Team logo

Team

CommunityPopular
MaxMiksa
team

Quickly assemble a temporary AI agent team for a task. Automatically select the most suitable members from .claude/agents/.

Overview

PublisherMaxMiksa
RepositoryAuto-Company
Skill nameteam
Stars
3.1K
Forks
493
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by MaxMiksa on GitHub. Read the source before you install it.

Installation

Install the Team AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/MaxMiksa/Auto-Company/tree/main/.claude/skills/team
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/MaxMiksa/Auto-Company.git /tmp/Auto-Company
mkdir -p .claude/skills
cp -r /tmp/Auto-Company/.claude/skills/team .claude/skills/team
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Team in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Team on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Team is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Assemble a Temporary Team

For the task below, select the most suitable members from the company's existing AI agents and assemble a temporary team to complete it together.

Task

$ARGUMENTS

Available Agents

These are all of the company's agents, defined in .claude/agents/:

AgentFileResponsibilities
CEO.claude/agents/ceo-bezos.mdStrategic decisions, business models, PR/FAQ, priorities
CTO.claude/agents/cto-vogels.mdTechnical architecture, technology selection, system design
Inversion Advisor.claude/agents/critic-munger.mdChallenge decisions, identify fatal flaws, Pre-Mortem, prevent collective delusion
Product Design.claude/agents/product-norman.mdProduct definition, user experience, usability
UI Design.claude/agents/ui-duarte.mdVisual design, design systems, color and typography
Interaction Design.claude/agents/interaction-cooper.mdUser flows, personas, interaction patterns
Full-Stack Development.claude/agents/fullstack-dhh.mdCode implementation, technical solutions, development
QA.claude/agents/qa-bach.mdTest strategy, quality control, bug analysis
DevOps/SRE.claude/agents/devops-hightower.mdDeployment pipelines, CI/CD, infrastructure, monitoring and operations
Marketing.claude/agents/marketing-godin.mdPositioning, brand, acquisition, content
Operations.claude/agents/operations-pg.mdUser operations, growth, community, PMF
Sales.claude/agents/sales-ross.mdSales funnels, conversion strategy
CFO.claude/agents/cfo-campbell.mdPricing strategy, financial models, cost control, unit economics
Research.claude/agents/research-thompson.mdMarket research, competitive analysis, industry trends, opportunity discovery

Execution Steps

1. Analyze the Task and Select Members

Select the 2-5 most relevant agents for the nature of the task. Selection principles:

  • Select only those needed: More people is not always better; match the task's needs precisely
  • Consider the collaboration chain: If the task spans design through development, ensure the key roles along that chain are represented
  • Avoid redundancy: Do not select overlapping roles together

Briefly explain to the founder whom you selected and why, then immediately start assembling the team.

2. Create an Agent Team

Use the Agent Teams feature to assemble the temporary team:

  • Create a team with a short, task-based team_name (English, kebab-case)
  • Create a specific task for each member (TaskCreate), with enough context in the task description
  • Use the Task tool to spawn each teammate with subagent_type set to general-purpose; inject the full content of the corresponding agent file into the prompt as its role definition
  • When spawning a teammate, state in the prompt: its role definition, the task to complete, the cycle's runtime Language instruction, and that output documents belong under docs/<role>/

For frontend work, name one selected member as design owner without expanding the team just for a title. The owner and implementer must read .claude/skills/frontend-design.md. Pass the user task, agreed visual direction, key component decisions and acceptance states with the implementation handoff; the owner checks the implemented screens, not only a written design.

For a dedicated frontend finishing cycle, the design owner, implementer and verifier also use .claude/skills/frontend-polish/SKILL.md. Hand off the current product's screenshots and known functional behavior, the identity to retain, concrete defects to fix and the interface version already reviewed. Share only materials within the permitted project workspace. Complete and record the pass once for that version; later targeted reviews do not restart a full redesign.

3. Coordinate and Consolidate

  • Coordinate the members' work as team lead
  • Collect their outputs and consolidate them into a unified conclusion or proposal
  • If there are disagreements, present each position for the founder to decide
  • Clean up team resources after completion

Notes

  • Follow the runtime product Language instruction for user-facing communication and documents throughout the current product, including pauses and restarts. A requested language change applies to the next product. If no product language is assigned, follow explicit human language instructions or the user's language. Keep technical terms in English. The language of this skill's source does not set the output language
  • Leave language preference changes to the human-operated settings interface; do not edit saved language configuration or the current product's language state
  • Store each member's output documents under docs/<role>/ as agreed
  • The team is temporary and dissolves when the task is complete
  • The founder is the final decision-maker; agents provide advice but do not replace that decision-making authority

Frequently asked questions

What does the Team AI skill do?

Quickly assemble a temporary AI agent team for a task. Automatically select the most suitable members from .claude/agents/.

Why use Team on TypingMind?

Because you install it once and use it with any model. Team is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Team in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MaxMiksa/Auto-Company/tree/main/.claude/skills/team. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Team?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Team?

As many as you like. As long as a model supports skills, you can use Team with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Team AI skill free?

Yes. It is published on GitHub by MaxMiksa under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