compare-docs

Name: compare-docs
Author: lennonli

github.com/lennonliDocuments1168 installsUpdated 40w ago

About compare-docs

A document comparison skill that identifies substantive differences, errors, and inconsistencies across two files. It is intended for reviewing contracts, financial reports, and revised documents, with optional focus areas and a generated report.

Key features

01Compare DOCX, PDF, Markdown, and text files
02Extract DOCX content with pandoc
03Check numbers, dates, clauses, and definitions
04Create a structured Markdown comparison report
05Convert the report to DOCX

Use cases

01Reviewing revised legal contracts
02Checking financial reports for changed figures
03Comparing document versions with a chosen focus

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/lennonli/compare-docs --skill compare-docs

After installing, type/compare-docsin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

.gitignore

README.md

scripts/

compare_docs.py

scripts/comparators/

spell_check.py

llm_client.py

logic_check.py

consistency_check.py

fuzzy_logic.py

scripts/parsers/

office_parser.py

section_chunker.py

table_parser.py

scripts/reporters/

md_reporter.py

scripts/utils/

nlp_utils.py

Details

From the project README

Document Comparison Skill

This skill compares two documents to find substantive differences, errors, or inconsistencies. It is particularly useful for legal contracts, financial reports, or revised document versions.

Usage

# Compare two specific files
/compare-docs file1.docx file2.docx

# Compare with specific focus
/compare-docs file1.docx file2.docx --focus "financial data"

Workflow

Input Verification:
- Verify both input files exist.
- Determine file type (.docx, .pdf, .md, .txt).
Content Extraction:
- If files are .docx, use pandoc to convert them to Markdown for clear text analysis.
```
pandoc -t markdown "file1.docx" -o "file1.md"
pandoc -t markdown "file2.docx" -o "file2.md"
```
- If files are .pdf, use available PDF reading tools.
Analysis & Comparison:
- Read the extracted content.
- Compare the documents section by section or key-value by key-value.
- Focus Areas:
  - Numbers & Dates: Check for discrepancies in financial figures, dates, percentages, and quantities.
  - Key Clauses: Identify added, removed, or modified clauses (especially in legal/contractual contexts).
  - Definitions: Check for changes in defined terms.
- Note: Ignore minor formatting changes unless explicitly requested.
Report Generation:
- Create a Markdown report (comparison_report.md) structured as follows:
  - Summary: Brief overview of the comparison result.
  - Critical Differences (High Risk): Data mismatches, missing clauses, conflicting obligations.
  - Substantive Changes: Changes in meaning or scope.
  - Stylistic/Format Changes: (Optional) Brief mention of layout or phrasing changes that don't alter meaning.
  - Recommendations: Actionable advice based on findings.
Output formatting & Delivery:
- Convert the Markdown report to a professional .docx document using pandoc.
```
pandoc "comparison_report.md" -o "Comparison_Report.docx"
```
- Open the file: Automatically open the generated document so the user can view it immediately.
  - On macOS: open "Comparison_Report.docx"
  - On Windows: start "Comparison_Report.docx"
  - On Linux: xdg-open "Comparison_Report.docx"
- Inform the user of the report location.
Cleanup:
- Remove temporary intermediate files (e.g., converted .md files) to keep the workspace clean.

Example Output Structure

Comparison Report

1. Executive Summary

...

2. Key Discrepancies

Item	File A Value	File B Value	Impact
Revenue	$10M	$12M	Significant
...	...	...	...

3. Detailed Clause Analysis

...

Comments

Markdown supported

Details

Author: lennonli
Repository: lennonli/compare-docs
Category: Documents
Installs: 168
GitHub stars: 1

Report

More skills

All skills

handoff

github.com/mattpocock

1.1M

Compact the current conversation into a handoff document for another agent to pick up

lark-doc

open.feishu.cn

831.4k

Operate on Feishu cloud documents (Docx / Wiki): read, create, and edit documents; insert or download image attachments; and work with mind notes. Use when the user provides a document URL/token (including /docx/ or /wiki/ on doubao.com); route by URL path/token rather than domain. `/page/<token>` is a Miaoda app, not a Feishu cloud document. Route embedded document resources according to the unified rules in the reading reference. Use lark-drive for standalone comment operations; use docs +fetch to read comments alongside the main text. Operations on spreadsheet or Base internal data are outside this skill.

lark-drive

open.feishu.cn

830.7k

Feishu cloud storage (Drive): manage Drive files and folders, including uploads/downloads, folder creation, copying/moving/deleting, viewing metadata, checking permission settings, comments/permissions/subscriptions, titles, versions, Feishu document security labels (secure labels), and local file imports. Use when users need to organize Drive folders, handle cloud storage resource URLs/tokens, identify link types/actual tokens/titles, or import Word/Markdown/Excel/CSV/PPTX/.base as docx/sheet/bitable/slides. Route doubao.com cloud storage URLs/tokens by resource path and token too; do not fall back to WebFetch. Not responsible for: editing document content (use lark-doc), spreadsheet/Base table data operations (use lark-sheets/lark-base), knowledge space node/member management (use lark-wiki), or native Markdown file read/write/patch/diff (use lark-markdown).

lark-sheets

open.feishu.cn

829.3k

Feishu Spreadsheets: create and operate spreadsheets. Supports worksheets and row/column structures (add/delete/merge/size/hide/freeze/group), cell read/write (values/formulas/styles/comments/cell images), range copy/move/sort/fill, find and replace, bulk updates, and creating and maintaining objects such as charts, pivot tables, conditional formatting, filters and filter views, dropdown lists, sparklines, and floating images. Also supports formula validation, restoring historical versions, and importing/exporting local Excel/CSV files and Feishu spreadsheets. Use when users need to create or edit spreadsheets, summarize and visualize data, format spreadsheets, calculate formulas (including migrating Excel formulas), or build financial models (DCF, three statements, budgets, Sensitivity, etc.). For multidimensional tables (Base/bitable), use lark-base. If users want to search for spreadsheet files in cloud storage (Drive/cloud storage) by name or keyword, use lark-drive's drive +search to locate resources first. When users provide a doubao.com /sheets/ URL/token, use this skill directly; do not fall back to WebFetch because the domain is not Feishu. Routing is based on the URL path pattern and token, not the domain.