Running Meetings logo

Running Meetings

OrganizationPopular
RefoundAI
running-meetings

Help users master the art of facilitating productive, decision-oriented meetings that unblock teams, strengthen interpersonal bonds, and accelerate shipping velocity.

Overview

PublisherRefoundAI
Repositorylenny-skills
Skill namerunning-meetings
Stars
1.4K
Forks
175
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 Running Meetings 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/RefoundAI/lenny-skills/tree/main/skills/running-meetings
  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/running-meetings .claude/skills/running-meetings
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Running Meetings 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 Running Meetings 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 Running Meetings 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.

Running Effective Meetings

Transform calendars from soul-crushing time-sinks into high-velocity alignment machines.

Help the user with running effective meetings using insights from 12 guests and posts across Lenny's Podcast and Newsletter.

How to Help

  1. Audit current meetings - Analyze the purpose and frequency of existing recurring sessions to ensure they solve specific problems that cannot be addressed asynchronously.
  2. Design the agenda - Structure sessions with clear objectives, silent reading periods, and psychological safety rituals to maximize participation.
  3. Facilitate real-time alignment - Use active listening and synthesis techniques to ensure stakeholders feel heard and blockers are surfaced.
  4. Streamline post-meeting debt - Implement rituals to finalize action items and documentation during the meeting rather than after it.

Core Principles

Separate discovery from decision

Annie Duke: "People generally think the purpose of a meeting is for three things, discover, discuss, decide. The only thing that's ever supposed to happen in a meeting is the discussion part."

Complete the information gathering phase asynchronously before the meeting starts so synchronous time is reserved for high-value debate and final choices.

Prioritize psychological safety

From "Ideal sprint length, designer vs. PM roles, running PM team meetings, running post-mortems, best product/executive coaches, and much more": "Our PM team has a section carved out for “what feels hard [harder than it should be]?” The purpose of this section is to discuss sticking points up and down the stack: troubleshooting comms with Team X; doing a teardown of a PRD that has raised unexpected questions and gotten “stuck”; trying on versions of a Vision/Strategy."

Create a dedicated space for vulnerability where team members feel safe to surface what is hard and seek help from their peers.

Solve for administrative debt

From "Product manager is an unfair role. So work unfairly.": "Instead of adding action items from meetings to a to-do list, do the action items live in the meeting. With everyone watching. While screensharing."

Complete small tasks and alignment rituals during the meeting to prevent the accumulation of follow-up work and ensure immediate momentum.

Validate before aligning

From "A PM’s guide to influence": "People often won’t listen to you until they feel that you’ve fully heard them. When people don’t think you deeply understand their POV, they often become obsessed with repeating their points more forcefully instead of hearing yours."

Use active listening and playback techniques to ensure stakeholders feel heard, which prevents defensive responses that block consensus.

Audit for intentionality

From "Leading a PM team meeting - Issue 19": "Don’t do this meeting just to do it. Make certain that adding (or continuing this meeting) is consistently worth everyone’s time. What problem are you trying to solve?"

Only maintain recurring meetings that solve a specific problem that cannot be addressed more efficiently through other channels.

Templates & Frameworks

  • PM Team Meeting Agenda Template (Ideal sprint length, designer vs. PM roles, running PM team meetings, running post-mortems, best product/executive coaches, and much more) - A structured weekly PM team meeting agenda designed to increase transparency, psychological safety, and PM output
  • Dory and Pulse (My favorite decision-making frameworks) - A two-part meta-framework for supercharging real-time decision-making in meetings by equalizing voices and removing groupthink, with 14 documented variations.
  • Note-and-Vote Decision-Making Technique (Introducing the Foundation Sprint: From the creators of the Design Sprint) - A fast group decision-making method that prevents groupthink by requiring individual silent thinking before group discussion
  • Live-in-Meeting Action Item Checklist (Product manager is an unfair role. So work unfairly.) - A list of action items PMs can complete live during meetings while screensharing, instead of adding them to a post-meeting to-do list.
  • WWW (Who/What/When) Action Clarity Test (Introducing the GAIN framework for feedback: an evidence-based approach to giving feedback that people love, appreciate, and act on) - A simple three-word test to ensure action items from any meeting or conversation are actually actionable
  • Meeting Effectiveness Checklist for PMs (Startup PM vs. big company PM) - A step-by-step checklist for running productive meetings as a product manager
  • PM Team Meeting Frequency Guide (Leading a PM team meeting - Issue 19) - Guidelines for choosing the right cadence for PM team meetings based on team size
  • Exquisite Exec Team Meeting Format (Matt Mochary) - A meeting structure designed to reduce a 3-hour meeting to 45 minutes by using asynchronous pre-reads.

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

Questions to Help Users

  • "What is the specific problem this meeting is intended to solve?"
  • "Could this information be communicated more effectively via a short video or asynchronous document?"
  • "Who is the absolute minimum group of people needed to reach a decision?"
  • "What artifacts or data must participants review before the meeting begins?"
  • "How will you ensure that every participant feels safe enough to share their honest perspective?"
  • "What ritual will you use to finalize action items before everyone leaves the room?"

Common Mistakes to Flag

  • Status report syndrome - Using synchronous time for one-way information sharing that could have been a dashboard or email.
  • Ambiguous ownership - Ending a meeting without a clear owner and deadline for every discussed action item.
  • Ignoring the human element - Focusing solely on the tactical agenda while neglecting team connection and psychological safety.
  • Passive facilitation - Allowing the loudest voices to dominate the conversation rather than using structured rituals to surface all perspectives.

Deep Dive

For all 19 sourced insights from 12 guests, see references/guest-insights.md

Related Skills

  • Product Reviews
  • Executive Communication
  • Managing Up
  • Written Communication

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 Running Meetings AI skill do?

Help users master the art of facilitating productive, decision-oriented meetings that unblock teams, strengthen interpersonal bonds, and accelerate shipping velocity.

Why use Running Meetings on TypingMind?

Because you install it once and use it with any model. Running Meetings 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 Running Meetings in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RefoundAI/lenny-skills/tree/main/skills/running-meetings. 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 Running Meetings?

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 Running Meetings?

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

Is the Running Meetings 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 👇