BrowseFull catalogOutcomesSolve a specific problemRolesStack by teamTrustFilter by risk tier
← Back to the Claude Observatory

PDF Skill (Anthropic)

Skill Documents & Content Solid
Works inClaude Code
Solid Reviewed

Reduces manual PDF processing overhead by automating extraction, form filling, and document manipulation at scale—critical for compliance, underwriting, and …

Reads, extracts, fills, combines, splits, rotates, and analyzes PDF files. Handles text extraction, form filling, and document manipulation. Official Anthropic skill.

161,014 starsFreeQuick setup

Reduces manual PDF processing overhead by automating extraction, form filling, and document manipulation at scale—critical for compliance, underwriting, and contract workflows where human review cycles create bottlenecks.

Enterprise operations and finance teams automating document intake, form processing, and contract analysis workflows.

Claude Code Claude Cowork Claude Chat

https://github.com/anthropics/skills

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → PluginsAdd plugin. Search and click Install. Skills work in Claude Code only.
Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.
Command
/plugin marketplace add anthropics/skills   then   /plugin install document-skills@anthropic-agent-skills   (also pre-installed for Claude.ai paid plans)

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

First thing to try

After installing, paste this into Claude:

Help me extract text and data from business documents automatically
CostFree

Trust Signals Reviewed

Stars161,014Contributors14Last updated2026-07-13Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-07-20 · scanner vattempted-no-data

Reviewer notes

Reviewed review. These are observations, not a security certification.

Official Anthropic tool.

Official Anthropic tool. Highest trust level in the ecosystem.

Things to check

  • Performance and accuracy degrade on poor-quality scans, handwritten text, or non-standard layouts. Complex form fields, embedded images as content, and non-Latin scripts may require preprocessing or fallback validation.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation

Ease of Use
4/5
Versatility
4/5
Reliability
4/5
Security
5/5
Overall score4.15 / 5.00 SolidEvaluatedApr 2026
Official Anthropic tool.

Related Outcomes

This tool shows up in these problem-focused recommendations.

← Back to the Claude Observatory

Rolling Claude out in your org? Let's talk.

Start a conversation →