bio-dataset-search
95 / 100 · Low risk
Fine to try.
Step 3 of the bio-manuscript pipeline: find and match public datasets to manuscript tasks. Use when extracting datasets from related papers or searching repositories (e.g. GEO), normalizing dataset metadata, and mapping datasets to the task system.
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/'bio-dataset-search' ] || [ -L ~/.agents/skills/'bio-dataset-search' ]; then echo 'A skill folder named bio-dataset-search already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/stanfish06/skillquarium' "$d" && git -C "$d" checkout --quiet 'ced6c96bd67acccbf0280a5071e59a523c118c66' -- 'skills/bio-dataset-search' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/bio-dataset-search' ~/.agents/skills/'bio-dataset-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/'bio-dataset-search' ~/.claude/skills/'bio-dataset-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
[](https://zalavijaysinh.github.io/skilltrust/repos/stanfish06/skillquarium/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | ced6c96 | 95 |
| 2026-11-08 | f748ea9 | 95 |