本文へ移動
cccskills
無料GitHub で公開

team-health-check

Assess team health using Patrick Lencioni's Five Dysfunctions of a Team model. Use when a leader says "my team feels off", "we have trust issues", "people aren't speaking up in meetings", "accountability is a problem", "we keep missing commitments", "the team is siloed", "we're not working well together", or "I want to do a team health check". Also trigger when someone describes symptoms like passive agreement in meetings, blame culture, missed deadlines without escalation, or people optimizing for their own metrics over team goals.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md7.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Overview

Based on "The Five Dysfunctions of a Team" by Patrick Lencioni. The five dysfunctions build on each other as a pyramid: absence of trust is the root, and each layer makes the next worse. You cannot fix accountability without first fixing conflict norms, and you cannot fix conflict without first building trust. Diagnose from the bottom up, fix from the bottom up.

The Five Dysfunctions Pyramid

         [5] Inattention to Results
        [4] Avoidance of Accountability
       [3] Lack of Commitment
      [2] Fear of Conflict
     [1] Absence of Trust
LayerDysfunctionHealthy State
1Absence of trustVulnerability-based trust
2Fear of conflictProductive ideological conflict
3Lack of commitmentClear decisions with buy-in
4Avoidance of accountabilityPeer-to-peer accountability
5Inattention to resultsCollective focus on team outcomes

Workflow

Step 1: Run the Diagnostic

Score each dysfunction 1-5 (1 = severe problem, 5 = healthy). Be honest - this is a diagnostic tool, not a performance review.

Trust - Score ___/5

  • Do team members admit mistakes without fear of judgment?
  • Do people ask for help when stuck, or silently struggle?
  • Is there a gap between what people say in 1:1s vs. group meetings?

Conflict - Score ___/5

  • Are difficult topics discussed openly in team meetings, or in side conversations afterward?
  • Does the team reach real resolution, or does it "table" uncomfortable discussions?
  • Do people disagree in the room, or wait until the decision is made and then undermine it?

Commitment - Score ___/5

  • After decisions are made, do people execute with full effort even if they disagreed?
  • Are meeting outputs clear decisions, or ambiguous "next steps"?
  • Do people leave meetings with different understandings of what was decided?

Accountability - Score ___/5

  • Do peers call each other out when a colleague drops the ball?
  • Does accountability only flow downward (manager to report), or sideways too?
  • Are standards applied consistently, or only when the manager is watching?

Results - Score ___/5

  • Do team members prioritize team goals or their individual/department metrics when they conflict?
  • Do people share information that would help teammates, or hoard it?
  • Is collective success celebrated, or only individual wins?

Step 2: Identify the Root Layer

Find the lowest-scored dysfunction. That is where to start. It is almost always trust. If two layers score equally low, start with the lower one on the pyramid.

Example: Conflict scores 2/5 and trust scores 3/5. The conflict problem is real but traces back to trust. Recheck trust using more specific questions before prescribing conflict interventions.

Step 3: Prescribe Interventions by Layer

Trust (score < 3)

  • Personal histories exercise: each person shares 3 facts others don't know (run in a team meeting or offsite)
  • Leader goes first - share your own mistakes, failures, and areas of growth before asking others
  • Working styles discussion: each person names their communication preferences and blind spots
  • Timeline: 4-8 weeks of consistent behavior before trust measurably shifts

Conflict (score < 3)

  • Name the pattern explicitly in the next team meeting: "I've noticed we align quickly. I want us to slow down and surface real disagreements."
  • Assign a devil's advocate role in major decisions - rotate it so no one person becomes "the skeptic"
  • Run pre-mortems: "Assume this plan fails in 6 months. What went wrong?" This gives permission to raise doubts
  • After significant meetings, ask: "Is there anything said in the hallway that wasn't said in the room?"

