ui-skills

Opinionated, evolving constraints to guide agents when building interfaces. Useful for keeping output coherent across many small UI pieces.

Quality

32%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ui-skills/SKILL.md

Quality

Content

36%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-sectioned but hollow catalogue stub: it duplicates the description, restates metadata, and delegates every actionable step to an upstream GitHub page. An agent reading it cannot execute anything beyond opening a URL, and no local reference material exists to back the advertised capabilities.

Suggestions

Inline the actual install command and target skills-directory path (e.g., a concrete git clone or copy command) instead of 'Inspect the upstream README for exact paths'.

Replace the 'What it does' section, which repeats the description verbatim, with a brief example of the constraints in action (one rule snippet or before/after).

Ship the core constraints as a local reference file (e.g., references/rules.md) so the skill is self-contained, or clearly list which files exist in the bundle with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is short and sectioned, but it pads: the 'What it does' section repeats the frontmatter description verbatim, and the upstream URL appears in both 'Source' and the bash block. It is 'mostly efficient but includes some unnecessary explanation or could be tightened' — not 4 because the verbatim duplication and OpenDesign catalogue narration earn no new information.	3 / 5
Actionability	The only executable content is `open https://github.com/ibelick/ui-skills` with the comment 'Inspect the upstream README for exact paths' — the actual install command, paths, and invocation steps are all delegated to an external page. This is 'minimal concrete guidance; high-level hints but missing the specific steps to execute', and not 3 because even the install step is unspecified rather than merely incomplete.	2 / 5
Workflow Clarity	There is a rough sequence (inspect upstream → install the bundle → invoke by name or trigger phrase) but each step is under-specified: no install command, no skills-directory path, no verification that the install worked. It matches 'rough sequence present but many gaps; steps poorly defined', and does not reach 3 because no step carries concrete detail.	2 / 5
Progressive Disclosure	Sections are clearly labeled and the skill is under 50 lines, but there is no local bundle (references/, scripts/, assets/ are absent) — all substantive content lives at an external URL rather than in one-level-deep local references. It fits 'some structure; references present but not clearly signaled; content that should be separate is inline (external)', and not 4 because navigation to the real material depends on a user clicking through to GitHub.	3 / 5
	Total	10 / 20 Passed

Description

28%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a two-sentence abstraction: it names the UI domain but lists zero concrete capabilities and gives no usage triggers, so an agent cannot tell what the skill actually does or when to reach for it. It reads like catalogue copy rather than a capability description.

Suggestions

Replace abstract language with 2-4 concrete capabilities (e.g., 'Enforces spacing, typography, and color constraints across generated UI components; keeps multi-piece output visually coherent').

Add an explicit 'Use when...' clause naming trigger situations (e.g., 'Use when building or restyling UI components, generating multi-screen interfaces, or when the user asks for consistent/ opinionated UI rules').

Include natural trigger keywords users would actually type — 'design system', 'UI rules', 'consistent styling', 'component styling' — instead of only 'interfaces'.

Dimension	Reasoning	Score
Specificity	The description names the domain ("building interfaces") but offers no concrete actions — "Opinionated, evolving constraints to guide agents" and "keeping output coherent" are generic abstractions with no named operations. It matches the anchor 'Names the domain but actions are minimal or generic', and does not reach 3 because no specific action (e.g., 'enforces spacing rules', 'generates component styles') is ever listed.	2 / 5
Completeness	It has a vague 'what' ("constraints to guide agents when building interfaces") and no 'when' clause at all — nothing states when the skill should be invoked. Per the judging guidelines a missing 'Use when...' clause caps completeness at 3, and the vague 'what' drags it to the anchor 'Has a vague what and no when'.	2 / 5
Trigger Term Quality	No natural phrases a user would say appear — terms like 'design system', 'UI components', 'styling rules', or 'consistent UI' are absent; only 'interfaces' and 'output coherent' gesture at the domain. It sits above 1 because the domain is at least identifiable, but below 3 because common variations users would actually say are missing.	2 / 5
Distinctiveness Conflict Risk	"Opinionated, evolving constraints... building interfaces" carves out a UI/design niche, but the phrasing overlaps with general design-system, styling, and frontend skills. It is 'somewhat specific but could still overlap with similar skills' — not 4 because the trigger language gives no signals that would reliably route to this skill over a generic design or dataviz skill.	3 / 5
	Total	9 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/ui-skills/SKILL.md
Commit: 1b47e60

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.