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

case-study-design-decisions

Skill1 starsChanged 4 months agoMITView on GitHub

Explain and defend pivotal design decisions in a case study using stakeholder context, user and business evidence, alternatives, constraints, trade-offs, consequences, limitations, and follow-up. Use when a portfolio draft shows screens without rationale, lists activities instead of decisions, needs executive credibility, must explain rejected options, or must communicate complex enterprise, platform, system, or AI-agent design choices.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    Remove aesthetic rationale that does not affect use, comprehension, trust, or performance.

    line 18
  2. Distinctive:

    Do not hide uncertainty or pretend consensus existed.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

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

Case Study Design Decisions

Make the decision legible to a skeptical non-designer. Read references/decide-record.md.

Workflow

  1. Identify the reader’s influence, priorities, vocabulary, and likely objection.
  2. Select only decisions that changed user outcomes, system behavior, risk, cost, or delivery.
  3. Complete a DECIDE record for each pivotal decision.
  4. Connect design evidence, business consequences, technical constraints, and limitations.
  5. Represent rejected alternatives fairly.
  6. State what agreement enabled and what happened next.
  7. Remove aesthetic rationale that does not affect use, comprehension, trust, or performance.

Communication pattern

For each decision:

  • set context before showing the artifact;
  • name the problem and tension;
  • explain the choice in the reader’s language;
  • ground the rationale in users, business, research, and constraints;
  • acknowledge limitations without weakening the argument;
  • show the decision or learning that followed.

Do not hide uncertainty or pretend consensus existed. Distinguish the design recommendation from the final organizational decision.

Output

Return a decision shortlist, completed DECIDE records, likely stakeholder questions, and recommended captions or callouts for the associated visuals.

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.