pdf-extract
95 / 100 · Low risk
Fine to try.
Extract text from PDF files for LLM processing
What this skill can do
Runs commands on your computer
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'pdf-extract' ] || [ -L ~/.agents/skills/'pdf-extract' ]; then echo 'A skill folder named pdf-extract already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/HKU-MMLab/UniClawBench' "$d" && git -C "$d" checkout --quiet 'a8ac4df6c554178c339f42696e3afe688a61f4b7' -- 'injection/101_skill_usage/task_101_33_exhibitor_compare/skills/pdf-extract' && mkdir -p ~/.agents/skills && cp -R "$d"/'injection/101_skill_usage/task_101_33_exhibitor_compare/skills/pdf-extract' ~/.agents/skills/'pdf-extract' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'pdf-extract' ~/.claude/skills/'pdf-extract' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/HKU-MMLab/UniClawBench/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-10 | a8ac4df | 95 |
Also found in
- HKU-MMLab/UniClawBench/injection/201_skill_usage_zh/task_201_33_exhibitor_compare/skills/pdf-extract