Case study

Skill jpoindexter/design-case-study-skills/skills/case-study

Evidence-backed UX and AI-agent case study skills for Codex and Claude

Install

npx -y skills add jpoindexter/design-case-study-skills --skill case-study

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

14 days oldThe repository was created 14 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Route and produce evidence-backed product or design case studies from raw notes, research, screenshots, specifications, decision logs, architecture, metrics, and project artifacts. Use when the user invokes /case-study, asks to write, critique, structure, or polish a portfolio case study, needs to explain a complex design project, or needs an AI-agent case study covering autonomy, human oversight, telemetry, trust, latency, failures, and recovery.

SKILL.md

3.9 KB, as published. Nobody here has run it

Case Study Dispatcher

Resolve the project, intended reader, available evidence, and requested format. Mark missing facts; never fill them with plausible fiction.

Route

Need	Load
Flat timeline or missing story	`narrative-arc-builder`
Screens without rationale	`extract-design-rationale`
Architecture shapes the experience	`system-architecture-translator`
Imprecise or inflated technical copy	`technical-microcopy-editor`
Dense, repetitive, slow-to-scan draft	`enforce-scannable-density`
AI agent or probabilistic system	`ai-agent-case-study` plus the applicable skills above
Complex multichannel or branching journey	`case-study-storytelling` and `case-study-story-map`
Deep stakeholder decision narrative	`case-study-design-decisions`
General long-form drafting and finishing	`case-study-writing`

Load the smallest set that covers the evidence and requested deliverable. When the user asks for a complete build from raw artifacts, apply the automated pipeline below as one workflow, not as separate reports.

Automated pipeline

Raw logs / notes / code / research
  → narrative-arc-builder
  → system-architecture-translator (when architecture affects the experience)
  → extract-design-rationale
  → technical-microcopy-editor
  → enforce-scannable-density
  → quality gate

For an AI-agent case study, apply ai-agent-case-study across every stage. It governs autonomy, permission, observability, uncertainty, intervention, and recovery; it is not an extra standalone report.

Evidence contract

Label every substantive claim:

Executed — supported by a test, trace, artifact, or measured output.
Observed — supported by research notes, usability observations, or recorded behavior.
Reported — attributed to a stakeholder, participant, or project record.
Proposed — a recommendation, hypothesis, future metric, or unverified narrative bridge.

Never convert a proposal into an outcome. Never invent research, metrics, quotes, responsibilities, constraints, alternatives, or impact. Use [evidence needed: …] where the story has a material gap.

Workflow

Inventory source artifacts and create an evidence ledger.
State the protagonist, goal, inciting problem, constraints, pivotal decisions, delivered change, and measured result.
Select the smallest route above.
Build the narrative arc before drafting sections.
Translate consequential system behavior into visible states, controls, and recovery.
Extract the decision rationale and rejected alternatives.
For AI systems, document supervision and uncertainty before visual polish.
Run the accuracy, clarity, and brevity edit.
Enforce scannable density without deleting evidence.
Run the quality gate in references/quality-gate.md.
Deliver one clean case study plus a short unresolved-evidence list.

Use assets/case-study-template.md when creating a new Markdown artifact.

Done

A case study is ready only when a skeptical reader can answer:

What changed, for whom, and under what constraints?
What did the designer actually own?
Which decisions were difficult, what alternatives existed, and why were they chosen?
What evidence supports the outcome?
What remains unknown, limited, or confidential?
For AI agents: where does autonomy stop, how does a human intervene, what is observable, and how does failure recover?