// Process, transform, analyze, and report on CSV and JSON data files. Use when the user needs to filter rows, join datasets, compute aggregates, convert formats, deduplicate, or generate summary reports from tabular data. Works with any CSV, TSV, or JSON Lines file.
| name | csv-pipeline |
| description | Process, transform, analyze, and report on CSV and JSON data files. Use when the user needs to filter rows, join datasets, compute aggregates, convert formats, deduplicate, or generate summary reports from tabular data. Works with any CSV, TSV, or JSON Lines file. |
| compatibility | Requires Python 3. No external dependencies beyond Python standard library (csv, json modules). |
Process tabular data (CSV, TSV, JSON, JSON Lines) using standard command-line tools and Python. No external dependencies required beyond Python 3.
| Script | Purpose | Dependencies |
|---|---|---|
csv_tool.py | All-in-one CSV/JSON processing tool | Python 3 (stdlib only) |
python --version
CRITICAL — Error Recovery: If any script below fails with an error, check that Python 3 is available and re-run the exact same command.
python scripts/csv_tool.py inspect "DATA_FILE"
Shows row count, column names, and non-empty value counts per column.
python scripts/csv_tool.py filter "DATA_FILE" --column COLUMN_NAME --op OPERATOR --value VALUE --output "OUTPUT_FILE"
Operators: eq, neq, gt, gte, lt, lte, contains, startswith, endswith
python scripts/csv_tool.py sort "DATA_FILE" --column COLUMN_NAME --order asc --output "OUTPUT_FILE"
Options: --numeric for numeric sorting, --order desc for descending.
python scripts/csv_tool.py dedup "DATA_FILE" --columns "col1,col2" --output "OUTPUT_FILE"
Remove duplicates by specified columns (or all columns if omitted).
python scripts/csv_tool.py aggregate "DATA_FILE" --group-by COLUMN --agg-column VALUE_COL --func sum --output "OUTPUT_FILE"
Functions: sum, avg, count, min, max
python scripts/csv_tool.py join "LEFT_FILE" "RIGHT_FILE" --on KEY_COLUMN --how inner --output "OUTPUT_FILE"
Join types: inner, left
python scripts/csv_tool.py convert "DATA_FILE" --to json --output "OUTPUT_FILE"
Supported conversions: csv, json, jsonl (JSON Lines), tsv
python scripts/csv_tool.py report "DATA_FILE" --group-by CATEGORY_COL --value-column VALUE_COL --output "report.md"
Generates a Markdown summary table with count, sum, avg, min, max per group.
python scripts/csv_tool.py clean "DATA_FILE" --output "CLEAN_FILE"
Strips whitespace, normalizes empty values (N/A, null, None → empty), normalizes booleans.
inspect to understand the dataaggregate for raw data, report for Markdown outputjoin two datasets on a shared keyconvert between CSV/JSON/TSVComprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When GLM needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Generate professional email drafts using Python templates. Use when the user needs to compose business emails, follow-ups, introductions, meeting requests, or other professional correspondence. Supports multiple tones, languages, and email types with structured output.
Read, write, analyze, and format Excel spreadsheets (.xlsx). Use when the user needs to create Excel files, extract data from spreadsheets, apply formulas, format cells, or generate Excel reports from data. Supports multiple sheets, charts, and conditional formatting.
Extract text from images using Python OCR. Use when the user wants to read text from screenshots, photos of documents, scanned pages, or any image containing text. Supports PNG, JPEG, TIFF, BMP, and WebP formats.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When GLM needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Scrape web pages, search the internet, and extract structured content using Python. Use when the user wants to fetch a webpage, search for information online, extract links, or crawl JavaScript-rendered dynamic pages.