Guides users through filing US federal and state taxes on FreeTaxUSA.com using document extraction, tax research, and browser-based form automation. Use when the user asks to file taxes, prepare a tax return, or automate FreeTaxUSA form filling.
See references/PHASE-1-SETUP.md
See references/PHASE-2-DISCOVERY.md
See references/PHASE-3-RESEARCH.md
Phases 2-3 are iterative. The life change questionnaire or filing plan review may reveal missing documents or new questions. Loop back to Phase 2 as needed — request additional docs, re-extract, update the summary, and revise the filing plan. Do NOT proceed to Phase 4 until all documents are accounted for and the filing plan is approved.
See references/PHASE-4-FILING.md
See references/PHASE-5-REVIEW.md
Extract text and render page images from tax document PDFs:
node "${SKILL_DIR}/scripts/extract-pdf.js" <pdf-path> [output-dir]
.txt and .png files in the output directoryoutput-dir is omitted, outputs are placed alongside the PDFTranscribe verified document values directly (W-2 box amounts, 1099 figures, employer info). Ask about ambiguous items, filing choices, and discrepancies between documents.
Tax data stays local. No data is sent to external services except FreeTaxUSA via the browser. Extracted files, research notes, and the summary report live in the user-chosen folder. Screenshots go to your browser automation tool's default location (e.g., /tmp/brw-screenshots/ for brw).
Each page auto-saves on FreeTaxUSA. If something goes wrong, re-login and resume from where you left off. Progress is never lost.
Go slow and verify. Speed is less important than accuracy for tax filing. Double-check every entry against source documents.
references/BROWSER-TIPS.md for FreeTaxUSA-specific browser automation patternsreferences/GOTCHAS.md for known quirks and common pitfalls