agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/case-study-writer/SKILL.md

case-study-writer

Skill13 starsChanged 21 days agoMITView on GitHub

Use this skill when you need a B2B customer case study or success story that sales can use: \"write a case study\", \"turn this customer interview into a story\", \"customer success story for our website\", \"one-pager for sales\". Plans the interview, structures the story (before, trigger, decision, rollout, results, what's next), writes it with real numbers and quotes, and produces versions for the website, a sales one-pager, a cold email paragraph and a LinkedIn post. Every claim is approved by the customer.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this when a customer has a result worth sharing.

    line 16
  2. Distinctive:

    MUST get customer approval for name, quotes and numbers before publishing.

    line 62
  3. Distinctive:

    MUST state how and over what period results were measured.

    line 63
  4. Distinctive:

    NEVER round up results or combine customers into one story.

    line 64
  5. Distinctive:

    NEVER publish an anonymised story with details that identify the customer anyway.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Use this when a customer has a result worth sharing. The best case studies read like a story a peer would tell, with the buyer's doubts left in.

Inputs

  • Interview transcript or notes with the customer (or run the guide below).
  • Results data: before and after numbers, time frames.
  • What the customer has approved for publication: name, logo, quotes, numbers.

The play

1. Interview for the story, not the praise

Ask:

  • What was happening before? What did it cost you?
  • What made you look for a change then?
  • What else did you consider? What almost stopped you?
  • How did the rollout actually go, including the bumps?
  • What changed, in numbers, and how do you measure it?
  • What would you tell a peer considering it?

2. Structure it

  1. Headline: the result, with the number. "How Northwind filled 15% more chairs in 90 days."
  2. Snapshot: company, size, use case, top 3 results.
  3. Before: the situation and its cost, in their words.
  4. Trigger and decision: why now, what they compared, why they chose.
  5. Rollout: what it took, honestly.
  6. Results: numbers with time frames and how they were measured.
  7. What's next.

3. Use quotes well

Two to four quotes, each doing a job: the pain, the decision, the result. Edit for length, never for meaning, and get approval on the final wording.

4. Make the versions

  • Website: 600-900 words with the structure above.
  • Sales one-pager: snapshot, before and after, three results, one quote.
  • Cold email paragraph: one sentence of before, one of after.
  • LinkedIn post: the story in 150 words with the turning point.

What good looks like

  • The headline number is specific, time-bound and approved.
  • The "before" is vivid enough that a prospect recognises themselves.
  • Doubts and bumps are included; they make the result credible.
  • The common mistake is a page of praise ("They're a great partner!") with no numbers and no story.

Rules

  • MUST get customer approval for name, quotes and numbers before publishing.
  • MUST state how and over what period results were measured.
  • NEVER round up results or combine customers into one story.
  • NEVER publish an anonymised story with details that identify the customer anyway.

Example prompts

  • "Turn this interview transcript with Northwind into a case study and a one-pager."
  • "Write interview questions for a customer who cut onboarding time by half."
  • "Make a cold email paragraph and a LinkedIn post from our Contoso case study."

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free