MCPInstall

team-builder

Creates high-trust, high-performance team environments through structural mechanisms for psychological safety, shared consciousness, and empowered execution. Use when building team culture, onboarding new teams, diagnosing team dysfunction, or improving collaboration.

Installs
39
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/joellewis/skill-library --skill team-builder
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads team-builder automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Overview

Team building is the discipline of creating high-trust, high-performance environments. This skill replaces "surface-level" team building with structural mechanisms for psychological safety, shared consciousness, and empowered execution, ensuring that every member feels safe to speak up, share vulnerability, and align with a common purpose.

Guiding Principles

Principle 1: Psychological Safety is #1 (Source: Edmondson, Fearless Organization)

The primary predictor of team success is the belief that one will not be punished or humiliated for speaking up with ideas, questions, concerns, or mistakes. Without safety, a team cannot learn or innovate.

Principle 2: Vulnerability Loops (Source: Coyle, The Culture Code)

Trust is built when people are willing to be vulnerable. When a leader admits they don't know something or asks for help, it signals to others that they can do the same, creating a reinforcing "vulnerability loop."

Principle 3: Shared Consciousness (Source: McChrystal, Team of Teams)

In complex environments, every team member must understand the "big picture" of the entire organization. High-performance teams rely on radical transparency so that decentralized individuals can make aligned decisions.

Principle 4: The Gardener Model (Source: McChrystal, Team of Teams)

The leader is not a chess player moving pieces; the leader is a "Gardener." Their job is to shape the ecosystem (culture, transparency, safety) so that the team can flourish and execute autonomously.

Principle 5: Candor over Honesty (Source: Catmull, Creativity Inc)

"Honesty" has a moral weight that can be intimidating. "Candor" is a professional tool. Build mechanisms (like Braintrusts) where candid feedback is expected, depersonalized, and focused solely on improving the work.

When to Use This Skill

  • When a team is experiencing "silence" or a lack of participation in meetings.
  • When a project fails and the team is "blaming" rather than learning.
  • When scaling an organization and needing to build a "Team of Teams" structure.
  • When culture feels "siloed" and departments are misaligned.

When NOT to Use This Skill

  • In low-complexity, repetitive tasks where individual output is the only metric.
  • In temporary, one-off groups where the overhead of building "Shared Consciousness" is not justified.

Core Process

Step 1: Establish Psychological Safety

Create the environment for open dialogue. (Source: Edmondson, Ch. 5)

  1. Frame the Work: Explicitly state that the project is complex and the outcome is uncertain. "We need everyone's eyes and brains on this."
  2. Model Fallibility: Admit your own mistakes and limitations. "I might miss something here, please call it out."
  3. Practice Inquiry: Ask genuine, open-ended questions. "What are you seeing that I'm missing?"

Step 2: Build the "Shared Consciousness"

Ensure everyone has the same "big picture" view. (Source: McChrystal, Ch. 8)

  1. Radical Transparency: Share information broadly and frequently (e.g., daily stand-ups, open dashboards).
  2. Context Sharing: Every tactical update must be connected back to the "Why" and the strategic aspiration.

Step 3: Launch the "Vulnerability Loop"

Deepen trust through shared risk. (Source: Coyle, Ch. 3)

  1. The Signal: Explicitly ask for help on a specific, non-trivial problem.
  2. The Response: Reward those who provide help or admit their own gaps.
  3. Belonging Cues: Use active listening, eye contact, and "post-meeting follow-ups" to signal that the member is valued.

Step 4: Implement Candor Mechanisms

Create a safe space for rigorous feedback. (Source: Catmull, Ch. 5)

  1. The Braintrust: Form a group of peers to review work. Rule: The reviewers have no authority to mandate changes; the creator has no obligation to follow them.
  2. Post-Mortem / Pre-Mortem: Conduct reviews focused on the system, not the person. "What in our process allowed this failure to happen?"

