Skip to content
People · Playbook

Sixty minutes. Three actions. One owner and one date each.

A minute-by-minute retrospective agenda that moves from silent input to voted themes to owned changes.

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
100 Playbooks in the catalogDelivered as Claude Skill + plain .mdReviewed Nov 11, 2026Instruction-only · verifiable

Most retros collect fifteen ideas, agree with all of them, and assign none. The same complaints return next quarter, the loudest people dominate, and the notes are never opened.

Team Retro builds the hour backward from the actions. It starts with last time's follow-through, uses silent writing so quieter people contribute, narrows to three themes, and ends by naming one owner and one date per change. It also drafts the follow-up message.

What you get

What it produces.

  • →A timed sixty-minute agenda with an output for every block
  • →A framing question and ground rules for the room
  • →Three owned actions with dates and a review point
  • →A follow-up message ready to send within a day
Who it's for
  • ✦Team leads whose retros end in a list nobody owns
  • ✦Managers running a first retro after a project or release
  • ✦Remote teams that need the structure written down
What's included
  • →team-retro.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →team-retro-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
  • →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
Delivery
Emailed within 60 seconds of payment
Compatibility
Claude, ChatGPT, Gemini, any LLM
License
One-time purchase, yours to keep
Sample output

What it does with a real question.

The brief

I lead a team of eight engineers and two designers at a mid-size logistics software firm. We shipped our checkout redesign on March 14, three weeks late, and the last six weeks were rough. Two senior engineers talk most of the time in meetings, and our past retros produced nothing. Can you run a sixty-minute retro for us?

Start with the closing block, then work backward. Your past retros failed at the end, so the sixty minutes should be built to finish with exactly three actions, each with one named owner and a date. Anything that cannot be turned into a change your team controls goes on a separate list for you to escalate. For a three-week slip, the date pressure from above probably belongs there.

Ten people, two of them dominant, means no one speaks first. Spend the opening on last quarter's actions (if any exist) and five minutes of silent writing: what worked, and what cost us time or quality. Everyone writes in a shared doc, so the six quieter voices land on the page before the senior engineers can frame the discussion. Then group the notes and give each person three votes. Take only the top three themes, not the top seven. You will likely see scope changes after design handoff, late integration testing, and the unclear call on when to cut features.

Frame every theme as "what happened," not "who caused it." Spend minutes thirty to fifty on one concrete change per theme, testing each for specificity and whether you will know by a set date that it worked. Hold the last ten minutes for owners and dates, read aloud, with each person stating one thing they will do differently.

Next move: send the silent-writing prompt to the team tomorrow, so the notes exist before you walk in.

The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.

Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.

One-time purchase
$12.99
Yours to keep
No subscription · free updates within v1.x

Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable

Questions

Before you buy.

How is this different from just asking Claude directly?

Asked cold, Claude suggests a generic start-stop-continue format. This builds a complete sixty-minute plan around your team's period and events, caps the output at three actions, and tests each action for ownership and a review date.

How is this different from a Tool?

Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.

Will this work with ChatGPT, Gemini, and other LLMs?

Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.

Can I share this with my team?

It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.

What if it doesn't work for me?

If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.

People Playbooks are structuring aids. They are not legal or HR advice. Employment law differs between the US and the UK and between states and countries, so check anything touching dismissal, performance plans, pay, or protected characteristics with a qualified HR professional or employment lawyer.

More People Playbooks

Other Playbooks.