Case Study Builder logo

Case Study Builder

Community
BrianRWagner
case-study-builder

Turn client wins into formatted case studies for proposals, social proof, and sales conversations. Use when someone needs to document results, build credibility, or create reusable proof assets.

Overview

PublisherBrianRWagner
Repositoryai-marketing-claude-code-skills
Skill namecase-study-builder
Stars
449
Forks
103
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by BrianRWagner on GitHub. Read the source before you install it.

Installation

Install the Case Study Builder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/BrianRWagner/ai-marketing-claude-code-skills/tree/main/case-study-builder
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/BrianRWagner/ai-marketing-claude-code-skills.git /tmp/ai-marketing-claude-code-skills
mkdir -p .claude/skills
cp -r /tmp/ai-marketing-claude-code-skills/case-study-builder .claude/skills/case-study-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Case Study Builder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Case Study Builder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Case Study Builder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Case Study Builder

Everyone wants social proof. Nobody makes time to create it. You finish a project, the client's happy, you move on — and six months later you're in a sales call with nothing to show.

This skill fixes that. Give me the raw details. I'll produce three formats you can use immediately.


Mode

Detect from context or ask: "Quick writeup, full case study, or full asset package?"

ModeWhat you getBest for
quick1 format: paragraph summary for proposalsFast social proof, proposal inserts
standard3 formats: proposal blurb, social proof pull-quote, sales storyActive pitching, LinkedIn, website
deep3 formats + blog-ready case study + FAQ variant + campaign assetsContent marketing, SEO, sales enablement

Default: standard — use quick if they say "just need something fast." Use deep if they want to turn the win into a marketing asset.


Context Loading Gates

Before generating anything, collect all 8 fields:

FieldWhat to Collect
1. ClientIndustry, company size/stage, named or anonymized?
2. BeforeWhat was broken or painful? Any numbers?
3. ActionsWhat did you specifically do? Scope, timeline, role
4. AfterREQUIRED: at least one specific number
5. TimelineHow long to achieve the result?
6. QuoteDirect client quote if available
7. NamingCan we name the client, or must we anonymize?
8. Use caseWhere will this be used? (proposals / website / LinkedIn)

Outcome Extraction Protocol — enforced on Field 4:

If the user says "results were good" or "things improved," stop and ask:

"I need at least one number to make this credible. Pick one:

  • Revenue change (e.g., 'closed 3 new clients worth $15K')
  • Time saved (e.g., 'cut from 10 hours to 2 hours/week')
  • Lead volume (e.g., 'went from 0 to 5 inbound leads/month')
  • Rough estimate is fine — it doesn't have to be exact."

Do not draft until Field 4 has at least one number.


Phase 1: Situation Analysis

Before drafting, reason through:

  1. Result strength: Is the outcome a Tier 1 (hard metric), Tier 2 (soft metric), or Tier 3 (proxy)? This determines how confident the language should be.
  2. Hero check: Is the story told from the client's perspective, or yours? Client = hero, you = guide.
  3. Tension check: What made this hard? Without a challenge, there's no story — just a list.
  4. Format match: Which use case did they specify? That determines which format to optimize.

Tier system for results language:

TierTypeExampleLanguage
1Hard metric"Revenue +40%"State directly
2Soft metric"Team finally aligned""For the first time in years..."
3Proxy metric"Enabled Series A close""Contributed to..."
4Directional"Noticeable improvement""Significant improvement in..."

Phase 2: The Hero Principle

The client is the hero. You are the guide.

Before writing, flip the framing:

❌ Wrong: "I built a content system that generated leads." ✅ Right: "Sarah went from scrambling to fill her pipeline to getting 3 inbound inquiries per week — all from a content system we built in 6 weeks."

Every format should be written from what the CLIENT experienced, not what YOU delivered.


Phase 3: Generate Three Formats

Format 1: Two-Liner (Proposals & Bios)

Formula: [What was done] + [scale/scope] + [for who] + [result or timeframe]

[Strong action verb] [what was delivered] for [specific client descriptor].
[Outcome metric] in [timeframe].

Example:

Built a full content system for a Series B SaaS founder with no marketing team. 0 to 3 inbound leads/week in 6 weeks.


Format 2: Story Version (LinkedIn & Sales Calls)

Structure — 4 paragraphs, 150–250 words:

**Set the scene:** [Their situation when you arrived — 2-3 sentences with stakes]

**Show the complexity:** [What made this hard — 2-3 sentences]

**What happened:** [Specific actions taken — no feature lists, just moves]

**What changed:** [Outcome — the number + the transformation]

Format 3: Full Case Study (Website & Portfolio)

markdown
# Case Study: [Client Name or Descriptor]

## The Challenge
[2-3 paragraphs: situation, stakes, what wasn't working]

## The Approach
[Phases or steps — what happened and in what order]

## The Results
[Metrics, before/after comparison, named outcomes]

## Key Details
- Client: [Named or "A [descriptor] company"]
- Industry: [Sector]
- Timeline: [Duration]
- Scope: [What was delivered]

## What Made This Different
[Unique angle, unexpected obstacle, or pivotal insight]

## Client Quote
> "[Testimonial — or placeholder if not yet collected]"
> — [Name], [Title]

Phase 4: Self-Critique Pass (REQUIRED)

After generating all three formats, evaluate:

Two-liner:

  • Does it have a specific number? (Not "improved results" — a real metric)
  • Is it 2 sentences or fewer?
  • Would someone scanning a proposal stop and read it?

Story version:

  • Is the client the hero (not the author)?
  • Is there genuine tension — something that made this hard?
  • Does the closing paragraph include the key metric?

Full case study:

  • Does the Results section lead with numbers?
  • Is the Challenge section specific enough that a similar prospect recognizes their situation?
  • Is the client quote (or placeholder) present?

Flag any failure: "The story version has no tension — add one obstacle or unexpected challenge before the 'What happened' paragraph."


Phase 5: Distribution Plan

FormatBest locationsWhen to use
Two-linerProposals, email bios, LinkedIn About sectionAny sales context
StoryLinkedIn post, podcast intros, sales call openerWeekly content
Full case studyWebsite portfolio page, PDF download, RFP responseLate-stage buyer research

Output Structure

markdown
## Case Study: [Client Descriptor] — [Date]

### Situation Summary
[2-sentence analysis from Phase 1]
Result tier: [1/2/3/4]

---

### Format 1: Two-Liner
[Final copy]

### Format 2: Story Version
[Final copy]

### Format 3: Full Case Study
[Full markdown]

---

### Self-Critique Notes
- Two-liner: [pass/issue]
- Story: [pass/issue]
- Full: [pass/issue]

### Distribution Plan
[Where to use each]

### Next Step
[If no quote collected → run testimonial-collector]
[If strong story → suggest LinkedIn post from story format]

Cross-reference: If a client quote was captured here, run testimonial-collector to properly format and score it for your testimonial library.


Skill by Brian Wagner | AI Marketing Architect | brianrwagner.com

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Case Study Builder AI skill do?

Turn client wins into formatted case studies for proposals, social proof, and sales conversations. Use when someone needs to document results, build credibility, or create reusable proof assets.

Why use Case Study Builder on TypingMind?

Because you install it once and use it with any model. Case Study Builder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Case Study Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/BrianRWagner/ai-marketing-claude-code-skills/tree/main/case-study-builder. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Case Study Builder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Case Study Builder?

As many as you like. As long as a model supports skills, you can use Case Study Builder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Case Study Builder AI skill free?

It is published on GitHub by BrianRWagner. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