team-builder

Discover, select, and run multiple AI agents in parallel with aggregated results.

1|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/xxih/ai-harness-zh --skill team-builder-xxih
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team-builder
Source: https://github.com/xxih/ai-harness-zh/tree/main/references/translations/everything-claude-code/docs/zh-CN/skills/team-builder
Command: npx skills add https://github.com/xxih/ai-harness-zh --skill team-builder-xxih

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates the manual effort of locating, reviewing, and launching multiple specialized AI agents, allowing users to quickly form functional teams for complex tasks.

Core Features & Use Cases

  • Dynamic Agent Discovery: Scans local and global markdown directories to list available agents without hard‑coded lists.
  • Interactive Selection: Presents domain‑based menus and supports flexible input (numbers, names, or phrases) to choose up to five agents.
  • Parallel Execution & Aggregation: Launches selected agents concurrently, captures their outputs, and produces a consolidated report.
  • Use Cases: Security review combined with SEO analysis, architectural design alongside product planning, or any cross‑disciplinary assessment requiring multiple expert agents.

Quick Start

Ask the team-builder to assemble a security engineer and SEO specialist for reviewing my e‑commerce site before launch.

Frequently Asked Questions about team-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run multiple AI agents in parallel for a single task?

Parallel AI agent execution works by dynamically discovering available agent markdown files, letting you select up to five specialized agents, launching them concurrently, and aggregating their outputs into one consolidated report.

What is dynamic agent discovery and how does it work for building AI teams?

Dynamic agent discovery scans local and global markdown directories to list available AI agents without relying on hard-coded lists, presenting interactive domain-based menus for selecting up to five specialized agents to form a collaborative team.

Can I select specific AI agents by name or number when forming a team?

Yes, you can select specific AI agents using flexible input formats including numbers, names, or descriptive phrases to choose up to five specialized agents from the dynamically discovered markdown-based menus.

Does team-builder require hard-coded agent lists to dispatch parallel AI teams?

No, it does not require hard-coded agent lists; it dynamically discovers available agent files by scanning local and global markdown directories to assemble and dispatch parallel AI teams for cross-disciplinary assessments.

What's the best way to combine a security review with an SEO analysis using AI agents?

The best way to combine a security review with SEO analysis is to assemble a collaborative AI team by selecting both a security engineer and an SEO specialist agent, executing them in parallel, and aggregating their results into a consolidated report.

How many specialized agents can I run concurrently for cross-disciplinary assessments?

You can run up to five specialized agents concurrently for cross-disciplinary assessments, capturing their parallel execution outputs and producing a consolidated aggregated report without needing hard-coded agent lists.