agentleFS
Sign inStart free
requierequie/endostack/skills/principle-exhaust-the-design-space/SKILL.md

principle-exhaust-the-design-space

Skill4 starsChanged 17 days agoMITView on GitHub

Use for a UI, architecture, or product choice the codebase has never faced, or one decided by how it feels in use. Build two or three rival throwaway prototypes and pick based on comparing them side by side.

44 other projects use a version of this, 13 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-pstack, poteto-help and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 25 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 14 projects that use this

  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 11 projects that use this

  • JoshueOsunaSkill

    Poteto Mode

    poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

    Also in 3 projects that use this

  • instructureSkill

    ketchup

    Rebuild context after /clear by analyzing uncommitted changes across Canvas LMS and all plugin repositories

    Also in 18 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 2

    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:

    When the codebase offers no existing pattern for a choice, make two or three rival prototypes and compare them directly before committing.

    line 9
  2. Distinctive:

    Put them side by side. For UI, place them behind one switcher and capture screenshots or recordings.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 31 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

Exhaust the design space

When the codebase offers no existing pattern for a choice, make two or three rival prototypes and compare them directly before committing. Your first design is a single sample from the options, and it cannot be judged without others next to it.

When it applies

A novel UI interaction or architectural choice with nothing similar already in the code, and product decisions where the right answer depends on how something feels to use more than on a logical argument. An example: choosing how an agent asks the user to approve a risky tool call (inline prompt, batched review queue, or a policy file the user edits once).

Skip it when the codebase already has an established pattern for the decision, or when one logical argument settles it.

What to do

  1. Name the open decision and the dimensions that matter (friction, error rate, latency, how much the user must read).
  2. Build two or three cheap, throwaway prototypes that take genuinely different approaches. Three color variants of one layout count as one approach.
  3. Put them side by side. For UI, place them behind one switcher and capture screenshots or recordings. For behavior, measure each on the same inputs.
  4. Choose from what you observed, record why, and delete the losers.

Parallel subagents can build the prototypes at the same time. The arena and architect skills run this pattern for code and design.

The failure it prevents

Locking in the first idea, and arguing about alternatives in the abstract when running them would answer the question in minutes.

Done when

The choice was made from compared, running alternatives.

Related: principle-experience-first.

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.

Check your setup, free