exec_python
100 / 100 · Low risk
Fine to try.
CaP-X-inspired Code-as-Policy escape hatch: instead of unrolling a multi-step plan into N separate tool_calls (each costing a round-trip), emit ONE Python snippet that calls the same tool dispatchers as functions. Every other registered base skill is callable as a Python function from inside the snippet: r = localize_object_top_center(object='red block') for arm in ('left', 'right'): chk = is_reachable(arm=arm, x=r['xyz'][0], y=r['xyz'][1], z=r['xyz'][2]) if chk.get('reachable'): break grasp_th…
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'exec-python' ] || [ -L ~/.agents/skills/'exec-python' ]; then echo 'A skill folder named exec-python already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/nssmd/RoboRSI' "$d" && git -C "$d" checkout --quiet '90c8569705bf4004a4f79e34e650c87ab7f075d4' -- 'roborsi/embodied/skills/base/exec_python/robotwin' && mkdir -p ~/.agents/skills && cp -R "$d"/'roborsi/embodied/skills/base/exec_python/robotwin' ~/.agents/skills/'exec-python' && 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/'exec-python' ~/.claude/skills/'exec-python' (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/nssmd/RoboRSI/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | 90c8569 | 100 |