← All skills

document-extraction

97 / 100 · Low risk

Fine to try.

By open-neko/openneko (GitHub) · other · 20 stars · scanned at commit 621f131

Extract plain text from any uploaded document — PDF (including scanned pages via OCR), DOCX, PPTX, XLSX, HTML, and unknown or oddly-encoded files. Use whenever you need the text content of a non-plain-text file before summarizing, cataloging, or answering questions about it.

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/'document-extraction' ] || [ -L ~/.agents/skills/'document-extraction' ]; then echo 'A skill folder named document-extraction already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/open-neko/openneko' "$d" && git -C "$d" checkout --quiet '621f131813e2fbb2a0fda670e81083041894a1ba' -- 'packages/llm/assets/builtin-skills/document-extraction' && mkdir -p ~/.agents/skills && cp -R "$d"/'packages/llm/assets/builtin-skills/document-extraction' ~/.agents/skills/'document-extraction' && 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/'document-extraction' ~/.claude/skills/'document-extraction' (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 open-neko/openneko shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/open-neko/openneko.svg)](https://zalavijaysinh.github.io/skilltrust/repos/open-neko/openneko/)

Score history