agent-design
100 / 100 · Low risk
Fine to try.
Use when building an LLM agent that uses tools over multiple steps. Covers tool design, the agent loop, error recovery, termination, human checkpoints, and knowing when an agent is the wrong architecture. Trigger on "my agent keeps looping", "agent calls the wrong tool", "build an agent that can use our api". Do not use for delegating work to a subagent — see the subagents skill; for building the MCP server that exposes tools, see the mcp-server skill.
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/'agent-design' ] || [ -L ~/.agents/skills/'agent-design' ]; then echo 'A skill folder named agent-design already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/nimadorostkar/Claude-Skills-collection' "$d" && git -C "$d" checkout --quiet '1691932edc17063d712a85d02bcc7a1cd3791057' -- 'skills/ai/agent-design' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/ai/agent-design' ~/.agents/skills/'agent-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/'agent-design' ~/.claude/skills/'agent-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/nimadorostkar/Claude-Skills-collection/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-09 | 1691932 | 100 |
| 2026-11-07 | 31f227e | 100 |