Step 5: Empower Execution (Eyes On, Hands Off)

Push decision-making down. (Source: McChrystal, Ch. 11)

  1. Define Intent: Provide the "Commander's Intent" (What and Why).
  2. Grant Authority: Formally state what decisions the team can make without approval.
  3. Monitor: Stay informed (Eyes On), but do not intervene unless the system is failing (Hands Off).

Frameworks & Models

The 5 Keys to Team Effectiveness (Source: Google re:Work)

  1. Psychological Safety: Can we take risks without feeling insecure?
  2. Dependability: Can we count on each other to do high-quality work on time?
  3. Structure & Clarity: Are goals, roles, and execution plans clear?
  4. Meaning: Are we working on something that is personally important?
  5. Impact: Do we fundamentally believe that our work matters?

The Braintrust Rules (Source: Catmull, Creativity Inc)

  • Feedback must be constructive and focused on the problem, not the person.
  • The director/creator owns the final decision.
  • The goal is candor, not politeness.

Cross-Skill Invocations

  • REQUIRED SUB-SKILL: feedback-coach — To deliver the candor required in Braintrusts.
  • RECOMMENDED SUB-SKILL: difficult-conversations — To address "Safety-killing" behaviors in the team.
  • RECOMMENDED SUB-SKILL: ownership-coach — To build the "I intend to..." culture within the team.

Common Mistakes

  1. The Zero-Error Trap: Punishing mistakes, which leads to hidden errors and lack of innovation. (Source: Catmull, Ch. 9)
  2. The Order Trap: Relying on "Leader-Follower" command in complex environments where "Shared Consciousness" is needed. (Source: McChrystal, Ch. 1)
  3. Surface-Level "Bonding": Assuming that "team building activities" (like escape rooms) build trust, while ignoring structural safety in meetings. (Source: Coyle, Ch. 1)
  4. Confusing Candor with Cruelty: Allowing "brutal honesty" that destroys psychological safety. (Source: Catmull, Ch. 4)

Diagnostic Checklist

  • Is every member of the team speaking up during meetings?
  • Have I (the leader) recently admitted a mistake or asked for help?
  • Does every member understand the "Big Picture" and the "Why" of the project?
  • Is there a mechanism (like a Braintrust) for depersonalized candid feedback?
  • Has decision-making authority been pushed down to the lowest possible level?

Sources

  • Edmondson, Fearless Organization, Ch. 1, 5, 7 — Psychological Safety, Learning, Failure.
  • Coyle, The Culture Code, Ch. 1-3, 5 — Safety, Vulnerability, Purpose.
  • McChrystal, Team of Teams, Ch. 8, 11-12 — Shared Consciousness, Empowered Execution.
  • Catmull, Creativity Inc, Ch. 4-5, 9 — Candor, Braintrust, Zero-Error Trap.
  • Schmidt, Trillion Dollar Coach — Team coaching principles.

FAQ

What does the team-builder skill do?

Creates high-trust, high-performance team environments through structural mechanisms for psychological safety, shared consciousness, and empowered execution. Use when building team culture, onboarding new teams, diagnosing team dysfunction, or improving collaboration.

How do I install team-builder?

Run npx skills add https://github.com/joellewis/skill-library --skill team-builder in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/team-builder/ (personal) or .claude/skills/team-builder/ (project).

Which AI agents can use team-builder?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is team-builder safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains team-builder?

It is published by joellewis in joellewis/skill-library. It has 39 recorded installs.

More from joellewis/skill-library

View all →

fiction-architect

joellewis/skill-library

Open the skill to read its SKILL.md instructions.

55 installs

dialogue-craft

joellewis/skill-library

Open the skill to read its SKILL.md instructions.

53 installs

world-building-logic

joellewis/skill-library

Open the skill to read its SKILL.md instructions.

53 installs

character-vulnerability

joellewis/skill-library

Open the skill to read its SKILL.md instructions.

Security47 installs

one-pager

joellewis/skill-library

Open the skill to read its SKILL.md instructions.

47 installs

problem-framing

joellewis/skill-library

Use when beginning analytical or strategic tasks, facing undefined problems, or facing analysis paralysis—requires explicit problem definition before proceeding.

47 installs

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.