agentleFS
mcabreradevmcabreradev/hermes-sdd-agency/skills/design-exploration/SKILL.md

design-exploration

Skill1 starsChanged 57 days agoMITView on GitHub

Generate multiple design variants, compare, and collect structured feedback.

8 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

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    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:

    If the user asked for one design, don't shotgun — that's a different task.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 7 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
<!-- hermes-add-skill: concept adapted from gstack /design-shotgun (garrytan/gstack, MIT). -->

Design exploration

Explore a UI problem by generating several distinct design variants, putting them side by side, and collecting structured feedback to iterate. Use when a feature has a visual shape the user hasn't seen yet and a single design would be a guess.

How

  1. Brief — state the page/feature, the users, and the one thing the design must communicate first (the hierarchy goal). No brief, no variants.
  2. Generate N variants (3-5) that differ in a meaningful structural way — layout, hierarchy, or visual language — not just color swap. Different angles on the problem.
  3. Compare — put them in a visible comparison (grid / separate views with the same scale reference).
  4. Collect structured feedback — per variant, on the same axes: does the primary action land first? Is the content scannable? Does the tone match the product? Not "I like A".
  5. Iterate — combine the strongest elements or go a level deeper on the favorite, then re-present. Stop when a variant satisfies the brief, not at a fixed count.

Rules

  • Variants must be comparable (same content, same browser scale) or the comparison is meaningless.
  • Feedback is captured as observations about the brief's hierarchy goal, never as a mood vote.
  • If the user asked for one design, don't shotgun — that's a different task. Only invoke when options are actually wanted.

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.