Interview notes in. A one-page customer story out.
A case study built from your notes on one customer call: headline, summary box, a three-part story, and a claim-by-claim fact check.
Customer wins sit in call notes for months because turning them into a case study feels like a project. When they do get written, they read like a press release about the vendor, with the customer reduced to a quote at the end.
Case Study Writer makes the customer the protagonist. It sorts what they actually said from what you assumed, picks the one result worth leading with, and writes a short before, turning point, and after. Then it traces every claim back to a line in your notes before anyone sees it.
What it produces.
- →A headline built on one specific result
- →A three-line summary box for readers who stop early
- →A short story in the customer's own words with two or three verbatim quotes
- →A fact-check list tying each claim to a source line, with gaps flagged for the customer
- ✦Account managers and customer success leads with notes but no write-up
- ✦Founders who need a proof asset for the sales page
- ✦Marketers building a case study library on a thin budget
- →case-study-writer.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →case-study-writer-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 just got off a 40-minute call with Dana Ruiz, the VP of Operations at a regional freight broker I'll call "Northline Freight." Before switching to our dispatch tool last March, her team spent about 12 hours a week on manual load matching, and she says that dropped to 3 hours. Her notes are pasted below; please draft a one-page case study for our sales team.
Headline: "How Northline Freight cut weekly load matching from 12 hours to 3."
Here is the draft, and the judgment behind it. The result that carries this story is the 12-to-3 drop, so it goes in the headline with the time frame: since last March. The summary box beneath it reads: Northline Freight, a regional freight broker; the problem, manual load matching that consumed 12 hours a week of Dana Ruiz's team; the result, 3 hours. A prospect who stops there still gets the point.
The body should open on Dana's problem, not our product. Lead with what 12 hours a week actually cost her team, using her words from the call, then the moment she decided to act, then the change. Dispatch is a supporting character. Her quotes go in verbatim, one near the top, one at the turning point, one beside the 3-hour figure. Do not polish them into marketing copy.
Two cautions before this reaches the sales team. First, your notes give hours but no dollar value or load volume, so the draft should not claim savings or growth she never stated. If she mentioned either in the pasted notes, I can only use it if it appears there as her statement. Second, "about 12" and "3" are her estimates, so label them as her figures, not audited results.
Next move: send Dana the finished draft with the 3-hour claim tagged [CONFIRM WITH CUSTOMER], and get written approval, including permission to use the Northline name, before sales touches it.
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 will happily tidy your notes and add flattering detail the customer never said. This separates stated facts from implied ones, builds around a single checkable result, keeps quotes verbatim, and ends with a source check so nothing unsupported gets published.
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.