# Process PDF files with confidence

PDF work often requires several tools for text, tables, forms, and page management. This skill provides focused Python examples for common PDF processing tasks.

## Install

```bash
npx skillstore add joseph obrien/89jobrien-pdf-processing
```

## Metadata

- Status: approved
- Slug: 89jobrien-pdf-processing
- Version: 1.0.1
- Author version: 1.0.1
- Skillstore revision: r2
- Version status: valid
- Tree hash: db97aceff2487d7cca540aea60c8221e1e7f7419df2ff98ec15c4967aa315ac4
- Author: Joseph OBrien
- GitHub username: 89jobrien
- License: MIT
- Repository: https://github.com/89jobrien/steve/tree/main/steve/skills/pdf-processing
- Ref: 80999bf530a7874d7bedf8ce202001ecb4c4f5e0
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: filesystem, external\_commands
- Quality score: 79
- Quality tier: bronze
- Public page: https://skillstore.pages.dev/skills/89jobrien-pdf-processing
- Manifest: https://skillstore.pages.dev/api/skills/89jobrien-pdf-processing/manifest

## Capabilities

- Extract text from a selected PDF page with pdfplumber.
- Extract tables from PDF pages and iterate through their rows.
- Read all pages and combine their extracted text.
- Fill PDF form fields and write a completed form.
- Merge multiple PDFs or split selected pages into a new PDF.
- Export extracted text to TXT and tables to CSV files.

## Use Cases

- Extract a report summary: Extract text from a report and save the relevant pages for review.
- Prepare completed forms: Fill known form fields, validate required values, and create a flattened PDF for distribution.
- Prepare data from PDF tables: Extract report tables and export them to CSV for spreadsheet analysis.

## Prompt Templates

### Extract first-page text

```
Extract the text from the first page of document.pdf using the recommended library. Explain how to run the example.
```

### Export a PDF table

```
Extract tables from tables.pdf and save them to output.csv. Include checks for pages with no tables.
```

### Merge monthly reports

```
Merge January.pdf, February.pdf, and March.pdf into merged.pdf. Preserve the source files.
```

### Fill and validate a form

```
Inspect form.pdf fields, validate my required values, fill the form, and save a separate flattened copy. Report validation errors before writing output.
```

## Limitations

- Scanned PDFs may need OCR tools that are only listed, not configured.
- Table extraction quality depends on the PDF layout and source quality.
- Form examples require PDFs with compatible fillable fields.
- The skill does not install Python packages or validate library versions.

## Best Practices

- Keep original PDFs unchanged and write results to separate files.
- Validate required form values before filling or flattening a document.
- Test extraction and table detection on a small representative PDF first.

## Anti Patterns

- Do not assume scanned PDFs contain extractable text without OCR.
- Do not overwrite source PDFs when creating merged, split, or filled outputs.
- Do not rely on table extraction without reviewing the exported rows.

## Security Audit

- Audited at: 2026-07-18T09:26:58.607\+00:00
- Summary: All 21 static findings are false positives. The external-command detections match Markdown code fences rather than shell execution, and the filesystem detections are fixed local output files used for the documented PDF operations. No prompt injection, data exfiltration, or malicious intent was found in SKILL.md or FORMS.md.

## Stats

- Views: 202
- Downloads: 19
- Favorites: 0
- Popularity score: 0