Retro Facilitator logo

Retro Facilitator

Community
Mehdibargach
retro-facilitator

Facilitate a team retrospective. Generate a retro board with prompts (4Ls, Start-Stop-Continue, Sailboat formats) or synthesize retro notes into grouped themes and prioritized action items.

Overview

PublisherMehdibargach
Repositoryclaude-code-pm-skills
Skill nameretro-facilitator
Stars
97
Forks
38
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Retro Facilitator 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/Mehdibargach/claude-code-pm-skills/tree/main/skills/retro-facilitator
  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/Mehdibargach/claude-code-pm-skills.git /tmp/claude-code-pm-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-pm-skills/skills/retro-facilitator .claude/skills/retro-facilitator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Retro Facilitator 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 Retro Facilitator 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 Retro Facilitator 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.

Retro Facilitator

Two modes: GENERATE a retro board with prompts, or SYNTHESIZE raw retro notes into themes and actions. Retros without actions are just venting sessions.

Process

Mode Detection

  • If the input is a format name (4Ls, start-stop-continue, sailboat) → GENERATE mode
  • If the input is pasted notes, bullet points, or raw feedback → SYNTHESIZE mode
  • If unclear, ask.

GENERATE Mode

  1. Select format. Parse which retro format the user wants.
  2. Create sections. Build the board structure for that format with section descriptions.
  3. Add seed prompts. 2-3 starter questions per section to get the team thinking.
  4. Add facilitation tips. How to run each section effectively.
  5. Suggest time allocation. Based on a 60-minute retro by default.

SYNTHESIZE Mode

  1. Ingest notes. Read all raw input — sticky notes, bullet points, free-form text.
  2. Group into themes. Cluster related items. Name each theme clearly.
  3. Prioritize themes. Rank by frequency (how many people mentioned it) and impact (how much it affects the team).
  4. Generate action items. Each action must have: what, who, and by when.
  5. Identify patterns. If context from previous retros is available, flag recurring themes.

Output Format

GENERATE Mode

## Retro Board: [Format Name]
**Duration:** 60 minutes | **Team size:** [adjust if specified]

### Format Overview
[2-3 sentences explaining this retro format and when it works best.]

### Section 1: [Name]
**What goes here:** [description]
**Seed prompts:**
- [Specific question to spark discussion]
- [Specific question to spark discussion]
- [Specific question to spark discussion]
**Facilitation tip:** [How to run this section]

### Section 2: [Name]
[same structure]

### Section 3: [Name]
[same structure]

### Section 4: [Name] (if applicable)
[same structure]

### Time Allocation
| Phase | Duration | Notes |
|-------|----------|-------|
| Check-in | 5 min | Quick round — one word for the sprint |
| Individual writing | 10 min | Silent, everyone adds stickies |
| Group & discuss | 25 min | Read, cluster, vote on top themes |
| Action items | 15 min | Assign owners and deadlines |
| Close | 5 min | One takeaway per person |

### Facilitation Tips
- [Tip about creating psychological safety]
- [Tip about keeping discussion productive]
- [Tip about ensuring actions get assigned]

SYNTHESIZE Mode

## Retro Synthesis: [Date/Sprint]

### Themes (ranked by frequency + impact)

#### Theme 1: [Name] (mentioned by [N] people)
- [Grouped item]
- [Grouped item]
- [Grouped item]
**Root cause:** [One sentence hypothesis]

#### Theme 2: [Name] (mentioned by [N] people)
- [Grouped item]
- [Grouped item]
**Root cause:** [One sentence hypothesis]

#### Theme 3: [Name]
[same structure]

### Action Items
| # | Action | Owner | Due | Theme |
|---|--------|-------|-----|-------|
| 1 | [Specific, actionable task] | [person] | [date] | Theme 1 |
| 2 | [Specific, actionable task] | [person] | [date] | Theme 2 |
| 3 | [Specific, actionable task] | [person] | [date] | Theme 1 |

### Patterns (if prior retro context available)
- **Recurring:** [Theme that keeps appearing] — previous actions may not have been effective
- **New:** [Theme appearing for the first time] — investigate
- **Resolved:** [Theme from last retro that did not appear] — actions worked

### Team Health Signal
[One sentence summary: is the team trending better, worse, or stable based on these notes?]

Supported Formats

4Ls

  • Loved: What went well that we want to keep doing
  • Learned: What we discovered or gained insight on
  • Lacked: What was missing or insufficient
  • Longed For: What we wish we had

Start-Stop-Continue

  • Start: What should we begin doing
  • Stop: What should we stop doing
  • Continue: What is working and should keep going

Sailboat

  • Wind (propelling us): What is pushing us forward
  • Anchor (holding us back): What is slowing us down
  • Rocks (risks ahead): What could hurt us
  • Island (destination): Where we are trying to get to

Rules

  • In GENERATE mode, seed prompts must be specific to the team context if provided. Generic prompts like "what went well?" waste everyone's time.
  • In SYNTHESIZE mode, every theme must have at least one action item. Themes without actions are just observations.
  • Action items must be specific and assigned. "Improve communication" is not an action. "Schedule a 15-min daily sync for the next 2 weeks — owned by [person]" is.
  • Do not create more than 5 themes when synthesizing. If there are more, merge the smaller ones.
  • Maximum 5 action items. Teams that leave retros with 10 actions complete zero of them.
  • Always include a team health signal in SYNTHESIZE mode. The point of retros is continuous improvement — track the direction.
  • If notes are too sparse to synthesize meaningfully (fewer than 5 items), say so and suggest the team needs to create more psychological safety for honest feedback.

Frequently asked questions

What does the Retro Facilitator AI skill do?

Facilitate a team retrospective. Generate a retro board with prompts (4Ls, Start-Stop-Continue, Sailboat formats) or synthesize retro notes into grouped themes and prioritized action items.

Why use Retro Facilitator on TypingMind?

Because you install it once and use it with any model. Retro Facilitator 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 Retro Facilitator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Mehdibargach/claude-code-pm-skills/tree/main/skills/retro-facilitator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Retro Facilitator?

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 Retro Facilitator?

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

Is the Retro Facilitator AI skill free?

It is published on GitHub by Mehdibargach. Check the repository for licensing terms. 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 👇