pick-ui-library
An agent skill by emilkowalski, from emilkowalski/skills. Tags: developer-tools, planning, react, ui-ux, validation.
What it does
Pick the right library for a given frontend task from a curated, opinionated list — numbers, OTP inputs, charts, command menus, virtualization, drag and drop, toasts, state, styling, and more. Only runs when explicitly invoked; it does not trigger on its own.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add emilkowalski/skills --skill pick-ui-library
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/emilkowalski/skills
cp -r skills/skills/pick-ui-library ~/.claude/skills/pick-ui-library
Safety box score
Grade A, minimal risk: 0 of 100 risk points, rated 2026-09-23. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This is a read-only library-picking lookup skill: it reads `package.json` and recommends a frontend library from a curated list. It does not ship scripts or perform actions itself, so the main risk is just opinionated guidance rather than machine impact.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | `SKILL.md` contains only guidance text; there are no shell commands, scripts, or code evaluation steps. |
| Network access | 0 (none) | It references external library sites in markdown, but there is no instruction or code to fetch from or send data to any remote host. |
| Filesystem reach | 0 (none) | The only file access mentioned is reading `package.json`; there is no write/delete scope outside the project. |
| Secrets & credentials | 0 (none) | The skill does not ask for tokens, keys, passwords, `.env` files, or any other credential material. |
| Privilege & persistence | 0 (none) | There is no mention of sudo, global installs, services, shell startup files, or OS-level changes. |
| Instruction hijack surface | 0 (none) | `SKILL.md` gives normal task-routing instructions and does not tell the agent to ignore policies, hide actions, or follow remote instructions. |
| Irreversible actions | 0 (none) | It recommends libraries but does not itself deploy, publish, send messages, or make irreversible changes. |
| Transparency | 0 (none) | The skill is fully readable markdown with no binaries, minified code, or decoded-at-runtime content. |
Before installing
- No special checks needed: this skill is read-only and ships no executable scripts.
- If you want to verify scope, skim `SKILL.md` and confirm it only contains the curated library list and usage guidance.
Rated 2026-09-23 by an automated review of 1 file from the skill's repository.
Source
- Repository
- emilkowalski/skills (all skills from this repository)
- Path
- skills/pick-ui-library/SKILL.md
- Branch
- main
- Updated
- 2026-09-22
Related skills
- check-agent-compatibility
- cli-for-agents — Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors.
- create-verification-skill — Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
- expo-data-fetching — Framework (OSS). Use when implementing or debugging ANY network request, API call, or data fetching.
- expo-overview — Framework (OSS). Entry point and router for every Expo or EAS task.
- principle-encode-lessons-in-structure — Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.