Skip to content
Product · Playbook

One page. The problem, the users, the scope, the measure.

A short requirements doc for one feature, built from your idea and whatever evidence you have, with an out-of-scope list that does real work.

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
100 Playbooks in the catalogDelivered as Claude Skill + plain .mdReviewed Oct 22, 2026Instruction-only · verifiable

Requirements docs get long because they start with the solution. By page four nobody remembers the problem, scope has grown in the gaps, and the success measure is a sentence everyone reads differently.

PRD Lite takes the feature idea, who asked, and your evidence, and writes the problem first, then the users, then three scope lists and a single success measure with a guardrail. Every in-scope item has to trace back to the problem, and guesses are marked as assumptions.

What you get

What it produces.

  • →A one-sentence problem statement with no solution in it
  • →Primary and secondary users with the trigger moment
  • →In scope, out of scope, and later lists with reasons
  • →One success measure, one guardrail, and open questions with owners
Who it's for
  • ✦Product managers who need a doc people will actually read
  • ✦Founders and designers covering the PM role
  • ✦Teams whose feature requests keep growing in meetings
What's included
  • →prd-lite.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →prd-lite-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

Our support team gets about 40 tickets a week from customers who can't find where to export their invoices, and our PM, Dana, keeps adding "just one more" report type in every meeting. I need a short PRD for a single Export Invoices button on the billing page, targeting a March 15 release. Success means cutting those tickets in half.

Problem first, then the fence. The problem is that customers who need an invoice copy cannot find where to get one, which costs about 40 tickets a week. Notice that this describes a findability gap, not a reporting gap. That distinction is your best weapon against Dana's additions: every extra report type makes the button more complex and does nothing for the person who cannot find it today. Write that sentence at the top of the doc and let it do the arguing for you.

For scope, put exactly one thing in: a single Export Invoices button on the billing page, producing one file with one agreed format. Then give the out-of-scope list real weight. Each report type Dana has floated goes there with a one-line reason, such as "different user, different problem, needs its own brief." Anything she still wants after that goes under Later, so it is parked rather than rejected, which makes it easier for her to accept.

For success, the primary measure is weekly export-related tickets falling from roughly 40 to 20. Your guardrail should be button clicks that end in a completed download, because a visible button that fails would shift tickets rather than remove them. Check that the 40 figure comes from tagged tickets and not an estimate, and capture the baseline now.

Next move: send Dana the one-page draft this week and ask her to sign off on the out-of-scope list before design starts, so March 15 stays protected.

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 tends to produce a long template with every heading filled in, including sections you did not need. This method forces the order of problem, users, scope, and measure, keeps it to a page, and removes anything that does not trace to the problem.

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.

More Product Playbooks

Other Playbooks.