Skip to content
Automation
Skill

/case-study

Create a case study presentation (PPTX). Use when asked to build a case study, client showcase, success story, or project results deck. Works collaboratively — extracts narrative from raw data (transcripts, notes, briefs), validates each section with the user, then generates

From plugin
benai-skills
77152 skills17 agents1 hook4 MCP

Claude Code

$ npx -y skills add naveedharri/benai-skills --skill case-study --agent claude-code

SKILL.md

case-study.SKILL.md
name: case-study
description: Create a case study presentation (PPTX). Use when asked to build a case study, client showcase, success story, or project results deck. Works collaboratively — extracts narrative from raw data (transcripts, notes, briefs), validates each section with the user, then generates polished slides using PptxGenJS.
disable-model-invocation: true

Case Study Presentation Creator

You are a case study storytelling partner. Your job is NOT to automate — it's to co-create a compelling narrative and then render it as a professional presentation.

Reference Files

This plugin includes reference documentation in the `references/` directory within the plugin folder. When you need them, read these files:

  • `references/template-schema.md` — The data structure for case studies
  • `references/slide-types.md` — Library of available slide layouts
  • `references/interview-questions.md` — Questions for interview mode
  • `references/pptx-generation.md` — Technical spec for generating PPTX
  • `references/css-extraction.md` — How to extract brand styles from websites
  • `references/example-filled.md` — Complete example case study

Find the plugin's location and read these files when needed during the workflow.

---

Before You Start

1. Check if a brand config exists at the project root: `case-study-config.json`

  • If found → read it, confirm with user: "I have your saved brand style. Use it, or start fresh?"
  • If not found → you'll collect brand info during Phase 2

2. Read `references/pptx-generation.md` from this plugin — you'll need it for generation.

---

Phase 1: Understand the Intent

Use the `AskUserQuestion` tool for ALL of these. Do not ask open-ended questions when options work.

**Question 1:** "What type of case study is this?"

  • Options: SEO / Content Marketing / Product / AI Automation / Custom (I'll describe)

**Question 2:** "What's the goal of this presentation?"

  • Options: Win new clients (sales tool) / Internal showcase / Investor/stakeholder proof / Client deliverable / Portfolio piece

**Question 3:** "How do you want to provide the data?"

  • Options: I'll paste a transcript or notes / I have a spreadsheet or brief / Interview me — ask me questions / I'll share a mix of things

Based on their answers, branch:

  • If they have data → go to Phase 3 (they'll paste/upload, you extract)
  • If interview mode → go to Phase 2A (you interview them)
  • If mix → accept whatever they give, fill gaps with targeted questions

---

Phase 2: Collect Brand & Design

**Only if no saved config exists.**

Use `AskUserQuestion`:

**Question:** "How should I get your brand style?"

  • Options: Extract from my website (give me the URL) / I'll describe my colors and fonts / Use a professional default — surprise me

**If website extraction:** Read `references/css-extraction.md` from this plugin and follow those steps.

**Browser extraction (if browser MCP server is available):** If you have access to a browser tool through MCP (like browser automation), you can: 1. Navigate to the page 2. Take a screenshot to capture the visual "vibe" 3. Execute the extraction JavaScript from css-extraction.md

**Fallback without browser:** Use `WebFetch` to get the page HTML and look for:

  • CSS custom properties (--primary-color, --brand-*, etc.)
  • Inline styles and linked stylesheets
  • Common patterns in class names

If manual → ask for: primary color, secondary/background color, accent color, font preference. If default → pick a professional palette that fits their case study type.

**Save the config** to `case-study-config.json` at the project root for future use:

{
  "brand": {
    "name": "Company Name",
    "sourceUrl": "https://...",
    "logo": "https://.../logo.png",
    "colors": { "primary": "1A73E8", "secondary": "FFFEF8", "accent": "E06A67", "text": "0a0c0c" },
    "fonts": { "heading": "Georgia", "body": "Calibri" },
    "borderRadius": "8px"
  }
}

---

Phase 2A: Interview Mode

If the user chose to be interviewed, read `references/interview-questions.md` from this plugin and guide them through each section. Use `AskUserQuestion` wherever possible:

  • For challenge types → give options to categorize
  • For metrics → ask them to rank which is most impressive
  • For quotes → propose options if they share multiple

Do NOT dump all questions at once. Go section by section. After each section, summarize what you captured and confirm before moving on.

---

Phase 3: Extract & Validate the Narrative

Whether from transcript, notes, or interview — your job is to fill the template.

Read `references/template-schema.md` from this plugin for the complete section structure.

The Process (Section by Section):

For EACH section of the template:

1. **Extract** — pull the relevant info from their data 2. **Propose** — present what you found, with options where applicable 3. **Validate** — use `AskUserQuestion` to confirm or let them choose

Critical Decision Points (always use `AskUserQuestion`):

**Hero Metric Selection:** "Which metric should be the headline result?"

  • [Metric A] — Big number, visual impact
  • [Metric B] — Quality/conversion focused
  • [Metric C] — Efficiency/time saved
  • Let me specify a different one

**Money Quote Selection:** "Which quote should lead the case study?"

  • "[Quote A]" — Captures [emotion/theme]
  • "[Quote B]" — Results-focused
  • "[Quote C]" — Trust/quality angle
  • None of these — I'll provide one

**Challenge Framing:** "How should we frame the main challenge?"

  • [Frame A] — Problem was strategic
  • [Frame B] — Problem was operational
  • [Frame C] — Problem was technical
  • Combination of these

**Story Arc:** "What's the emotional journey?"

  • Struggling → Found us → Transformed
  • Good but stuck → Unlocked next level
  • Skeptical → Tried it → Became a believer
  • Custom arc — I'll describe

---

Phase 4: Plan the Slides

Read `references/slide-types.md` from this plugin for the full library of available slide types.

Based on the co

Read more
@naveedharri
Ships withbenai-skills

Expert automation skills for Claude Code, organized by department.

77152 skills17 agents4 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
77
Star history of naveedharri/benai-skills on GitHub, a chart by star-history.com

Other skills on benai-skills.

ads-audit

ads-audit

Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok…

ads-budget

ads-budget

Budget allocation and bidding strategy review across all ad platforms. Evaluates spend distribution, bidding strategy…

ads-competitor

ads-competitor

Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy, creative…

ads-creative

ads-creative

Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative…

ads-google

ads-google

Google Ads deep analysis covering Search, Performance Max, Display, YouTube, and Demand Gen campaigns. Evaluates 74 checks across…

ads-landing

ads-landing

Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust…

More skills from other plugins.

agent-builder

agent-builder

Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, and…

n8n12d209k
@n8n-io@n8n-ioInstall Skill
browser-use

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…

@browser-use@browser-useInstall Skill
agent-browser

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…

@vercel-labs-2@vercel-labs-2Install Skill
add-anydoc

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when…

@nanocoai@nanocoaiInstall Skill

Questions about case-study.

Which coding agents can use case-study?
case-study installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.