1. Habit
  2. Skills
  3. Better Interface skill
jakubkrehel · 29K installs

Better Interface skill
Runs by itself, weekly flow review.

One ranked verdict across six domains.

Install the Better Interface skill and make it a habit: follow https://gethabit.dev/skills/jakubkrehel/better-interface.md

  1. 1Copy
  2. 2Paste into Claude Code, Codex or Cursor
  3. 3It runs by itself

29K installs8K starsMIT licenceSource on GitHub ↗

Better Interface

by jakubkrehel · 29K installs

The skill

The better interface skill runs one review across accessibility, layout, writing, typography, color and UI polish by routing to the better-* skills and merging one ranked verdict.

Only when you ask.

The habit

One ranked verdict across six domains.

↻ Runs by itselfweekly flow review

How the habit works.
You don't have to.

Three questionsWhen does it start? How does it check its work? What does it remember?

01

It starts by itself

weekly flow review. Runs in Claude Code routine.

  • ↻ weekly flow review
  • 0 9 * * 1

02

It checks its work

evidence + coverage check. If a check fails, it tells you.

  • ✓every finding cites path/to/file:line
  • ✓no more than 15 findings
  • ✓each domain is reviewed or marked Not reviewed
  • ✓escalation triggers are rated HIGH

03

It remembers

findings by root cause. The next run reads it first: open findings, flows already covered and domains marked Not reviewed.

loops/interface-review-loop/run-log.md

One run, step by step.
Then it stops.

Stop ruleOne flow per run, at most 15 findings.

  1. 01

    Resolve scope

    The agent picks one complete flow and states what it left out.

  2. 02

    Recon

    It finds the framework, tokens and viewports, and reads CONTRIBUTING.md, AGENTS.md or CLAUDE.md if present.

  3. 03

    Run domain skills

    It loads better-accessibility, better-layout, better-writing, better-typography, better-colors and better-ui in that order.

  4. 04

    Rank

    Findings get one shared HIGH, MEDIUM or LOW scale, with triggers first.

  5. 05

    Pick cheap fixes

    Each fix starts from delete, then the platform, then project tokens, before adding anything.

  6. 06

    Verify and report

    It runs safe project checks and writes one table in the review-format.md format.

What it may do.
Nothing more.

Safe by defaultIt writes only in its own folder and asks you before anything goes out.

Is it for you?
Use it when it fits.

Quick checkRead both lists. If the left one sounds like you, the Better Interface skill helps.

Use it when

  • ✓ You want one review across all UI disciplines
  • ✓ You audit a full user flow
  • ✓ You need findings ranked by user impact

Skip it when

  • – You want a review of a branch or pull request
  • – The other better-* skills are not installed

Questions

Better Interface skill, answered.

Can it review a pull request?

No. Branch and pull request reviews belong to interface-review, which you start yourself.

Does it edit code?

Not by default. A review is read-only unless you also ask it to implement the findings.

How do I install the Better Interface skill?

Copy the prompt at the top into your agent. It installs the skill from jakubkrehel/skills and sets up the habit. Or run npx skills add jakubkrehel/skills --skill better-interface.

Is the Better Interface skill free?

Yes. It is published under MIT. Habit is free too.

Better Interface. Now as a habit.

Install the Better Interface skill and make it a habit: follow https://gethabit.dev/skills/jakubkrehel/better-interface.md

  • Free
  • No account
  • Undo in one line

All jakubkrehel skills →More design skills →

Works in

  • Claude Code
  • Codex
  • Cursor
  • ChatGPT
  • Claude app

Made by jakubkrehel, published under MIT. Habit links to the original and never changes it. Is this your skill?

Copying didn't work here. Select the line and copy it by hand.