Open-source tax engine. Onboards users, installs the CLI, and routes to the right skill -- preparing a return or reviewing one.
Langue du texte source : anglais
Menu
SkillsMP a collecté 10 skills depuis filedcom/opentax. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 10 skills collectés sur 10.
Open-source tax engine. Onboards users, installs the CLI, and routes to the right skill -- preparing a return or reviewing one.
Langue du texte source : anglais
Tax preparer agent that uses the opentax CLI to prepare, validate, and export federal tax returns. Handles W-2s, 1099s, all major schedules, credits, and more.
Langue du texte source : anglais
Tax return reviewer that audits a completed return against source documents using the opentax CLI. Finds discrepancies, missing income, incorrect deductions, and missed credits.
Langue du texte source : anglais
Downloads and installs the opentax CLI binary. Detects OS and architecture automatically.
Langue du texte source : anglais
Helps users permanently set up the OpenTax skill on their AI platform so they don't have to load it every time.
Langue du texte source : anglais
Generic audit/fix loop. Pass a goal string. Planner subdivides work, auditor/fixer teams run in parallel, loop until 2 consecutive clean cycles.
Langue du texte source : anglais
Autonomous bug-fix loop for any form:year. Reads failing benchmark cases, spawns parallel bug-fixer agents per root cause cluster, validates, commits net-positive fixes, and loops until all pass or stalled.
Langue du texte source : anglais
Generate realistic benchmark cases from IRS-published sources (VITA exercises, Pub 17 examples, MeF test cases). Correct values come directly from IRS publications — no reference calculator involved.
Langue du texte source : anglais
Human-readable status report for all tax forms. Shows benchmark accuracy, active root causes, and build/fix state for each form:year.
Langue du texte source : anglais
Autonomous form builder. Given a form number (e.g. 1120), researches IRS instructions, extracts ground truth from IRS sample returns, builds all nodes section by section, then runs a validate+fix loop until ≥95% of benchmark cases pass.
Langue du texte source : anglais