agentleFS
matteotittamatteotitta/genesys-skills/skills/case-study/SKILL.md

case-study

Skill53 starsChanged 5 days agoMITView on GitHub

Writes a customer case study with a challenge, solution and results structure, using verbatim quotes and verified metrics, ready for web or PDF. Use when asked for a case study, customer story, success story or to write up a win.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use audit.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • OpenAISkill

    audit

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before proceeding: customer name + industry known.

    line 55
  2. Distinctive:

    If inputs are missing: ask for customer name, primary challenge, and at least one measurable outcome.

    line 57
  3. Very specific:

    Metrics from source only: Never invent numbers. Mark as [METRIC NEEDED] if not provided.

    line 109
  4. Distinctive:

    Quotes verbatim: Use exact customer words. Don't paraphrase into "better" quotes.

    line 110
  5. Very specific:

    Mark unconfirmed details: Use [CONFIRM: detail] for anything requiring verification.

    line 111
  6. Distinctive:

    Attribution required: Every quote needs name, title, company.

    line 113

“Common” is measured: kept by at least 6 in 10 of the 18 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

Case study

Generate compelling B2B SaaS case studies that transform customer success data into persuasive proof points. Output structured narratives with quantified results, authentic quotes, and visual sections ready for web pages or PDF downloads.


Claude Code triggers

Invoke when user says:

  • "Write a case study"
  • "Create a customer story"
  • "Case study for [customer]"
  • "Customer success story"
  • "Turn this into a case study"
  • "Customer story from [data]"
  • "Case study from interview"
  • "Win story for [customer]"
  • "Success story for [company]"
  • "Reference customer content"

Do NOT invoke when the user wants testimonial quotes only (extract them directly), sales deck slides, a full campaign, or a video script.


Input requirements

Required

InputDescriptionSource
Customer nameCompany being featuredUser provides
Challenge/problemWhat they struggled with beforeInterview, call transcripts, user provides
SolutionHow they used the productInterview, user provides
ResultsQuantified outcomesCustomer data, interview

Optional (improve quality)

InputHow it helps
Customer interview transcriptAuthentic quotes, story details
Win-loss analysisContext on decision drivers
Usage dataSpecific feature adoption metrics
Customer logoVisual asset for header
Contact info (name, title)Attribution for quotes
Industry/verticalVertical-specific framing
TimelineDuration context (implemented in X weeks)

Validation

Before proceeding: customer name + industry known; ≥1 quantified result available; challenge clearly articulated; solution approach understood.

If inputs are missing: ask for customer name, primary challenge, and at least one measurable outcome. Offer to structure interview questions if no transcript — see the premium reference.


Process

The case study runs in 3 phases. Read the premium reference for the full step-by-step (4 extraction steps, 4 structure steps, 3 output steps, plus per-phase checkpoints and the process flowchart).

Phase summary:

  1. Story extraction — transformation arc, quote library (3-5), metrics table, signature moment
  2. Structure development — hero statement, section drafts, metrics callouts, pull quotes
  3. Output generation — pick format (web / PDF / slide), apply template, generate derivatives

Case study structure

Standard sections

SectionPurposeLength
Hero statementCapture attention, summarize transformation1 sentence
Metrics barImmediate proof of results3 numbers
Company overviewContext on customer2-3 sentences
The challengeProblem + pain articulation2-3 paragraphs
The solutionHow they use the product2-3 paragraphs
The resultsQuantified outcomes + quotes2-3 paragraphs
Closing CTANext step for reader1 sentence

Metrics bar format

┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ 3-5x │ │ 40-60 │ │ 20-40% │
│ More creator │ │ Hours saved │ │ Stronger │
│ content/month │ │ per month │ │ performance │
└─────────────────┘ └─────────────────┘ └─────────────────┘

Quote format

"[Verbatim quote, one or two sentences, naming the before and after.]"

— [Full name], [Job title], [Company]

Anti-hallucination guardrails

  1. Metrics from source only. Never invent numbers. Mark as [METRIC NEEDED] if not provided.
  2. Quotes verbatim. Use exact customer words. Don't paraphrase into "better" quotes.
  3. Mark unconfirmed details. Use [CONFIRM: detail] for anything requiring verification.
  4. No invented story beats. The "signature moment" must come from customer data.
  5. Attribution required. Every quote needs name, title, company.

Quality checklist (pre-delivery)

Content

  • Hero statement under 25 words
  • At least 3 quantified metrics
  • At least 3 attributed quotes
  • Challenge clearly articulated
  • Solution tied to specific features
  • Results include before/after comparison

Format

  • All sections complete
  • Metrics bar formatted
  • Quotes properly attributed
  • CTA included
  • Derivatives generated (if requested)

Gotchas

  • Invented metrics. Creates "3x improvement" or "50% reduction" without sourced data → every metric must come from the customer or be marked [UNAVAILABLE]. Never fabricate results.
  • Generic challenge section. Opens with "Company X was struggling with..." instead of specific, named pain → the challenge must reference the actual problem as the customer described it, not a generic industry pain.
  • Missing customer voice. Writes the entire case study in third person without direct quotes → at least 3-5 verbatim customer quotes are needed. These are the most credible parts.
  • No clear "before" snapshot. Jumps straight to the solution without establishing the baseline state → the "before" picture makes the "after" results meaningful. Include specific metrics or processes that existed before.

MCP data integration

Level: 2 — PM Execution (customer-specific pulls)

Pulls fresh

SourceWhat to pullToolWhen
GranolaCustomer-specific call transcriptssearch_meetingsAlways (per-customer story)
SlackCustomer success threadsslack_search_publicAlways (per-customer data)

Fallback (no MCP)

  • User-provided customer interview transcripts
  • Manual success metrics from customer
  • Email threads or shared docs with customer quotes

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.