case-study-writing
B2B case study writing with STAR framework, data visualization, and research. Covers structure, customer quotes, metrics presentation, and distribution formats. Use for: customer success stories, portfolio pieces, sales enablement, marketing content. Triggers: case study, customer story, success story, b2b case study, client testimonial, customer case study, portfolio case study, use case, customer win, results story
- Installs
- 42
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/magentosh/superpowers --skill case-study-writing- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads case-study-writing automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Install the belt CLI skill:
npx skills add belt-sh/cli
Case Study Writing
Create compelling B2B case studies with research and visuals via inference.sh CLI.
Quick Start
Requires inference.sh CLI (
belt). Install instructions
belt login
# Research the customer's industry
belt app run tavily/search-assistant --input '{
"query": "SaaS customer onboarding challenges 2024 statistics"
}'
The STAR Framework
Every case study follows: Situation -> Task -> Action -> Result
| Section | Length | Content | Purpose |
|---|---|---|---|
| Situation | 100-150 words | Who the customer is, their context | Set the scene |
| Task | 100-150 words | The specific challenge they faced | Create empathy |
| Action | 200-300 words | What solution was implemented, how | Show your product |
| Result | 100-200 words | Measurable outcomes, before/after | Prove value |
Total: 800-1200 words. Longer loses readers. Shorter lacks credibility.
Structure Template
1. Headline (Lead with the Result)
❌ "How Company X Uses Our Product"
❌ "Company X Case Study"
✅ "How Company X Reduced Onboarding Time by 60% with [Product]"
✅ "Company X Grew Revenue 340% in 6 Months Using [Product]"
The headline should be specific, quantified, and state the outcome.
2. Snapshot Box
Place at the top for skimmers:
┌─────────────────────────────────────┐
│ Company: Acme Corp │
│ Industry: E-commerce │
│ Size: 200 employees │
│ Challenge: Manual order processing │
│ Result: 60% faster fulfillment │
│ Product: [Your Product] │
└─────────────────────────────────────┘
3. Situation
- Who is the customer (industry, size, location)
- What relevant context existed before the problem
- 1-2 sentences of company background
4. Task / Challenge
- Quantify the pain: "spending 40 hours/week on manual data entry" not "had data problems"
- Show stakes: what would happen if unsolved (lost revenue, churn, missed deadlines)
- Include a customer quote about the frustration
5. Action / Solution
- What was implemented (your product/service)
- Timeline: "deployed in 2 weeks" / "3-month rollout"
- Key decisions or configurations
- Why they chose you over alternatives (briefly)
- 2-3 specific features that addressed the challenge
6. Results
- Before/after metrics — always quantified
- Timeframe — "within 3 months" / "in the first quarter"
- Unexpected benefits beyond the original goal
- Customer quote about the outcome
Metrics That Matter
How to Present Numbers
❌ "Improved efficiency"
❌ "Saved time"
❌ "Better results"
✅ "Reduced processing time from 4 hours to 45 minutes (81% decrease)"
✅ "Increased conversion rate from 2.1% to 5.8% (176% improvement)"
✅ "Saved $240,000 annually in operational costs"
Metric Categories
| Category | Examples |
|---|---|
| Time | Hours saved, time-to-completion, deployment speed |
| Money | Revenue increase, cost reduction, ROI |
| Efficiency | Throughput, error rate, automation rate |
| Growth | Users gained, market expansion, feature adoption |
| Satisfaction | NPS change, retention rate, support tickets reduced |
Data Visualization
# Generate a before/after comparison chart
belt app run infsh/python-executor --input '{
"code": "import matplotlib.pyplot as plt\nimport matplotlib\nmatplotlib.use(\"Agg\")\n\ncategories = [\"Processing Time\", \"Error Rate\", \"Cost per Order\"]\nbefore = [4, 12, 8.50]\nafter = [0.75, 1.5, 2.10]\n\nfig, ax = plt.subplots(figsize=(10, 6))\nx = range(len(categories))\nwidth = 0.35\nax.bar([i - width/2 for i in x], before, width, label=\"Before\", color=\"#ef4444\")\nax.bar([i + width/2 for i in x], after, width, label=\"After\", color=\"#22c55e\")\nax.set_ylabel(\"Value\")\nax.set_xticks(x)\nax.set_xticklabels(categories)\nax.legend()\nax.set_title(\"Impact of Implementation\")\nplt.tight_layout()\nplt.savefig(\"results-chart.png\", dpi=150)\nprint(\"Chart saved\")"
}'
Customer Quotes
What Makes a Good Quote
❌ "We love the product." (vague, could be about anything)
❌ "It's great." (meaningless)
✅ "We went from processing 50 orders a day to 200, without adding a single person to the team."
— Sarah Chen, VP Operations, Acme Corp
✅ "Before [Product], our team dreaded Monday mornings because of the report backlog.
Now it's automated and they can focus on actual analysis."
