A practical AI task guide

How to extract data from PDFs with AI

The answer

Use the pdf-analyzer skill to extract text, tables, and metadata from PDF files in Cursor, Claude Code, Codex, or Gemini CLI.

Explore pdf-analyzer →

3 steps

Step 1: Install with Terminal Skills CLI

npx terminal-skills install pdf-analyzer

Step 2: Or curl the SKILL.md into your agent skills folder

# Claude Code
curl -sL https://raw.githubusercontent.com/TerminalSkills/skills/main/skills/pdf-analyzer/SKILL.md -o .claude/skills/pdf-analyzer.md
# Codex
curl -sL https://raw.githubusercontent.com/TerminalSkills/skills/main/skills/pdf-analyzer/SKILL.md -o .codex/skills/pdf-analyzer.md
# Cursor
curl -sL https://raw.githubusercontent.com/TerminalSkills/skills/main/skills/pdf-analyzer/SKILL.md -o .cursor/skills/pdf-analyzer.md

Step 3: Point the agent at a PDF and ask for extraction

Use pdf-analyzer to extract text and tables from ./report.pdf

Author's take / 作者点评

Reliable for text/table PDF extraction with pdfplumber. Best for digital PDFs; scanned docs need OCR outside the skill.

对可复制文本/表格的 PDF 很稳；扫描件要另加 OCR，本技能不覆盖。

Money-saving tip

Skills are free/open-source; spend goes to your agent plan. Start on Cursor Plus ($8/mo) or Claude Pro / ChatGPT Go before upgrading.

Alternatives

markdown-writer →

Generates well-structured technical documentation in Markdown. Use when a user asks to write docs, create a README, document an API, write a how-to guide, ge...

openai-docs →

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation...

FAQ

Which skill should I use?

Use the pdf-analyzer skill to extract text, tables, and metadata from PDF files in Cursor, Claude Code, Codex, or Gemini CLI.

What tools does the primary skill support?

Cursor, Claude Code, Codex, Gemini CLI

Where is the source?

https://github.com/TerminalSkills/skills/tree/main/skills/pdf-analyzer