scientific-impl
85 / 100 · Low risk
Fine to try.
Use for tasks that implement a numerical, statistical, or sampling algorithm with formal tests against known truth — "implement a sampler / estimator / integrator", "compare results to known distributions", "validate inputs and reject invalid cases". Covers R/Python scientific code with modular functions and PASS/FAIL test output.
What this skill can do
Downloads and installs other software
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'scientific-impl' ] || [ -L ~/.agents/skills/'scientific-impl' ]; then echo 'A skill folder named scientific-impl already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/RUC-NLPIR/FlashRSI' "$d" && git -C "$d" checkout --quiet '37837ec5052aee24a252c88fd3b10215ccb4af7d' -- 'exports/harnesses/meta_harness-claude_code-terminalbench/skills/scientific-impl' && mkdir -p ~/.agents/skills && cp -R "$d"/'exports/harnesses/meta_harness-claude_code-terminalbench/skills/scientific-impl' ~/.agents/skills/'scientific-impl' && 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/'scientific-impl' ~/.claude/skills/'scientific-impl' (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/RUC-NLPIR/FlashRSI/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-14 | 37837ec | 85 |
| 2026-11-09 | 0ce41eb | 85 |