Skip to main content
Manusで任意のスキルを実行
ワンクリックで
GitHub リポジトリ

opentax

opentax には filedcom から収集した 10 個の skills があり、リポジトリ単位の職業カバレッジとサイト内 skill 詳細ページを表示します。

収集済み skills
10
Stars
24
更新
2026-05-01
Forks
6
職業カバレッジ
4 件の職業カテゴリ · 100% 分類済み
リポジトリエクスプローラー

このリポジトリの skills

opentax
ソフトウェア開発者

Open-source tax engine. Onboards users, installs the CLI, and routes to the right skill -- preparing a return or reviewing one.

2026-05-01
tax-preparer
確定申告代行者

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.

2026-05-01
tax-reviewer
税務審査員・徴収員・歳入担当者

Tax return reviewer that audits a completed return against source documents using the opentax CLI. Finds discrepancies, missing income, incorrect deductions, and missed credits.

2026-05-01
install-cli
ソフトウェア開発者

Downloads and installs the opentax CLI binary. Detects OS and architecture automatically.

2026-04-13
save-skill
ソフトウェア開発者

Helps users permanently set up the OpenTax skill on their AI platform so they don't have to load it every time.

2026-04-12
audit-harness
ソフトウェア品質保証アナリスト・テスター

Generic audit/fix loop. Pass a goal string. Planner subdivides work, auditor/fixer teams run in parallel, loop until 2 consecutive clean cycles.

2026-04-12
tax-fix
ソフトウェア開発者

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.

2026-04-11
tax-cases
確定申告代行者

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.

2026-04-09
tax-status
確定申告代行者

Human-readable status report for all tax forms. Shows benchmark accuracy, active root causes, and build/fix state for each form:year.

2026-04-09
tax-build
ソフトウェア開発者

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.

2026-04-09