design
100 / 100 · Low risk
Fine to try.
This skill should be used when the user has a workflow's requirements and wants to plan how AI will do the work: which parts are skills or agents, how much the AI decides at each step, where a person checks, what it connects to, and how each part will be checked. It writes a plan the Build step follows, task by task, and asks the user only what only they can decide. Also use when the user says "continue my workflow" and the workflow needs its plan, a plan was stopped partway, or Build sent back…
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/'design' ] || [ -L ~/.agents/skills/'design' ]; then echo 'A skill folder named design already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/jamesgray-ai/handsonai' "$d" && git -C "$d" checkout --quiet '5a3a1d92737e42de232f377ba9ce3f5bd7d64433' -- 'plugins/handsonai/skills/design' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/handsonai/skills/design' ~/.agents/skills/'design' && 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/'design' ~/.claude/skills/'design' (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/jamesgray-ai/handsonai/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-12 | 5a3a1d9 | 100 |
| 2026-11-08 | f89ab27 | 100 |