plan
100 / 100 · Low risk
Fine to try.
Declare and revise an execution plan. Rollout §III-B 4-phase pattern: RECEIVE_INSTRUCTION → DESCRIBE_SCENE → STEPS_PLANNING → EXECUTE. Each substep has progress %, success_evidence, fallback. The plan is RECORDED, not enforced — re-emit plan() any time during execution to revise based on what was learned (substeps changed, scene differs, new strategy). Validation is LENIENT: warns about issues but accepts the plan; VLM uses the warnings to refine.
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/'plan' ] || [ -L ~/.agents/skills/'plan' ]; then echo 'A skill folder named plan 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 "$d" checkout --quiet '90c8569705bf4004a4f79e34e650c87ab7f075d4' -- 'roborsi/embodied/skills/base/plan/robotwin' && mkdir -p ~/.agents/skills && cp -R "$d"/'roborsi/embodied/skills/base/plan/robotwin' ~/.agents/skills/'plan' && 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/'plan' ~/.claude/skills/'plan' (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 |