tax-return-cleanup
Parses noisy PDF-to-text tax forms into structured, agent-readable summaries.
Install
mkdir -p .claude/skills/tax-return-cleanup && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15790" && unzip -o skill.zip -d .claude/skills/tax-return-cleanup && rm skill.zipInstalls to .claude/skills/tax-return-cleanup
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Clean and restructure a PDF-converted IRS Form 1065 KB file into an agent-readable markdown document. Removes IRS form noise (footer codes, tracking lines, tilde tab stops, address headings, anchor IDs), extracts Schedule K totals and partner capital accounts into summary tables, and groups content by logical section (CPA letter, Schedule K, K-1s, state returns). Writes a new _clean.md file alongside the original.Key capabilities
- →Remove IRS form noise from PDF-converted files.
- →Extract Schedule K totals into a summary table.
- →Extract partner capital accounts into a summary table.
- →Group content by logical sections (CPA letter, Schedule K, K-1s, state returns).
- →Write a new cleaned markdown file.
How it works
The skill locates and runs a Python script that transforms the input file by removing noise and adding structure, then verifies the output.
Inputs & outputs
When to use tax-return-cleanup
- →Cleaning tax form data
- →Extracting schedule totals
- →Preparing tax files for AI analysis
About tax-return-cleanup
Uses scripts to remove document noise like tracking lines and footers, grouping data into organized sections and tables for analysis.
Clean and restructure a PDF-converted IRS Form 1065 KB file into an agent-readable markdown document. Removes IRS form noise (footer codes, tracking lines, tilde tab stops, address headings, anchor IDs), extracts Schedule K totals and partner capital accounts into summary tables, and groups content
When not to use it
- →If the cleanup script (`tax_return_cleanup.py`) is not present.
Prerequisites
Limitations
- →The script must be present at `$PROJECT_ROOT/.agent/scripts/tax_return_cleanup.py`.
- →The skill processes IRS Form 1065 KB files.
How it compares
This skill automates the cleaning and structuring of specific tax forms, providing a machine-readable format, unlike manual data extraction or general document parsing.
Compared to similar skills
tax-return-cleanup side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| tax-return-cleanup (this skill) | 0 | 6mo | Review | Intermediate |
| miniqmt-skill | 0 | 7mo | Review | Intermediate |
| quant-analyst | 103 | 4mo | No flags | Advanced |
| stock-analyzer | 71 | 3mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by cdrguru
View all by cdrguru →You might also like
miniqmt-skill
xiaxiaoqian
MiniQMT量化交易开发技能,基于迅投XtQuant库提供行情数据获取(xtdata)和交易执行(xttrader)功能。用于开发股票、期货、期权等量化交易策略,支持历史/实时行情数据下载、K线/分笔数据获取、财务数据查询、自动下单/撤单、持仓查询、资产查询等。适用于需要连接MiniQMT客户端进行量化交易的场景。
quant-analyst
zenobi-us
Expert quantitative analyst specializing in financial modeling, algorithmic trading, and risk analytics. Masters statistical methods, derivatives pricing, and high-frequency trading with focus on mathematical rigor, performance optimization, and profitable strategy development.
stock-analyzer
FrancyJGLisboa
Provides comprehensive technical analysis for stocks and ETFs using RSI, MACD, Bollinger Bands, and other indicators. Activates when user requests stock analysis, technical indicators, trading signals, or market data for specific ticker symbols.
data-engineering
pluginagentmarketplace
ETL pipelines, Apache Spark, data warehousing, and big data processing. Use for building data pipelines, processing large datasets, or data infrastructure.
crawl4ai
basher83
This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.
data-cleaning-pipeline
aj-geddes
Build robust processes for data cleaning, missing value imputation, outlier handling, and data transformation for data preprocessing, data quality, and data pipeline automation