Agent-Skills.md

Agent Skills: pdf-text-extractor

Extracts text content from one or more PDF documents.

UncategorizedID: okgoogle13/careercopilot/pdf-text-extractor

Repository

okgoogle13/careercopilot
okgoogle13
1

Install this agent skill to your local

pnpm dlx add-skill https://github.com/okgoogle13/careercopilot/tree/HEAD/.claude/skills/pdf-text-extractor

Skill Files

Browse the full folder contents for pdf-text-extractor.

Download Skill

Loading file tree…

.claude/skills/pdf-text-extractor/SKILL.md

Skill Metadata

Name
pdf-text-extractor
Description
Extracts text content from one or more PDF documents.

Purpose

Extracts textual content, summaries, or structured data from PDF documents using Claude's multimodal vision capabilities.

When to Use

  • When needing to pull raw text from a PDF for processing or analysis.
  • When summarizing multi-page reports or documents.
  • When extracting specific fields from forms using a JSON schema.

Process

  1. Ingestion: Process all provided PDF documents.
  2. Task Determination: Analyze the prompt for extraction, summarization, Q&A, or data extraction.
  3. Execution: Maintain reading order and extract content according to task requirements.
  4. Format: Return a valid JSON object entry for each document.

Agent Call

Called by: doc-processor-agent (or any other agent) Input: $PROMPT (what to do) and one or more PDF files.

Output

Returns a JSON object containing the processed output for each document, or an error object.