports, and other career data sources. The Skill extracts and normalizes information from these formats into structured experience entries, case studies, and other portfolio components in your content/ directory.

Automated data transformation eliminates manual reorganization of scattered notes and exports. This Skill processes entire directories of raw career data at once, validates outputs against schema definitions, and produces consistent, standardized portfolio structures faster than hand-organizing files.

No, the Skill handles the complete setup. It processes raw career data from source directories, creates the content/ structure automatically, and generates validated YAML and Markdown files with all required portfolio sections without requiring pre-existing organization.