Claude-skills pdf-handling

Name: pdf-handling
Author: belumume

Extract PDFs to text and images before reading

install

source · Clone the upstream repo

git clone https://github.com/belumume/claude-skills

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/belumume/claude-skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/plugins/pdf-guard/skills/pdf-handling" ~/.claude/skills/belumume-claude-skills-pdf-handling && rm -rf "$T"

manifest: plugins/pdf-guard/skills/pdf-handling/SKILL.md

source content

PDF Extraction

Standard:

python "$CLAUDE_PLUGIN_DIR/scripts/pdf_extract.py" "file.pdf"

Unified:

python "$CLAUDE_PLUGIN_DIR/scripts/pdf_extract_unified.py" "file.pdf"

Read the extracted .txt or _unified.md, not the PDF.