agentleFS
jpoindexterjpoindexter/design-case-study-skills/skills/case-study-writing/SKILL.md

case-study-writing

Skill1 starsChanged 4 months agoMITView on GitHub

Draft, edit, and finish concise design case-study copy from an evidence ledger or structured outline. Use when a portfolio case study is verbose, vague, generic, overly chronological, full of UX process theater, missing scannable headings and captions, inconsistent in voice, or needs publication-ready structure without inventing research, metrics, outcomes, or quotes.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Treat writing as part of the design.

    line 8
  2. Distinctive:

    Use headings that carry the argument.

    line 21
  3. Distinctive:

    Prefer concrete nouns and verbs over design adjectives.

    line 22
  4. Distinctive:

    Keep captions analytical: explain what the reader should notice and why it mattered.

    line 24
  5. Distinctive:

    Do not invent participant quotes or compress several people into a fake quote.

    line 27
  6. Very specific:

    Use [evidence needed: …] rather than generic filler.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Case Study Writing

Treat writing as part of the design. Read references/editorial-loop.md.

Workflow

  1. Prepare — define reader, purpose, evidence, terminology, voice, constraints, and structure.
  2. Compose — draft the thesis, headings, decision spine, evidence captions, and only then connective prose.
  3. Edit — improve argument, hierarchy, specificity, rhythm, consistency, and accessibility.
  4. Finish — verify facts, links, captions, alt text, credits, redactions, formatting, and unresolved placeholders.

Writing rules

  • Lead with the outcome and defining constraint.
  • Give each paragraph one job.
  • Use headings that carry the argument.
  • Prefer concrete nouns and verbs over design adjectives.
  • Replace “we conducted” chronology with what the evidence changed.
  • Keep captions analytical: explain what the reader should notice and why it mattered.
  • State ownership precisely.
  • Preserve uncertainty and missing evidence.
  • Do not invent participant quotes or compress several people into a fake quote.
  • Use [evidence needed: …] rather than generic filler.

Output

Return the revised case study, a short evidence-gap list, and an edit note naming any claims removed or softened because they were unsupported.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.