Skip to main content
在 Manus 中运行任何 Skill
一键导入
GitHub 仓库

opentax

opentax 收录了来自 filedcom 的 10 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。

已收集 skills
10
Stars
24
更新
2026-05-01
Forks
6
职业覆盖
4 个职业分类 · 已分类 100%
仓库浏览

这个仓库中的 skills

opentax
软件开发工程师

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
税务申报员

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
税务审查员、征收员与税收代理人

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
软件开发工程师

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

2026-04-13
save-skill
软件开发工程师

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
软件质量保证分析师与测试员

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
软件开发工程师

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
税务申报员

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
税务申报员

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
软件开发工程师

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