agentleFS
NikitaDmitrieffNikitaDmitrieff/auto-co-meta/.claude/skills/team/SKILL.md

team

Skill43 starsChanged 9 months agoMITView on GitHub

Quickly assemble a temporary AI Agent team for a task. Automatically selects the best members from .claude/agents/.

50 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ralplan.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ibahgatSkill

    ralplan

    Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.

    Also in 8 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 36 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All agents are defined in .claude/agents/:

    line 18
  2. Distinctive:

    Use the Agent Teams feature to form a temporary team:

    line 50
  3. Very specific:

    Create a team with team_name based on a short task name (English, kebab-case)

    line 51
  4. Distinctive:

    Create a specific task for each member (TaskCreate) with sufficient context in the description

    line 52
  5. Very specific:

    When spawning, tell each teammate: their role definition, the task to complete, and that output documents go in docs/<role>/

    line 54
  6. Distinctive:

    If there are disagreements, list each side's viewpoint for the CEO to decide

    line 60

“Common” is measured: kept by at least 6 in 10 of the 36 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Assemble Temporary Team

Based on the task below, select the most suitable members from the company's AI Agents and form a temporary team to collaborate on it.

Task

$ARGUMENTS

Available Agents

All agents are defined in .claude/agents/:

AgentFileRole
CEOceo-bezosStrategic decisions, business models, PR/FAQ, prioritization
CTOcto-vogelsTechnical architecture, technology selection, system design
Criticcritic-mungerChallenge decisions, identify fatal flaws, Pre-Mortem, prevent groupthink
Product Designproduct-normanProduct definition, user experience, usability
UI Designui-duarteVisual design, design system, color and typography
Interaction Designinteraction-cooperUser flows, Personas, interaction patterns
Full-Stack Devfullstack-dhhCode implementation, technical proposals, development
QAqa-bachTest strategy, quality gates, bug analysis
DevOps/SREdevops-hightowerDeployment pipelines, CI/CD, infrastructure, monitoring
Marketingmarketing-godinPositioning, brand, acquisition, content
Operationsoperations-pgUser operations, growth, community, PMF
Salessales-rossSales funnel, conversion strategy
CFOcfo-campbellPricing strategy, financial models, cost control, unit economics
Researchresearch-thompsonMarket research, competitive analysis, industry trends, opportunity discovery

Execution Steps

1. Analyze the Task, Select Members

Select 2-5 of the most relevant Agents as team members based on the task. Selection principles:

  • Only pick who's needed -- more people is not better; match precisely to the task
  • Consider the collaboration chain -- if the task spans design to development, include key roles along the chain
  • Avoid redundancy -- don't select agents with overlapping roles

Briefly state who you selected and why, then immediately begin assembling the team.

2. Assemble the Agent Team

Use the Agent Teams feature to form a temporary team:

  • Create a team with team_name based on a short task name (English, kebab-case)
  • Create a specific task for each member (TaskCreate) with sufficient context in the description
  • Spawn each teammate using the Task tool with subagent_type set to general-purpose, injecting the full content of the corresponding agent file as the role definition in the prompt
  • When spawning, tell each teammate: their role definition, the task to complete, and that output documents go in docs/<role>/

3. Coordinate and Synthesize

  • As team lead, coordinate each member's work
  • Collect outputs from all members and synthesize into a unified conclusion or plan
  • If there are disagreements, list each side's viewpoint for the CEO to decide
  • Clean up team resources when done

Notes

  • Communicate in English
  • Each member's output documents go in docs/<role>/ as defined
  • Teams are temporary -- disband once the task is complete
  • The CEO (Bezos) is the ultimate decision-maker; other agents provide recommendations but do not override

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.