Case study builder
Create customer case studies in sales-ready format — Challenge→Solution→Results structure, before/after metrics, quote integration, two-length formats (1-page summary + full version). Use when creating case studies, customer success stories, proof content, or sales collateral. Triggers on: "case study", "customer story", "success story", "proof content", "customer example", "results story", or any request to document customer outcomes.From its SKILL.md
npx -y skills add LeadMagic/gtm-skills --skill case-study-builderAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
6.7 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it
Case Study Builder
Overview
A case study is the most versatile proof asset in B2B. It proves your product works in someone else's hands. This skill produces sales-ready case studies: one-page for quick sharing, full version for late-stage deals, always with specific metrics and real quotes.
The golden rule: a case study without numbers is a testimonial. Every case study must answer "what changed, and by how much?"
Authoritative Foundations
- Challenge-Solution-Results — Shapes deliverables for this skill — A case study is the most versatile proof asset in B2B.
- Before-After-Bridge — Shapes deliverables for this skill — A case study is the most versatile proof asset in B2B.
- Nielsen Norman Group — Usability Heuristics — Usability Heuristics
When to Use
- "Create a case study about [customer]"
- "Write a customer success story"
- "Build proof content for sales"
- "Document customer results"
- "Create a case study for our website"
- "I need customer proof for a deal"
Step-by-Step Process
Phase 1: Information Gathering
Collect from the customer:
- Company profile (industry, size, use case)
- Challenge before your product (what was broken, what it cost)
- Solution (how they use your product, implementation timeline)
- Results (specific metrics — "reduced X by Y%" not "improved efficiency")
- Customer quote (in their words, not yours)
- Permission to use their name and logo
Phase 2: Structure
1-Page Summary (for quick sharing):
┌──────────────────────────────────────────┐
│ CASE STUDY: [Customer Name] │
│ │
│ [Customer logo] │
│ Industry: [X] | Size: [Y employees] │
│ │
│ THE CHALLENGE │
│ [2-3 sentences. What was broken? │
│ What did it cost?] │
│ │
│ THE SOLUTION │
│ [2-3 sentences. How they use us. │
│ Implementation timeline.] │
│ │
│ THE RESULTS │
│ • [Metric 1 — specific number] │
│ • [Metric 2 — specific number] │
│ • [Metric 3 — specific number] │
│ │
│ "[Customer quote — in their words]" │
│ — [Name, Title] │
│ │
│ [CTA: Book a demo / See full case study] │
└──────────────────────────────────────────┘
Full Version (for late-stage deals):
Add: detailed implementation story, additional metrics, second quote from a different stakeholder (e.g., end user + executive), "what's next" section showing expansion plans, and a comparison table (before vs after).
Phase 3: Writing Guidelines
- Lead with the result. Not "Company X uses our product." — "Company X reduced time-to-close by 40% in 90 days. Here's how."
- Customer's words, not yours. Use their language. If they say "it was a nightmare," say "it was a nightmare" — not "they faced significant challenges."
- Specific over impressive. "Saved $247,000 annually" beats "drove significant cost savings." Specific numbers build credibility.
- One story, one takeaway. Don't try to prove everything. Pick the strongest story and tell it well.
Phase 4: Approval and Distribution
- Customer approval: send draft, let them edit quotes, get written permission.
- Sales distribution: add to CRM, sales portal, pitch deck, proposal templates.
- Marketing distribution: website, social, email nurture, paid retargeting.
Output Format
Two versions: 1-page summary (for email, LinkedIn, quick sharing) and full version (for late-stage deals, website, sales portal).
Quality Check
- Specific, named metrics (not "improved efficiency")
- Customer quote in their words (not marketing language)
- Challenge → Solution → Results structure
- Customer name and logo included (with permission)
- 1-page version scannable in 30 seconds
- Full version has implementation detail
- Customer has approved final text
- CTA present on both versions
Common Pitfalls
-
No metrics. "They love our product" is a testimonial, not a case study. Every case study needs specific, named numbers.
-
Marketing language in quotes. "We leveraged their best-in-class solution" — no human talks like this. Use their actual words.
-
Too many results. 3-4 metrics max. Pick the strongest ones. More metrics dilute the impact of each.
-
No customer approval. Never publish a case study without written permission. Include the approval step in your process.
-
One format for everything. Sales needs a 1-pager. Marketing needs a story. Website needs both. Build both formats.
Execution Artifacts
references/framework-notes.md— named frameworks, citation anchors, and operating assumptionstemplates/output-template.md— copy-paste deliverable structure for the userscripts/check-output.py— local checklist validator for required sections This skill includes lightweight artifacts the agent can load on demand: Use the artifacts when the user asks for an implementation-ready deliverable, a repeatable workflow, or a quality check rather than generic advice.
Related Skills
- customer-marketing: Customer advocacy program
- sales-enablement: Sales collateral package
- roi-calculator: Quantify results for case studies
What ships with it: 3 files
2.3 KB alongside SKILL.md, 1 of them executable
references/
- framework-notes.md793 B
scripts/
- check-output.pyruns659 B
templates/
- output-template.md879 B
Gives 0 of the 12 instructions most learn study skills give in ~1.3k tokens
Counted across 545 of the 593 authors here whose files we hold, read 2026-09-06
- Treat the current directory as a teaching workspacein 20 of 545, across 17 files
- Teach knowledge first then practice skillsin 19 of 545, across 16 files
- Design lessons which build long-term retentionin 15 of 545, across 12 files
- Save each lesson as a self-contained HTML filein 15 of 545, across 12 files
- Question the user on why they want to learn thisin 15 of 545, across 12 files
- Reuse components from the assets directoryin 14 of 545, across 11 files
- Never trust your parametric knowledgein 13 of 545, across 10 files
- Record user preferences in NOTES.mdin 11 of 545, across 8 files
- Ground all teaching in the MISSION.md documentin 11 of 545, across 8 files
- Save each lesson to the lessons directoryin 8 of 545
- Question the user if the mission is unclearin 7 of 545
- Gather primary sources onlyin 7 of 545, across 4 files
Said here and by no other author read
- Collect company profile and challenge
- Incorporate customer quotes
- Structure using challenge solution results
- Lead with the result
- Keep to specific numbers
- Build both 1-page and full versions
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.