Commitment (score < 3)

  • Close every meeting with a 2-minute "decisions made" summary - read aloud, confirm agreement
  • Use "disagree and commit" explicitly: team members can vote against but commit to execute
  • Reduce decision latency - slow decisions kill commitment because context and energy decay

Accountability (score < 3)

  • Create a team working agreement (written, visible, referenced in retrospectives)
  • Shift accountability conversations from manager-only to peer-enabled: "I want you to tell each other when standards slip, not wait for me"
  • Monthly retro focused only on: "what did we commit to, and what actually happened?"

Results (score < 3)

  • Post team-level metrics somewhere everyone sees them (Slack, wiki, standup)
  • Celebrate team wins explicitly - not just individual contributions
  • When conflicts arise between team and individual goals, resolve them in favor of team - visibly, with explanation

Step 4: Write the Team Health Report

Team Health Check - [your team] - [date]

Overall Health Score: [x/25]

Scores:
  Trust:          [x/5]
  Conflict:       [x/5]
  Commitment:     [x/5]
  Accountability: [x/5]
  Results:        [x/5]

Root issue: [lowest layer]
Primary intervention: [specific action and owner]
Timeline: [when you will reassess - 6-8 weeks]

Key observations:
  [2-3 specific behaviors observed that support the diagnosis]

Next check-in: [date]

Anti-Patterns

1. Starting at the top layer Bad: "Our results are bad, let's focus everyone on metrics." Good: Poor results almost always trace back to trust or conflict issues. Fixing metrics without fixing trust produces short-term compliance and long-term cynicism.

2. Treating symptoms as the root cause Bad: "We have an accountability problem, so I'm adding more check-ins and status updates." Good: Accountability without commitment is theater. Commitment without healthy conflict produces fake buy-in. Check whether the "accountability problem" is actually a commitment or conflict problem first.

3. Leader skipping vulnerability Bad: Running trust exercises with the team but not sharing your own mistakes, fears, or development areas. Good: The leader always goes first. If you won't model vulnerability, the team won't either - they read your behavior, not your words.

4. One-time exercise Bad: "We did a team offsite and covered all five dysfunctions. We're done." Good: Health degrades under pressure. Teams revert. Reassess every 6-8 weeks during high-stress periods, every quarter otherwise.

5. Using the framework as a performance review Bad: Scoring individuals on the five dysfunctions and sharing those scores. Good: The framework is a team diagnostic, not a 360 review. Keep scores at the team level.

Quality Checklist

  • Scored all five layers, not just the most visible problem
  • Identified the lowest-scoring layer as the starting point
  • Prescribed at least one concrete behavioral intervention per problematic layer
  • Leader's own behavior included in the assessment
  • Report documents specific observed behaviors, not just impressions
  • Reassessment date is set (6-8 weeks out)

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Generate A/B copy variants grounded in Eugene Schwartz's awareness and market-sophistication stages and John Caples' tested-headline discipline. Every variant declares its angle, the awareness stage it targets, and a falsifiable hypothesis, and the skill recommends which pair to test first and what delta counts as signal. Use when the user says "A/B test this", "write variants", "give me options", "test different angles", "copy variants", "ab copy", "test this headline", "multiple versions", "which version is better", or wants to test copy before publishing. For reviewing copy that already exists, see copy-review. For sample size and stopping rules, see growth-experiment. For diagnosing a page rather than its words, see page-cro. For full paid ad sets by platform, see ad-campaign-writer.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Build a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Write paid ad copy for LinkedIn, Google, Meta, and YouTube. Produces multiple variants per platform, each targeting a different Eugene Schwartz awareness level and Cialdini persuasion principle. Use when the user asks for ad copy, ad variants, "write LinkedIn ads", Google ads, Meta ads, paid social copy, ad headlines, or wants creative for a paid campaign. Reads brand voice, ICP, and positioning from knowledge/. For organic social posts, see linkedin-post or social-calendar. For the landing page the ad points at, see landing-page-writer. For testing variants, see ab-copy-writer.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Design clean and consistent APIs. Use when the user says "design an API", "API design review", "design these endpoints", "REST API for X", "GraphQL schema", "API contract", "how should this endpoint work", "review my API design", or wants to create or improve an API interface - even if they don't explicitly say "API design".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

qa-aman のスキルをすべて見る

このスキルの問題を報告する