# reporting

> PDF generation, extraction, and document conversion tools

- Author: KIrill Enkogu
- Repository: enkogu/pipeline-fullstack-app
- Version: 20260125155958
- Stars: 0
- Forks: 0
- Last Updated: 2026-02-06
- Source: https://github.com/enkogu/pipeline-fullstack-app
- Web: https://mule.run/skillshub/@@enkogu/pipeline-fullstack-app~reporting:20260125155958

---

---
name: reporting
description: PDF generation, extraction, and document conversion tools
python_requires:
  - pypdf
  - xhtml2pdf
  - pandas
  - markdown-it-py
  - requests
api_keys:
  - OPENROUTER_API_KEY
capabilities:
  - pdf_extract
  - pdf_merge
  - pdf_split
  - convert_to_pdf
  - image_extract
  - excel_to_markdown
---

# Reporting Skill

## Requirements
- OPENROUTER_API_KEY for PDF/image extraction (Gemini LLM)
- Python packages: xhtml2pdf, pypdf, markdown-it-py, pandas, pillow

## PDF Operations

### Extract Text from PDF
Param names: `input_path`, `mode`
```
# Single argument (default mode: text):
run_skill("reporting/pdf-extract.py", "<input_path>")

# With mode specified - use JSON array:
run_skill("reporting/pdf-extract.py", '["<input_path>", "mode:metadata"]')
run_skill("reporting/pdf-extract.py", '["<input_path>", "mode:both"]')
```
Uses Gemini LLM to extract content in detailed Markdown format.

**Example:**
```
run_skill("reporting/pdf-extract.py", "/path/to/invoice.pdf")
run_skill("reporting/pdf-extract.py", '["/path/to/invoice.pdf", "mode:text"]')
```

### Merge PDFs
Param names: `output_path`, `paths...`
```
# Use JSON array for multiple paths:
run_skill("reporting/pdf-merge.py", '["<output_path>", "<path1>", "<path2>", ...]')
```
Concatenate multiple PDFs into one document.

**Example:**
```
run_skill("reporting/pdf-merge.py", '["/output/merged.pdf", "/file1.pdf", "/file2.pdf", "/file3.pdf"]')
```

### Split PDF
Param names: `input_path`, `output_path`, `ranges`
```
# Use JSON array for 3 arguments:
run_skill("reporting/pdf-split.py", '["<input_path>", "<output_path>", "<ranges>"]')
```
Extract pages using range expression (e.g., "1-3,5,7-")

**Example:**
```
run_skill("reporting/pdf-split.py", '["/input.pdf", "/output/", "1-3,5,7-10"]')
```

### Convert to PDF
Param names: `output_path`, `input_path`, `kind`, `theme`
```
# Single file conversion (auto-detect format):
run_skill("reporting/convert-to-pdf.py", '["<output_path>", "<input_path>"]')

# With explicit format and theme:
run_skill("reporting/convert-to-pdf.py", '["<output_path>", "<input_path>", "kind:md", "theme:compact"]')
```
Kinds: auto, md, csv, txt, html. Themes: simple, compact.

**Example:**
```
run_skill("reporting/convert-to-pdf.py", '["/output/report.pdf", "/input/report.md"]')
run_skill("reporting/convert-to-pdf.py", '["/output/data.pdf", "/input/data.csv", "kind:csv", "theme:simple"]')
```

## Image/Excel Operations

### Extract Text from Image
```
run_skill("reporting/image-extract.py", "<input_path>")
```
Uses Gemini LLM to extract text and content from images.

**Example:**
```
run_skill("reporting/image-extract.py", "/path/to/screenshot.png")
```

### Excel to Markdown
Param names: `input_path`, `output_path`
```
# Single argument (output to stdout):
run_skill("reporting/excel-to-markdown.py", "<input_path>")

# With output path - use JSON array:
run_skill("reporting/excel-to-markdown.py", '["<input_path>", "<output_path>"]')
```
Convert Excel file to Markdown with tables for each sheet.

**Example:**
```
run_skill("reporting/excel-to-markdown.py", "/path/to/data.xlsx")
run_skill("reporting/excel-to-markdown.py", '["/path/to/data.xlsx", "/output/data.md"]')
```

### Process Attachment to Markdown
Param names: `file_path`, `mime_type`
```
# Use JSON array for 2 arguments:
run_skill("reporting/process-attachment.py", '["<file_path>", "<mime_type>"]')
```
Converts PDF, Excel, or text files to Markdown based on MIME type.
Supported: application/pdf, application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, text/*

**Example:**
```
run_skill("reporting/process-attachment.py", '["/path/to/invoice.pdf", "application/pdf"]')
run_skill("reporting/process-attachment.py", '["/path/to/data.xlsx", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"]')
```

## Notes
- All scripts output JSON to stdout
- PDF extraction uses Gemini 2.5 Flash via OpenRouter
- Paths can be absolute or relative to workflow artifacts