agenthub
FeaturedMulti-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.
Install
Quality Score: 94/100
Skill Content
Details
- Author
- alirezarezvani
- Repository
- alirezarezvani/claude-skills
- Created
- 9 months ago
- Last Updated
- 1 weeks ago
- Language
- Python
- License
- MIT
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
agent-coordination
Agent spawning, lifecycle management, and coordination patterns. Manages 60+ agent types with specialized capabilities. Use when: spawning agents, coordinating multi-agent tasks, managing agent pools. Skip when: single-agent work, no coordination needed.
agent-swarm
(Industry standard: Parallel Agent) Primary Use Case: Work that can be partitioned into independent sub-tasks running concurrently across multiple agents. Parallel multi-agent execution pattern. Use when: work can be partitioned into independent tasks that N agents can execute simultaneously across worktrees. Includes routing (sequential vs parallel), merge verification, and correction loops.
agent-team
Auto-spawn a coordinated team of Claude Code teammates (each with own context, can DM each other, share a task list) when the user describes work that spans multiple domains and would benefit from specialists working in parallel with feedback loops. Triggers on phrases like "create a website for X", "build me an app for Y", "spin up a landing page for Z", "make me a site about W", "I need this built end-to-end", "review this from multiple angles", "debug this with competing hypotheses", or any request that implies multi-specialist parallel work with a quality loop. Auto-classifies the request, picks team composition + model-per-role + file ownership + hand-off graph, then spawns. Skip for single-domain tasks (use matching specialist skill), sequential pipelines (use subagents), or simple one-shot work. Requires the host's multi-agent team feature to be enabled; on Claude Code that means setting CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in settings.json.