team-topology
100 / 100 · Low risk
Fine to try.
Define a multi-agent team for ANY task on ANY system as an explicit deployment topology - pick the shape from the task's dominant risk, specify the runtime/communication/trust layers, place model capability by lane, present it as a diagram + table + trust-boundary note + open choices, and deploy ONLY after the user agrees to the proposed shape. Use when the user asks to "define/design/lay out the team", "what topology are we deploying", "how should the agents be arranged", "design the team for …
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.
Other copies in this repository
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'team-topology' ] || [ -L ~/.agents/skills/'team-topology' ]; then echo 'A skill folder named team-topology already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Cotal-AI/Cotal' "$d" && git -C "$d" checkout --quiet '85da7dac6d4c87bb1b9e02c45abdfdfeec5aa0ea' -- 'claude-plugin/cotal-skills/skills/team-topology' && mkdir -p ~/.agents/skills && cp -R "$d"/'claude-plugin/cotal-skills/skills/team-topology' ~/.agents/skills/'team-topology' && 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/'team-topology' ~/.claude/skills/'team-topology' (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/Cotal-AI/Cotal/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | 85da7da | 100 |
| 2026-11-09 | bdf6fce | 100 |
| 2026-11-07 | dfaf305 | 100 |