— Marcus Rodriguez, Head of Analytics, DataCo
Quote Placement
- 1 quote in the Challenge section — about the frustration/pain
- 1-2 quotes in the Results section — about the outcome/transformation
- Always attribute: full name, title, company
Quote Formatting
> "We went from processing 50 orders a day to 200, without adding anyone to the team."
>
> — Sarah Chen, VP Operations, Acme Corp
Research Support
Finding Industry Context
# Industry benchmarks
belt app run tavily/search-assistant --input '{
"query": "average e-commerce order processing time industry benchmark 2024"
}'
# Competitor landscape
belt app run exa/search --input '{
"query": "order management automation solutions market overview"
}'
# Supporting statistics
belt app run exa/answer --input '{
"question": "What percentage of e-commerce businesses still use manual order processing?"
}'
Distribution Formats
| Format | Where | Notes |
|---|---|---|
| Web page | /customers/ or /case-studies/ | Full version, SEO-optimized |
| Sales team, email attachment | Designed, downloadable, gated optional | |
| Slide deck | Sales calls, presentations | 5-8 slides, visual-heavy |
| One-pager | Trade shows, quick reference | Snapshot + key metrics + quote |
| Social post | LinkedIn, Twitter | Key stat + quote + link to full |
| Video | Website, YouTube | Customer interview or animated |
Social Media Snippet
Headline stat + brief context + customer quote + CTA
Example:
"60% faster order processing.
Acme Corp was drowning in manual fulfillment. 4 hours per batch. 12% error rate.
After implementing [Product]: 45 minutes per batch. 1.5% errors.
'We went from 50 orders a day to 200 without adding headcount.' — Sarah Chen, VP Ops
Read the full story → [link]"
Writing Checklist
- Headline leads with the quantified result
- Snapshot box with company, industry, challenge, result at top
- Challenge is quantified, not vague
- 2-3 specific customer quotes with attribution
- Before/after metrics with timeframe
- 800-1200 words total
- Skimmable (headers, bold, bullet points)
- Customer approved the final version
- Visual: at least one chart or before/after comparison
Common Mistakes
| Mistake | Problem | Fix |
|---|---|---|
| No specific numbers | Reads like marketing fluff | Quantify everything |
| All about your product | Reads like a sales pitch | Story is about the CUSTOMER |
| Generic quotes | No credibility | Get specific, attributed quotes |
| Missing the "before" | No contrast to show impact | Always show the starting point |
| Too long | Loses reader attention | 800-1200 words max |
| No customer approval | Legal/relationship risk | Always get sign-off |
Related Skills
npx skills add inference-sh/skills@web-search
npx skills add inference-sh/skills@prompt-engineering
Browse all apps: belt app list
FAQ
What does the case-study-writing skill do?
B2B case study writing with STAR framework, data visualization, and research. Covers structure, customer quotes, metrics presentation, and distribution formats. Use for: customer success stories, portfolio pieces, sales enablement, marketing content. Triggers: case study, customer story, success story, b2b case study, client testimonial, customer case study, portfolio case study, use case, customer win, results story
How do I install case-study-writing?
Run npx skills add https://github.com/magentosh/superpowers --skill case-study-writing in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/case-study-writing/ (personal) or .claude/skills/case-study-writing/ (project).
Which AI agents can use case-study-writing?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is case-study-writing safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains case-study-writing?
It is published by magentosh in magentosh/superpowers. It has 42 recorded installs.
More from magentosh/superpowers
ai-image-generation
magentosh/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image
ai-video-generation
magentosh/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-avatar-video
magentosh/superpowers
Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc
twitter-automation
magentosh/superpowers
Automate Twitter/X with posting, engagement, and user management via inference.sh CLI. Apps: x/post-tweet, x/post-create (with media), x/post-like, x/post-retweet, x/dm-send, x/user-follow. Capabilities: post tweets, schedule content, like posts, retweet, send DMs, follow users, get profiles. Use for: social media automation, content scheduling, engagement bots, audience growth, X API. Triggers: twitter api, x api, tweet automation, post to twitter, twitter bot, social media automation, x automation, tweet scheduler, twitter integration, post tweet, twitter post, x post, send tweet
agent-browser
magentosh/superpowers
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video
web-search
magentosh/superpowers
Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabilities: AI-powered search, content extraction, direct answers, research. Use for: research, RAG pipelines, fact-checking, content aggregation, agents. Triggers: web search, tavily, exa, search api, content extraction, research, internet search, ai search, search assistant, web scraping, rag, perplexity alternative
Popular docs & writing skills
grill-with-docs
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
lark-markdown
open.feishu.cn
飞书 Markdown：查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件，或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档，也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。
writing-beats
mattpocock/skills
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
writing-shape
mattpocock/skills
Writing, exploit: shape raw material into an article, paragraph by paragraph.
writing-fragments
mattpocock/skills
Writing, explore: mine raw fragments, no structure yet.
writing-for-agents
mattpocock/skills
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.