Pdf

What it does

This skill helps an agent select a PDF processing approach according to the requested output. Its examples distinguish page manipulation from text and table extraction, and document creation from editing an existing form. That distinction matters because readable extracted text does not preserve a page's visual layout, and a scanned page may contain no usable text layer at all.

Best for

Combining reports, extracting a table for further analysis, preparing a searchable scan, or producing a document with a fixed page layout. Provide the original files and specify which page structure, form fields or image details must survive the transformation.

Tradeoffs and requirements

The referenced Python and command-line tools must be available in the execution environment. OCR can misread names and numbers, and extracted tables can lose column boundaries. The skill declares proprietary terms in its bundled license; inspect that source before reusing its materials.

Unknown; inspect source requirements and supporting scripts.

Install from the source

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.

npx skills add https://github.com/anthropics/skills/tree/ca45fc496a3436251f191354091d557da31c15b5/skills/pdf --skill pdf

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

• Shell Or Package Install — review the source context.

Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.

AI Craft Pad Skill Score

86/100 · Metadata coverage 100% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation

100/100

100

Maintenance

100/100

100

License Clarity

100/100

100

Repository Health

85/100

85

Compatibility Evidence

80/100

80

Popularity

95/100

95

Originality

80/100

80

Static Safety

60/100

60

Supporting-file static inspection

Bounded source inspection, not a runtime security audit. This inspection does not execute code.

9 text files inspected at this exact repository snapshot. 2 files outside the inspection budget or type allowlist. Dependencies were not installed or independently audited.

• Network Client: 1 file — inspect context before use.
• File Write Or Delete: 4 files — inspect context before use.

Absence of a pattern is not proof of safety. Permission needs and runtime behavior remain Unknown.

Suggested workflow

Work on a copy, identify whether pages contain text or images, perform the narrow transformation, then inspect the output alongside the original. Use a spreadsheet skill when the final deliverable is an editable workbook.

How to judge the result

Check page count, reading order, fonts, table alignment and representative extracted values. For forms, reopen the saved file and confirm that the intended fields remain usable.