Fixing Underperforming Teams logo

Fixing Underperforming Teams

OrganizationPopular
RefoundAI
fixing-underperforming-teams

Help users identify why a team is struggling and implement a structured recovery plan by addressing leadership gaps, individual performance, and structural misalignments.

Overview

PublisherRefoundAI
Repositorylenny-skills
Skill namefixing-underperforming-teams
Stars
1.3K
Forks
170
Bundled files
2
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Fixing Underperforming Teams 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.
  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/RefoundAI/lenny-skills.git /tmp/lenny-skills
mkdir -p .claude/skills
cp -r /tmp/lenny-skills/skills/fixing-underperforming-teams .claude/skills/fixing-underperforming-teams
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fixing Underperforming Teams 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 Fixing Underperforming Teams 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 Fixing Underperforming Teams 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.

Fixing Underperforming Teams

Diagnose the root cause of dysfunction and take decisive action to restore high performance.

Help the user with fixing underperforming teams using insights from 12 guests and posts across Lenny's Podcast and Newsletter.

How to Help

  1. Diagnose the source - Help the user distinguish between leadership failure, skill gaps, or structural strategy issues.
  2. Identify complicity - Guide the leader in reflecting on how their own patterns are contributing to the team struggles.
  3. Draft an action plan - Structure a sequence of interventions ranging from process changes to talent decisions.
  4. Prepare for hard conversations - Provide scripts and frameworks for delivering direct feedback or handling terminations.

Core Principles

Apply the Enthusiastic Rehire Test

Uri Levine: "Every time that you hire someone new, mark your calendars for 30 days down the road and ask yourself one question, knowing what I know today, would I hire this person? If the answer is no, fire them immediately."

Regularly ask if you would still hire an individual today knowing what you know now. Admitting a hiring mistake early prevents cultural decay.

Distinguish Skill from Will

Anuj Rathi: "There are only three reasons why things do not happen the way you want them to happen as a leader. You can look at a person, and you would say either that person can't do, which is a capability issue, or they won't do, which is a motivation or an alignment issue, or they were not set up to do, which is really your problem that you didn't set up the ways of working now design properly."

Systematically determine if underperformance is a lack of ability (can't do) or a lack of motivation (won't do). This determines whether to coach or move the person.

Align the Five Elements of Change

Bangaly Kaba: "I found this framework travels with me. It's got these five components to it, vision, skills, incentives, resources, action plan, and you need all of those to have change. And then within those buckets you've got to figure out what are the right levers that you need to pull? What are the things that are missing?"

Audit failing initiatives against vision, skills, incentives, resources, and action plans. If any one of these is missing, the turnaround will fail.

Use Goals as Diagnostics

Christina Wodtke: "So, I say OKRs are more of a vitamin, they're not a medicine. So, if you take OKRs and you're like, 'Oh, this will fix everything that's wrong with you.' No, that's not going to happen. It's just going to reveal everything that's wrong with your company."

Treat failed OKRs or goals as signals of underlying strategy or safety issues rather than the root problem itself. Verify strategy before blaming the goal-setting process.

Stop Masking Manager Failures

From "Five principles for successfully managing managers": "Even though the skip leader subconsciously (or even explicitly) knows that the line manager is struggling, confronting the issue head-on is hard—especially as a new skip. So the natural inclination is to quietly solve the issue themselves, pull double duty by taking on part of the line manager’s job, and then provide cover for the direct-report manager’s performance with others."

Resist the urge to do the work of a struggling manager. Covering for them prevents organizational visibility and stops you from fixing the actual leadership gap.

Templates & Frameworks

  • Five Tips for Turning Around an Underperforming Team (Turning around an underperforming team - Issue 17) - A five-step playbook for a PM or leader joining a team with a history of underperformance.
  • Observe, Identify, Share, and Act (OISA) Framework (Turning around an underperforming team - Issue 17) - A four-step framework for making changes on an underperforming team, adapted from the book Nonviolent Communication. It structures how to diagnose problems, bui
  • Team Diagnosis Document (Turning around an underperforming team - Issue 17) - A document template for structuring your findings when diagnosing an underperforming team, referenced in the OISA framework's Identify step.
  • Execution Problem Diagnostic (Shreyas Doshi) - A diagnostic approach for determining whether a recurring execution problem is actually a strategy problem, culture problem, or interpersonal problem
  • Enthusiastic Rehire Test (Rachel Lockett) - A binary question used at Stripe to gain clarity on talent decisions: 'Would you enthusiastically rehire this person for the same role?'
  • Performance Diagnosis Framework (Anuj Rathi) - A mental model for diagnosing why a team member or team is underperforming.
  • The Waterline Model (Molly Graham) - A diagnostic tool for identifying the root cause of team dysfunction by looking below the surface.
  • Playbook: Moving or Letting Go of an Underperforming EM (Turning around an underperforming team - Issue 17) - A step-by-step process for handling an underperforming engineering manager on your team.

See references/artifacts.md for the full list with details.

Questions to Help Users

  • "What factual evidence do you have that distinguishes between a skill gap and a motivation gap in this team?"
  • "How might your own leadership style or unexamined patterns be contributing to the current dysfunction?"
  • "If you had to re-hire every person on this team today, who would you not enthusiastically bring back?"
  • "Is the friction caused by individual personality clashes or by overlapping roles and unclear decision rights?"
  • "Does the team have all five critical elements: vision, skills, incentives, resources, and a clear action plan?"
  • "What is the single most impactful change that would improve this team's velocity immediately?"

Common Mistakes to Flag

  • Ruinous empathy - Withholding direct criticism to avoid temporary discomfort prevents employees from fixing their performance.
  • Pulling double duty - Doing a struggling manager's job for them hides underperformance and prevents the team from actually improving.
  • Overlooking structural causes - Blaming individuals for friction that is actually caused by poorly defined roles or a missing product strategy.
  • Delaying talent decisions - Keeping bad hires too long destroys company culture and drives away your highest performing talent.

Deep Dive

For all 12 sourced insights from 12 guests, see references/guest-insights.md

Related Skills

  • Hiring Product Talent
  • Interviewing Evaluating Candidates
  • Org Design
  • Building Growth Team

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Fixing Underperforming Teams AI skill do?

Help users identify why a team is struggling and implement a structured recovery plan by addressing leadership gaps, individual performance, and structural misalignments.

Why use Fixing Underperforming Teams on TypingMind?

Because you install it once and use it with any model. Fixing Underperforming Teams 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 Fixing Underperforming Teams in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RefoundAI/lenny-skills/tree/main/skills/fixing-underperforming-teams. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Fixing Underperforming Teams?

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 Fixing Underperforming Teams?

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

Is the Fixing Underperforming Teams AI skill free?

Yes. It is published on GitHub by RefoundAI 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 👇