← All skills

bgpt-paper-search

85 / 100 · Low risk

Fine to try.

By K-Dense-AI/claude-scientific-skills (GitHub) · research · 57,146 stars · scanned at commit 2d2065f

Searches BGPT scientific papers by topic or DOI and retrieves claim-level evidence extracted from full text, including experiments, reported statistics, scope, limitations, and provenance. Use for literature reviews, evidence synthesis, and finding experimental details beyond abstracts.

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/'bgpt-paper-search' ] || [ -L ~/.agents/skills/'bgpt-paper-search' ]; then echo 'A skill folder named bgpt-paper-search already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/K-Dense-AI/claude-scientific-skills' "$d" && git -C "$d" checkout --quiet '2d2065fb4520fa3f3f2bcf61cff26ec8b7eba4b5' -- 'skills/bgpt-paper-search' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/bgpt-paper-search' ~/.agents/skills/'bgpt-paper-search' && 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/'bgpt-paper-search' ~/.claude/skills/'bgpt-paper-search' (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 K-Dense-AI/claude-scientific-skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/K-Dense-AI/claude-scientific-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/K-Dense-AI/claude-scientific-skills/)

Score history

Also found in

Identical copies of this skill exist at:

• K-Dense-AI/scientific-agent-skills/skills/bgpt-paper-search