Independent reviews. IonBin has no partnerships with the tools on this page and was not paid for these listings. Our evaluations are our own, based on public documentation and our research. Product names are trademarks of their owners and are used for identification only. How disclosure works.

Tokens & playbooks / Design playbook

UI Skills

Turn broad polish requests into focused review tasks.

Documentation reviewed

Source review

What this status means

Understand the resource

What it is.

UI Skills curates design-engineering guidance and skills across accessibility, interaction, motion and visual systems. Its current catalog also offers CLI and MCP access, which should be evaluated separately from reading the playbooks.

When it is useful

A first implementation works, but its states and interaction details need a structured review.

A proposed application

Put it to work.

This example illustrates a possible use. The proposed workflow and expected result are separate from the bounded checks recorded below.

Try this

Choose a narrow form-review guide and record defects with reproduction steps instead of asking an agent to redesign everything.

Result to aim for

A prioritized UI issue list with observable acceptance criteria.

Before you start

What you need.

  • A concrete screen or component and permission-scoped access for any later agent workflow.

The practical boundaries

What to watch for.

  • Curated skills can come from different authors and carry different permissions or executable helpers.
  • The catalog was read; its CLI, MCP and individual skills were not installed or evaluated here.

Review record

What we could establish.

  • Public primary documentation and the bounded account-free checks below were reviewed. Public search returned nine accessibility-related links. Pinned skill text was inspected as data; no skill was installed or asked to edit a project.
Source coverage and runtime coverage are separate

The source-review notes describe documentation and identity. The account-free evaluation below records exactly which public interaction or local fixture was checked, what happened, and what remains untested.

Check current access, terms, licensing and data handling before using a resource with your own material.

Runtime and security evaluation

What the evaluation covers.

Limited evaluationAccount-free ·

Public search returned nine accessibility-related links. Pinned skill text was inspected as data; no skill was installed or asked to edit a project.

Methods: Public HTTP response · Public browser sample · Source review. A completed check covers the stated sample; it is not a safety certification.

Target
https://github.com/ibelick/ui-skills
Version or capture
747a47fdb6b405e5cbf268f7c410123930455157
Integrity scope
sha256:fea3322f36d58fdafafce2aef56e4556dd2ac7b20876b7dff7d8be7f25fa597f

Test conditions

  • Chromium 155.0.8059.82 on Windows; fresh temporary profile and fresh account-free contexts.
  • Public HTTPS GET/HEAD requests only; telemetry/auth routes and WebSockets blocked. No account storage or credential environment variables.

Individual checks and observations

  1. Public document and DOM

    pass

    Public browser sample: Fresh Chromium GET, then inspect rendered controls after hydration delay

    Observed: HTTP 200; 4 captured button labels; 1 inputs; 0 canvases.

  2. Skill search

    pass

    Public browser sample: Open search, type accessibility and inspect result links

    Observed: Search dialog returned 9 visible links for the synthetic query; no skill was invoked.

Security findings and boundaries

Passive inspection of the public response headers, requested hosts and the named browser sample. Also inspected the named pinned skill text as untrusted data. No active exploitation, authenticated permissions test or complete security audit.

Documented · caution

Skill text can authorize project changes only through its host

The reviewed accessibility and component-canvas instructions describe code review, edits and preview boundaries. Their usefulness and safety still depend on the agent permissions and the project supplied to it.

Practical caveats

  • Treat the selected SKILL.md as third-party instructions and review its requested tools before adding it to a host.
  • Pin and recheck the selected version or sample before adoption; the observations apply only to the scope and date shown.

What remains untested

  • Search functionality does not establish that an agent will find or repair accessibility defects.
  • Fresh-browser restrictions can affect external assets and hydration. Initial failed selectors and limited probes remain in the evidence; they are not blanket product failures.

Security limits

  • No authenticated workspace, private content, production backend permissions or data-retention verification.
  • Search functionality does not establish that an agent will find or repair accessibility defects.

Evaluation sources

  1. Primary public resource
  2. Pinned upstream revision

Download this evaluation record (JSON)

Follow the evidence

Sources and further reading.

  1. Primary product page
  2. Official linked repository

Keep exploring

More in tokens & playbooks.

View category

Documentation reviewed

DesignSystems.one

Compare published systems and inspect their design foundations.

Documentation reviewed

Open Props

Replace repeated visual guesses with a named CSS scale.