Open-source tax engine. Onboards users, installs the CLI, and routes to the right skill -- preparing a return or reviewing one.
Quellsprache: Englisch
Menü
SkillsMP hat 10 Skills aus filedcom/opentax gesammelt. Öffne einen Skill, um Quelle und Details zu prüfen.
Es werden 10 von 10 gesammelten Skills angezeigt.
Open-source tax engine. Onboards users, installs the CLI, and routes to the right skill -- preparing a return or reviewing one.
Quellsprache: Englisch
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.
Quellsprache: Englisch
Tax return reviewer that audits a completed return against source documents using the opentax CLI. Finds discrepancies, missing income, incorrect deductions, and missed credits.
Quellsprache: Englisch
Downloads and installs the opentax CLI binary. Detects OS and architecture automatically.
Quellsprache: Englisch
Helps users permanently set up the OpenTax skill on their AI platform so they don't have to load it every time.
Quellsprache: Englisch
Generic audit/fix loop. Pass a goal string. Planner subdivides work, auditor/fixer teams run in parallel, loop until 2 consecutive clean cycles.
Quellsprache: Englisch
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.
Quellsprache: Englisch
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.
Quellsprache: Englisch
Human-readable status report for all tax forms. Shows benchmark accuracy, active root causes, and build/fix state for each form:year.
Quellsprache: Englisch
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.
Quellsprache: Englisch