Retrospective Stinger logo

Retrospective Stinger

Organization
legioncodeinc
retrospective-stinger

Facilitate engineering retrospectives. Use for format selection, safety pre-check, facilitation, or action-item follow-through. Read README.md for the guide map.

Overview

Publisherlegioncodeinc
Repositoryvibe-coding-tools
Skill nameretrospective-stinger
Stars
94
Forks
44
Bundled files
11
LicenseAGPL-3.0-or-later
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.

  • 11 bundled files

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

  • Open source

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

Installation

Install the Retrospective Stinger 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/legioncodeinc/vibe-coding-tools/tree/main/plugins/business-and-product-tools/skills/retrospective-stinger
  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/legioncodeinc/vibe-coding-tools.git /tmp/vibe-coding-tools
mkdir -p .claude/skills
cp -r /tmp/vibe-coding-tools/plugins/business-and-product-tools/skills/retrospective-stinger .claude/skills/retrospective-stinger
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Retrospective Stinger 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 Retrospective Stinger 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 Retrospective Stinger 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.

retrospective-stinger

The retrospective surface end-to-end: choosing the right format, creating the conditions for honesty, facilitating the session, and enforcing follow-through. Built from 2026 research into what makes retros actually change behavior rather than generate a board no one reads.

The most important finding from the research: only 50% of retro action items ever get completed (survey of 419 professionals across 5 countries, 2026-05-15). The format is almost irrelevant if no one does anything differently next sprint. This stinger is calibrated around the follow-through problem, not the facilitation aesthetics problem.

When this stinger applies

Load when retrospective-wasp-drone is invoked. Trigger on:

  • "Run a retro" / "plan our retrospective" / "help us do a sprint retrospective"
  • "Which retro format should we use?"
  • "Our retros produce no change" / "action items never get done" / "retro theater"
  • "How do we do an async retro?" / "remote retrospective"
  • "We need better psychological safety in our retros"
  • "Review last sprint's action items"

Do NOT load for:

  • Incident postmortems (different cadence, participants, and root-cause methodology)
  • Sprint planning or backlog grooming
  • OKR-setting or strategy planning

First action when this stinger is loaded

Read in this order:

  1. guides/00-principles.md: the philosophy: retros are behavior-change instruments, not complaint sessions. The output is what the team does differently; measure follow-through rate, not participation.
  2. guides/01-formats.md: the format matrix: nine formats with best-for context, time budget, and selection logic.
  3. guides/02-psychological-safety.md: the safety gate: Edmondson 7-item scale, the low-safety mitigation playbook, the anonymity bridge technique.

Then walk the remaining guides based on the task:

  • Facilitating a session: guides/03-facilitation.md
  • Action-item review or capture: guides/04-action-items.md
  • Async or remote team: guides/05-async-retro.md

Critical directives

  • Never skip the safety pre-check. A retro run without minimum psychological safety produces theater. Surfacing the gap is more valuable than running a polished session. See guides/02-psychological-safety.md.
  • Always capture action items with owner and deadline. The five structural failure modes: no owner, no deadline, too large, invisible on the backlog, no accountability loop. See guides/04-action-items.md.
  • Open every retro with a follow-through review of the previous retro's actions. Teams that skip this signal that action items are optional. See guides/04-action-items.md.
  • Name the format and explain the selection. Teams that understand why a format was chosen are more engaged and can adapt it without the Drone next time. See guides/01-formats.md.
  • Frame async as a first-class option, not a fallback. Async retros see 42% higher participation from introverts. See guides/05-async-retro.md.
  • Use the 3-question filter during live sessions. Before any action item leaves the board: Who owns this? When does it close? What does done look like? See guides/04-action-items.md.

Folder layout

retrospective-stinger/
+- SKILL.md                         (this file — master index)
+- README.md                        (one-page human overview)
+- guides/
|  +- 00-principles.md              (the retro-as-behavior-change philosophy)
|  +- 01-formats.md                 (format matrix: 9 formats with selection logic)
|  +- 02-psychological-safety.md    (Edmondson scale, safety gate, mitigation playbook)
|  +- 03-facilitation.md            (agenda template, time-boxing, synthesis, closing ritual)
|  +- 04-action-items.md            (SMART+, 3-question filter, backlog placement, accountability loop)
|  +- 05-async-retro.md             (4-day timeline, tool options, async facilitation patterns)
+- examples/
|  +- happy-path-retro.md           (end-to-end sync retro with a mid-maturity team)
|  +- async-retro-example.md        (end-to-end async retro for a distributed team)
+- templates/
|  +- action-items.md               (the four-component action item template)
|  +- facilitation-plan.md          (blank agenda the Drone fills in per-retro)
+- reports/
|  +- README.md                     (how retro output files accumulate over time)
+- research/                        (owned by scripture-historian; read-only for this stinger)
   +- research-summary.md
   +- index.md
   +- internal/
   +- external/

Forged by stinger-forge for retrospective-wasp-drone. Part of the Wasp Nest.

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 Retrospective Stinger AI skill do?

Facilitate engineering retrospectives. Use for format selection, safety pre-check, facilitation, or action-item follow-through. Read README.md for the guide map.

Why use Retrospective Stinger on TypingMind?

Because you install it once and use it with any model. Retrospective Stinger 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 Retrospective Stinger in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/business-and-product-tools/skills/retrospective-stinger. 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 Retrospective Stinger?

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 Retrospective Stinger?

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

Is the Retrospective Stinger AI skill free?

Yes. It is published on GitHub by legioncodeinc under the AGPL-3.0-or-later 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 👇