agentleFS
Sign inStart free
Dragoon0xDragoon0x/taste-skills/skills/articulation/design-rationale/SKILL.md

design-rationale

Skill5 starsChanged 8 months agoMITView on GitHub

Defend a design decision to skeptical stakeholders with structure and evidence. Use when presenting design work, writing design documentation, or pushing back on requests to change something.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 6

    Distinctive

    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:

    MUST include all four elements in one paragraph:

    line 17
  2. Distinctive:

    MUST connect to user behavior or business goals, not aesthetic preference

    line 22
  3. Distinctive:

    NEVER defend a design decision with "it feels right" or "it looks better"

    line 23
  4. Distinctive:

    MUST address the most likely pushback before it's raised

    line 26
  5. Distinctive:

    SHOULD acknowledge what's lost by this choice (the tradeoff)

    line 27
  6. Distinctive:

    MUST have a fallback position if the primary argument doesn't land

    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

Design Rationale

Convince the room with structure, not feelings.

How to use

  • /design-rationale Apply rationale constraints to defend design decisions in this conversation.

Constraints

Rationale Structure

  • MUST include all four elements in one paragraph:
    1. What you chose
    2. What you didn't choose (and why)
    3. What principle guided the decision
    4. What outcome you expect
  • MUST connect to user behavior or business goals, not aesthetic preference
  • NEVER defend a design decision with "it feels right" or "it looks better"

Anticipate Objections

  • MUST address the most likely pushback before it's raised
  • SHOULD acknowledge what's lost by this choice (the tradeoff)
  • MUST have a fallback position if the primary argument doesn't land

Anti-Patterns

  • Defending decisions by appealing to authority ("Apple does it this way")
  • Using data as a shield without explaining the logic ("our A/B test showed...")
  • Getting defensive when challenged instead of engaging with the objection
  • Over-explaining simple decisions (not every choice needs a thesis)

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.

Reviews can't be read right now.

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.

Check your setup, free