pdf-reading — Claude Code skill: extract, inspect, read PDFs
Skill for reading PDF files from disk: text extraction, page rasterization, table parsing, image and attachment retrieval.
npx skills add SeifBenayed/cloclo --skill pdf-reading -a claude-codeWhat pdf-reading does
The skill gives the agent a set of strategies for working with PDFs: quick diagnostics with pdfinfo and pdftotext, text parsing with pypdf and pdfplumber, per-page rasterization to JPEG via pdftoppm, embedded image and file extraction with pdfimages and pdfdetach. For each document type — text report, scan, slide deck, form, table — it suggests an approach: when text suffices, when visual page inspection is needed, when to render and read the raster.
Inside: Python code samples (pypdf, PyMuPDF, pdfplumber) and Poppler utility commands. The skill does not create PDFs or fill forms — reading only. For multi-page documents cost matters: text runs 200–400 tokens per page, raster around 1,600; the skill teaches the agent what to render and what to skip.
What it helps with
- pull text from a PDF preserving columns and layout
- detect whether a PDF is text-based or scanned
- extract all images, charts, and embedded files
- visually inspect a page with charts and equations
- pick the right reading strategy for each document type
Example prompts for the agent
- Read the first page of
report.pdfand tell me if it's text or a scan - Extract all tables from
data.pdfusing pdfplumber - Rasterize page 3 of
slides.pdfat 150 DPI and show what's on it
How to install pdf-reading
1Skills CLI (Vercel)
npx skills add SeifBenayed/cloclo --skill pdf-reading -a claude-code2Manually: put the files in place
~/.claude/skills/pdf-reading/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pdf-reading/
1Skills CLI (Vercel)
npx skills add SeifBenayed/cloclo --skill pdf-reading -a codex2Manually: put the files in place
.agents/skills/pdf-reading/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add SeifBenayed/cloclo --skill pdf-reading -a cursor2Manually: put the files in place
.cursor/skills/pdf-reading/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install SeifBenayed/cloclo pdf-reading2Manually: put the files in place
.github/skills/pdf-reading/SKILL.md1Skills CLI (Vercel)
npx skills add SeifBenayed/cloclo --skill pdf-reading -a gemini-cli2Platform CLI
gemini skills install https://github.com/SeifBenayed/cloclo --path .claude/skills/pdf-readingManually: put the files in place
.devin/skills/pdf-reading/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add SeifBenayed/cloclo --skill pdf-reading -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pdf-reading
How to install pdf-reading in Claude Code?
Run npx skills add SeifBenayed/cloclo --skill pdf-reading -a claude-code, then open ~/.claude/skills/pdf-reading/SKILL.md — the skill is installed.
What does the pdf-reading skill do?
The skill teaches the agent to read PDFs: extract text, render pages for visual analysis, pull images, tables, and attachments. For each document type it suggests which tool to use and when to render versus when to parse text.
Does pdf-reading require Python or external utilities?
Yes. The skill uses pypdf, pdfplumber, and PyMuPDF libraries, plus Poppler utilities — pdfinfo, pdftotext, pdftoppm, pdfimages. Without them some functions are unavailable.
