A roadmap told as problems being solved, not a list to argue over.
A narrative version of your plan, grouped into two or three themes, with commitment levels and a plain list of what is not happening.
Hand people a feature list and they negotiate each item. The meeting becomes a debate about whether item seven is worth it, and nobody discusses whether the problems are the right ones.
Roadmap Narrative converts each planned item into the problem behind it, groups the problems into themes, and labels each Committed, Planned, or Exploring. It writes a short story per theme and a section on what you are deliberately not doing, then checks that the draft has not slipped back into a list.
What it produces.
- →A two-sentence summary of the direction
- →Two or three problem themes with why-now and a progress signal
- →Commitment labels, with dates only where you confirm them
- →A not-happening section, with reasons
- ✦Product leaders presenting a quarterly plan
- ✦Founders explaining direction to customers or a board
- ✦Teams tired of defending a feature list item by item
- →roadmap-narrative.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →roadmap-narrative-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
What it does with a real question.
I'm the PM for our B2B scheduling product, and I present the Q3 roadmap to our leadership team on June 12. Support tickets about double-booked shifts doubled since March, and our top three customers say onboarding takes over six weeks. Priorities are already set; I need to tell it as a story about those problems.
Open with two problems, not a feature list. For leadership on June 12, your story is that scheduling customers are losing trust in two places: during daily use, where double-booked shifts have doubled in support volume since March, and at the start, where your top three accounts wait over six weeks to get live. Those two facts carry the room. Name each as a theme in plain language, such as "Schedules we cannot trust" and "Too slow to get started," and hang every Q3 item under one of them.
I'd mark the double-booking theme as Committed, because the ticket trend is hard evidence and a fix can be tied to a visible measure: fewer tickets, measured against the March baseline. Onboarding deserves more care. Say plainly whether Q3 shortens it or only starts the work, and give no target number you cannot defend. Dates belong in the story only where you have confirmed them.
The part most presenters skip is the deliberate omissions. Take two or three things leadership will expect, name them, and give the reason each waits. Disappointment you head off now will not turn into an argument in July.
Your next move today: write the two-sentence opening summary and read it aloud. If a feature name appears in it, move that feature to an appendix and restate the sentence as a problem.
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.
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
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude tends to polish the list into prose and keep every feature in the story. This starts from problems, caps the themes, separates commitment from exploration, and moves features to an appendix.
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.