pm-case-study-builder
Skill0 starsChanged 7 months agoMITView on GitHub
Turn raw PM work experience into a polished, portfolio-ready case study. Takes a product initiative — a feature, a 0-to-1 build, a platform redesign, a hard decision — and transforms it into a structured narrative that demonstrates PM thinking: the problem, the process, the decisions, the outcome, and the lessons. Output formats include written case study (for portfolio sites, Notion, or interview prep), a condensed LinkedIn article version, and a talking-points outline for verbal storytelling. Use this skill whenever the user asks to write a PM case study, turn past work into a portfolio piece, write up a product project, document a product decision, or prep a work sample. Also triggers for: "case study", "portfolio piece", "write up my work", "turn this project into a story", "PM portfolio", "product story", "help me explain what I built", or when the user describes a product initiative and asks how to present it. Invoke immediately — gather context as part of the skill flow.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Bellistri-Nick/pm-skillsword for word, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 1
- Bellistri-Nick/pm-skills★ 0100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
Ask for the following in one prompt.
- Distinctive: line 58
Before writing, identify the narrative structure that makes this case study work.
- Distinctive: line 92
Keep it tight — only context that explains why decisions were hard.
- Distinctive: line 111
If you don't have metrics, describe what observable change occurred.
- Distinctive: line 121
After writing the full case study, produce two additional versions:
- Distinctive: line 139
After delivering all three formats, offer:
- Distinctive: line 167
If the user has their own voice, match it.
- Distinctive: line 188
If the raw material the user gives you would produce a weak case study, name the gap and ask the right question to unlock the real story.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
PM Case Study Builder
What this skill does
Takes a product initiative the user worked on — at any stage of completion, with or without polished metrics — and builds a structured, compelling case study that demonstrates PM thinking. The goal is not to write marketing copy. It's to surface the decisions that were hard, the context that made them hard, and the outcome that resulted.
A good case study shows how a PM thinks, not just what they shipped.
Step 1: Gather the raw material
Ask for the following in one prompt. If anything is already in context, skip asking for it. Imperfect information is fine — you'll work with what's there and flag gaps rather than blocking on them.
- The initiative — What did you work on? (Feature, product, platform, redesign, 0→1 build, strategy project, cancellation, etc.)
- Context and constraints — What company, what stage, what team size? What constraints mattered (timeline, resources, tech debt, org dynamics)?
- The problem you were solving — What was broken, missing, or unclear? Whose problem was it?
- What you did — The key decisions you made, the approaches you considered, the work you led
- The outcome — What shipped? What changed? Any metrics, even rough ones?
- What you'd do differently — Optional, but makes the story more credible
- Where this will be used — Portfolio site, interview, LinkedIn, internal doc, writing sample?
Once you have this, proceed. Don't wait for perfect information.
Step 2: Identify the story spine
Before writing, identify the narrative structure that makes this case study work. Every strong PM case study has:
- The problem worth caring about — Why did this matter? Who was affected?
- The non-obvious decision — The moment where multiple reasonable paths existed and judgment was required. This is the heart of the case study.
- The constraint that shaped everything — What made this hard? (Technical debt, stakeholder misalignment, ambiguous data, tight timeline, competing priorities)
- The outcome that proves something — Not just "we shipped it" but what changed in the world
Name these four elements explicitly before writing. If you can't find a "non-obvious decision," ask the user: "What was the hardest call you made?" That's usually the real story.
Step 3: Write the full case study
Structure:
[Initiative Title]
One-line framing: what it was and what it changed
The problem
What was broken or missing? Whose problem? How did you know it was a real problem worth solving? (2–4 sentences. Resist the urge to start with company background.)
Context
What were you working with? Team size, product stage, constraints that mattered. Keep it tight — only context that explains why decisions were hard.
What I did
Narrative of the key decisions, not a list of activities. Structure as a story: what you tried, what you learned, what you changed, what you decided.
Include:
- The hardest decision and the reasoning behind it
- What you considered and ruled out
- How you handled uncertainty or conflicting signals
- Who you worked with and why that mattered
Don't include:
- Everything that happened (this is a highlight, not a journal)
- Process steps that didn't require judgment ("I ran standups")
- Contribution language ("I supported the team in...")
The outcome
What shipped. What changed. Metrics if available — real ones, not vanity numbers. If you don't have metrics, describe what observable change occurred.
What I'd do differently
One honest observation. Makes the story feel real and signals a PM who learns. Skip if the user prefers.
Step 4: Produce output formats
After writing the full case study, produce two additional versions:
LinkedIn article version (600–900 words)
Same structure, tighter prose. Opens with the "so what" — the insight or decision that made the project interesting — not with background. Ends with a clear takeaway or open question. Appropriate for publishing on LinkedIn.
Talking-points outline (for verbal storytelling)
A structured outline the user can internalize for interviews or portfolio walkthroughs:
- One-sentence setup: "This was a [type of problem] at [company] during [context]"
- The non-obvious decision: what it was, what you considered, what you decided
- The outcome: what happened
- The lesson: what you'd do differently or what this taught you
Step 5: Offer refinements
After delivering all three formats, offer:
"Want me to adjust the angle, tighten a section, sharpen the metrics framing, or tailor this for a specific role or company? Just say what needs changing."
Common refinements:
- Tailoring for a specific role — Reframe which decisions to emphasize based on what the target company cares about
- Metrics coaching — Help the user figure out what numbers they can actually claim, and how to frame them honestly if they're partial or indirect
- Condensing for a portfolio — Cut to the essential narrative for a 2-minute portfolio walkthrough
- Strengthening the decision narrative — If the case study reads like a feature announcement, reframe it around the judgment calls
Tone and voice guidance
The default voice for case studies:
- First person, active — "I decided to..." not "The team decided to..."
- Specific about decisions — Name the trade-off, not just the outcome
- Honest about uncertainty — "We didn't know X, so we..." is stronger than pretending everything was planned
- Lean — One idea per sentence. Cut the preamble.
- No jargon — "We improved retention" not "We drove user engagement through a frictionless onboarding optimization"
If the user has their own voice, match it. Ask for a writing sample if they want a specific style.
What makes a PM case study strong vs weak
Strong:
- Centers on a decision, not a feature
- Names what was hard and why
- Has a specific outcome, even an imperfect one
- Shows judgment: what was considered and ruled out
- Reads like a person, not a job description
Weak:
- Leads with company background before the problem
- Describes process steps without explaining why they mattered
- Skips the hard decision — just says "we shipped X and it worked"
- Generic metrics ("improved NPS") without context
- Passive voice throughout ("the team was able to...")
If the raw material the user gives you would produce a weak case study, name the gap and ask the right question to unlock the real story.
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
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.

