agentleFS
OutThisLifeOutThisLife/brooklyn-skills/skills/ui-only/SKILL.md

ui-only

Skill207 starsChanged 4 months agoMITView on GitHub

While iterating on UI, do not waste time on tsc, lint, typecheck, format, full test suites, commit, or push until the user likes how it looks and works. Use for any UI/UX work, layout, redesign, Figma implementation, visual polish, "make it look right", or when they want to see the UI before cleanup.

  • Commits and pushes

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When you're changing how something looks or interacts: get the UI right first.

    line 12
  2. Distinctive:

    Don't burn turns on tsc, lint, or commit until they say it's good.

    line 13
  3. Distinctive:

    Don't start a dev server the user already has running — assume it's up unless told otherwise.

    line 25
  4. Very specific:

    When they say it's good / lgtm / clean it / commit it, then run checks, use clean, commit, and do whatever else the repo needs.

    line 34
  5. Distinctive:

    If you're not sure whether to keep iterating, ask.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

UI Only

When you're changing how something looks or interacts: get the UI right first. Don't burn turns on tsc, lint, or commit until they say it's good.

Don't run yet

Until they like the UI (or explicitly say to clean/commit):

  • tsc / typecheck / npm run build as a finish step
  • eslint / prettier / biome
  • full test suites just to greenlight a commit
  • git commit / git push / opening the PR as done

Dev server, screenshots, and targeted runs needed to see or use the UI are fine. Don't start a dev server the user already has running — assume it's up unless told otherwise. Keep debug logging in place while something's still broken; remove it only once it works.

Do this instead

  1. Change the UI.
  2. Show it (or tell them how to look).
  3. Take feedback and iterate.
  4. When they say it's good / lgtm / clean it / commit it, then run checks, use clean, commit, and do whatever else the repo needs.

If you're not sure whether to keep iterating, ask.

Scope

Any UI surface (web, desktop, TUI). Skip for backend-only work. For primitives and tokens, also use ui-system.

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.