Skip to content
SkillModel-led1,839 tokens in use

Better Interface

Reviews a screen, flow or whole interface across accessibility, layout, writing, typography, color, UI polish and motion, and returns one ranked report.

12,497 stars on the repository MIT Licensejakubkrehel/skills · skills/better-interface
npx skills add jakubkrehel/skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Better Interface costs

33tokens idle
1,839tokens in use
2,338tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure19/25
  • Examples0/15
  • Output15/15
  • Size15/15
  • Resources7/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity96
  • Maintenance52
  • Community48
  • Maturity24
  • Momentum40

Better Interface is the orchestrator of a set of design-engineering skills. It resolves the scope of a review, loads each domain skill in a fixed order, collects their evidence and consolidates everything into one findings table ranked by user impact, ending in a Block or Approve verdict.

It owns no domain rules itself. Accessibility, layout, writing, typography, color, UI polish and motion each stay with their own skill, and a domain whose skill is unavailable is marked Not reviewed.

What You Get

  • A scope and coverage section that names what was inspected in each of the seven domains
  • One findings table with severity, domain, file and line, current code, replacement and the reason it matters
  • Systemic findings merged into one row against the shared token or component, listing every location
  • A verification section separating checks that passed from checks marked Not verified
  • A Block or Approve verdict, where any remaining HIGH finding blocks

Common Use Cases

  • Reviewing a new settings screen before release across all interface disciplines at once
  • Auditing a checkout flow, including its empty, loading, error and narrow-width states
  • Getting one ranked list of interface problems to hand to a team in place of seven separate reports
  • Checking a repository’s shared components for systemic issues that repeat across pages

What Makes It Unique

It adds a shared severity scale and a list of escalation triggers, such as a control with no accessible name or text that fails contrast, that rank HIGH on sight. It also prefers the cheapest fix, trying deletion first, then the platform, then existing project tokens, then a corrected value, and adding something new last.

Under The Hood

The skill is a SKILL.md and one review-format file, and it contains no scripts. It reads the project’s own docs such as AGENTS.md, CLAUDE.md, CONTRIBUTING.md and design-system notes, loads the seven sibling better-* skills, may run the project’s safe check commands and may inspect the rendered interface in a browser. A review is read-only; it edits source only when you ask for the findings to be implemented. A change, branch or pull request review is sent to the interface-review skill.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers