# Teamwork

> Creates and manages AI agent teams for complex engineering tasks, with model routing, cost optimization, and performance evaluation.

- Skill: `oyi77/teamwork` (Agent Skill)
- Install (CLI): `npx skillmds@latest add oyi77/teamwork`
- Raw SKILL.md: https://api.skillmd.com/api/skills/oyi77/teamwork/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML, Agent Building
- Tags: Cost Optimization, Model Routing, Multi Agent, Team Management
- License: Apache-2.0
- Author: oyi77 (https://skillmd.com/u/oyi77)
- Updated: 2026-08-22
- Page: https://skillmd.com/skills/oyi77/teamwork

---


# Teamwork

## When to Use

**Trigger phrases:**
- "teamwork"
- "Help me with teamwork"

**Use cases:**
- When the task matches this skill's domain expertise

**When NOT to use:**
- For tasks outside this skill's scope


This skill enables dynamic team creation and management for executing complex engineering tasks through coordinated AI agents with intelligent model selection, cost optimization, and continuous performance evaluation.


## When NOT to Use

- When the task can be solved with existing standard libraries
- When the infrastructure is already in place and working
- When the added complexity does not provide measurable benefit


## Overview

Teamwork is a foundational core infrastructure skill that provides system foundation capabilities for the agent ecosystem.

## Architecture

- **Input layer** — Receives and validates incoming requests
- **Processing layer** — Core logic for system foundation
- **Output layer** — Formats and delivers results
- **State management** — Maintains context across invocations

## Configuration

- Set up required environment variables and paths
- Configure logging level and output format
- Define resource limits (memory, time, API calls)
- Enable/disable features via configuration flags

## Integration

- Exposes standard interfaces for other skills to consume
- Supports event-driven and request-response patterns
- Compatible with the 1ai-skills hook system
- Logs metrics for the skill performance monitor

## Anti-Rationalization Table

| Rationalization | Reality |
|---|---|
| "I will add monitoring later" | Without monitoring, you cannot detect failures. Add it from day one. |
| "One model is enough" | Different tasks need different models. Route intelligently. |
| "Premature optimization" | Infrastructure decisions are hard to change later. Design for scale early. |

```python
# Example: Model routing
ROUTES = {
    "code": ["claude-sonnet-4-20250514", "gpt-4o"],
    "vision": ["gemini-2.5-pro", "gpt-4o"],
    "fast": ["gemini-2.5-flash", "gpt-4o-mini"],
}

def route_request(task: str, prompt: str):
    models = ROUTES.get(task, ROUTES["fast"])
    for model in models:
        try:
            return call_model(model, prompt)
        except Exception:
            continue
    raise RuntimeError("All models failed")
```


## Process

1. **Prepare** — Gather requirements, verify prerequisites, set up environment
1. **Execute** — Run teamwork workflow with configured parameters
1. **Verify** — Validate output meets requirements, document results

## Verification

- [ ] All steps executed successfully
- [ ] Results validated against acceptance criteria
- [ ] Error handling tested with edge cases
- [ ] Documentation updated with findings