Skip to content
SkillModel-led1,127 tokens in use

pick-ui-library

Picks the library for a frontend task from a curated list of trusted choices, so an agent hand-writes no toast and installs no abandoned package.

58,388 stars on the repository MIT Licenseemilkowalski/skills · skills/pick-ui-library
npx skills@latest add emilkowalski/skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing pick-ui-library costs

43tokens idle
1,127tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. 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
  • Structure25/25
  • Examples3/15
  • Output5/15
  • Size15/15
  • Resources10/15

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 activity80
  • Maintenance40
  • Community52
  • Maturity28
  • Momentum40

Pick UI Library gives an agent a curated list to choose from. It is grouped into UI components and primitives, motion and visuals, charts, interaction and performance, and state and styling, and covers needs such as toasts, drawers, command menus, OTP inputs, numbers, virtualization and drag and drop. A closing section lists common mismatches to catch. It is set to run only when invoked.

What You Get

  • A library recommendation for the task at hand
  • A list grouped by components, motion, charts, interaction and state
  • Common mismatches to watch for
  • Guidance on how to use the list

Common Use Cases

  • Choosing a toast, drawer or command menu library
  • Picking a chart or virtualization library
  • Choosing state management and styling tools

What Makes It Unique

The list reflects libraries the author uses and trusts, and the skill exists to stop an agent hand-writing a component that a maintained library already covers. The mismatch section names where agents usually pick wrong.

Under The Hood

A single SKILL.md containing the list. It runs no scripts and has no network access. The model reads the list for the task, names the library and then uses it while writing code.

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