From unitor
Multi-AI collaboration for tasks requiring multiple perspectives, discussion, or negotiation. Use when: user explicitly requests collaboration (negotiate, discuss, multiple angles, review from different perspectives, get feedback from multiple experts), task benefits from diverse viewpoints (review, critique, evaluation, brainstorming), or task needs specialist discussion. Examples: 'review this from multiple angles', 'negotiate and handle this issue', 'get different perspectives on this', 'discuss pros and cons of this approach'.
How this skill is triggered — by the user, by Claude, or both
Slash command
/unitor:collaborationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Guidance for orchestrating multi-AI collaboration in Unitor.
Guidance for orchestrating multi-AI collaboration in Unitor.
Use /unitor:collab when a task requires multiple AI specialists working together:
Tasks needing multiple perspectives:
Tasks spanning multiple technical domains:
Collaboration keywords to watch for:
You (Claude) are the coordinator. The workflow:
Write task-specific descriptions (not generic templates):
Good:
Bad:
Task: "Build user authentication"
Roles JSON:
{
"roles": {
"auth-api": "JWT authentication API - implement login/register/refresh endpoints with token generation, validation middleware, bcrypt password hashing",
"login-ui": "React authentication UI - build login/signup forms with validation, error handling, loading states, token storage",
"user-db": "User database - design users table with email, password_hash, created_at, sessions table for refresh tokens"
}
}
Runtime call:
node "${CLAUDE_PLUGIN_ROOT}/scripts/unitor-runtime.mjs" collab /tmp/roles.json "build user authentication"
npx claudepluginhub done-0/unitor --plugin unitorGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.