agent-team-builder — Claude Code skill: design multi-agent teams
agent-team-builder generates production-ready multi-agent team configurations through interactive discovery of business workflows.
MIT 259 installs ★ 440 updated 2026-10-20
npx skills add OneWave-AI/claude-skills --skill agent-team-builder -a claude-codeWhat agent-team-builder does
This skill designs agent architectures without deploying them. It starts by asking open questions: which process to automate, who is involved now, where delays and errors occur, volume, success metrics, constraints. From your answers, it builds a minimal 3–7-agent team with roles like coordinator, specialist, validator, or interface agent.
Generates four outputs: team-config.yaml with all agent parameters, system prompts in agents/{id}/, workflow documentation, and test scenarios. Each agent gets only the tools it needs (least-privilege principle), with documented failure modes and recovery steps. Config uses environment variables for API keys—no secrets stored in plain text.
Fits complex processes with many handoffs, high error risk, or compliance gates. Overkill for a single-agent task.
What it helps with
- design a multi-agent system for sales pipeline, support triage, or market research
- discover pain points and bottlenecks in a business workflow
- define roles, tool access, and escalation rules for each agent
- generate system prompts tailored to your workflow
- create test scenarios before deploying to production
Example prompts for the agent
- Build a team to automate sales qualification through contract signing with CRM integration
- Design agents for routing support tickets through Slack, Jira, and knowledge base
- Create parallel data collection and validation workflow for competitive research
How to install agent-team-builder
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill agent-team-builder -a claude-code2Manually: put the files in place
~/.claude/skills/agent-team-builder/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/agent-team-builder/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill agent-team-builder -a codex2Manually: put the files in place
.agents/skills/agent-team-builder/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill agent-team-builder -a cursor2Manually: put the files in place
.cursor/skills/agent-team-builder/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills agent-team-builder2Manually: put the files in place
.github/skills/agent-team-builder/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill agent-team-builder -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path agent-team-builderManually: put the files in place
.devin/skills/agent-team-builder/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill agent-team-builder -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about agent-team-builder
How do I install agent-team-builder in Claude Code?
Run npx skills add OneWave-AI/claude-skills --skill agent-team-builder -a claude-code, then open ~/.claude/skills/agent-team-builder/SKILL.md. For Codex use -a codex, for Cursor -a cursor, for Gemini CLI -a gemini-cli, or use gh skill install for GitHub Copilot.
What does agent-team-builder do?
It conducts a guided discovery session about your business process, identifies bottlenecks and pain points, then generates configuration files for a multi-agent system with defined roles, system prompts, handoff rules, and test scenarios ready to validate.
How are tools assigned to agents?
Each agent receives only the tools it needs for its role. The skill applies least-privilege principle—a coordinator routes tasks between agents, a specialist accesses APIs or databases, a validator checks outputs, an interface agent handles external communication.
Source text
SKILL.md · MIT
---
name: agent-team-builder
description: Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.
tools: Read, Write, Bash, Glob
model: inherit
---
# Agent Team Builder
Design and generate production-ready multi-agent team configurations for business workflows through an interactive discovery session. This skill generates configuration files; it does not execute or deploy agents.
## Contents
- `references/team-templates.md` — Sales, Support, Research, and Content team starting points.
- `references/config-schema.md` — Full `team-config.yaml` schema plus advanced features (A2A messaging, scaling, shared context).
- `references/output-files.md` — Files to generate and the final response format.
## Workflow
Always complete discovery before designing. Never generate a team config without understanding the business process first.
1. **Run discovery.** Ask the user, one area at a time:
- Process name (what to automate).
- Current state (who is involved, handoff points).
- Pain points (where delays, errors, or bottlenecks occur).
- Volume (runs per day/week/month).
- Success metrics (time, error rate, satisfaction).
- Constraints (compliance, approval gates, human-in-the-loop).
- Integrations (CRM, email, Slack, databases, APIs).
2. **Design the team architecture.** Determine the minimum number of agents (typically 3-7). Select role types as needed:
- Coordinator — orchestrates workflow, routes tasks, handles exceptions.
- Specialist — deep expertise in one domain.
- Validator — quality assurance, compliance checking, output review.
- Interface — handles external communication.
- Data — manages retrieval, transformation, and storage.
Pick a communication pattern: hub-and-spoke (sequential), pipeline (linear), mesh (collaborative), or broadcast (notification). Start from a template in `references/team-templates.md` when one fits.
3. **Specify each agent.** Define: Agent ID, Role Title, full production-ready System Prompt, Tool Access (least privilege), Input Schema, Output Schema, Handoff Rules, Escalation Rules, Success Criteria, and Failure Modes.
4. **Generate the configuration files.** Produce `team-config.yaml`, per-agent `agents/{id}/prompt.md`, `workflow.md`, and `test-scenarios.yaml` per `references/output-files.md`, conforming to `references/config-schema.md`.
5. **Present the design** using the response format in `references/output-files.md`.
## Execution Rules
1. Always start with discovery.
2. Apply principle of least privilege — give each agent only the tools and access it needs.
3. Design for failure — every agent gets failure modes and recovery strategies.
4. Keep a human in the loop — include escalation paths for high-stakes decisions.
5. Define measurable outcomes — every agent gets trackable success criteria.
6. Start small — recommend 3-4 agents and expand based on performance data.
7. Document everything — keep the generated config self-documenting and maintainable.
8. Generate test scenarios so the team can be validated before deployment.
9. Recommend a pilot phase before full deployment.
10. Never include API keys, passwords, or secrets in generated config; use environment variable references.
The generated `team-config.yaml` is designed to be consumed by an agent orchestration framework. Treat all generated system prompts as starting points to refine against real-world performance.
© OneWave-AI · MIT · OneWave-AI/claude-skills