← All skills

extract_pdf_content

85 / 100 · Low risk

Fine to try.

By cxcscmu/SkillLearnBench (GitHub) · research · 93 stars · scanned at commit 726e1f7

Extracts text and mathematical descriptions from a PDF file to identify specific algorithm parameters and loss functions. This is used to ensure the implementation matches the theoretical definition in the paper.

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'extract-pdf-content' ] || [ -L ~/.agents/skills/'extract-pdf-content' ]; then echo 'A skill folder named extract-pdf-content already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/cxcscmu/SkillLearnBench' "$d" && git -C "$d" checkout --quiet '726e1f79b96b0cb3d729d0e55a1c847e0b5353ae' -- 'skills/b3-teacher-feedback-gemini-3-flash-preview/nlp-paper-reproduction/run2_extract_pdf_content' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/b3-teacher-feedback-gemini-3-flash-preview/nlp-paper-reproduction/run2_extract_pdf_content' ~/.agents/skills/'extract-pdf-content' && 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/'extract-pdf-content' ~/.claude/skills/'extract-pdf-content' (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

The badge for cxcscmu/SkillLearnBench shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/cxcscmu/SkillLearnBench.svg)](https://zalavijaysinh.github.io/skilltrust/repos/cxcscmu/SkillLearnBench/)

Score history