Name: ui-skills
Rating: 20.8 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

ui-skills

Opinionated, evolving constraints to guide agents when building interfaces

Quality

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/ui-skills/SKILL.md

The canonical home for this skill is ui-skills in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

7%Scale 1-5

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

This skill is essentially a placeholder with no substantive content. It repeats its own description three times across different sections without providing any actual guidance, patterns, code examples, or actionable instructions. It fails on every dimension because it contains no real skill content—just a circular description and a link to an external repository.

Suggestions

Add concrete UI patterns, constraints, or rules that Claude should follow when building interfaces (e.g., specific component patterns, accessibility requirements, styling conventions).

Include at least one executable code example showing a preferred UI pattern versus an anti-pattern.

Define a clear workflow for how Claude should approach building UI components, including validation steps (e.g., accessibility checks, responsive design verification).

Either inline the actual content from the source repository or create bundle files with detailed reference material and link to them from the SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	The content is padded with repetitive, circular descriptions that restate the same vague phrase ('opinionated, evolving constraints to guide agents when building interfaces') three times without adding any substance. It's not extensively verbose in length, but every line is essentially filler.	2 / 5
Actionability	There is zero concrete guidance—no code, no commands, no specific patterns, no examples, no steps. The entire content is a vague description that points to an external repository without providing any actionable instructions.	1 / 5
Workflow Clarity	There are no steps, no sequence, no workflow of any kind. The skill provides no process to follow whatsoever.	1 / 5
Progressive Disclosure	There are no bundle files, no referenced supporting documents, and the only link is to an external GitHub repository with no indication of what it contains. The content itself has section headers but they contain no meaningful content to organize.	1 / 5
	Total	5 / 20 Passed

Description

11%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.

This description is too abstract and meta to be useful for skill selection. It reads more like a philosophical tagline than a functional description — it doesn't specify what actions the skill enables, what technologies or domains it covers, or when Claude should select it. The lack of concrete actions, trigger terms, and a 'Use when...' clause makes it nearly impossible for Claude to reliably choose this skill from a pool of alternatives.

Suggestions

Replace abstract language with concrete actions, e.g., 'Provides design guidelines and component patterns for building web UIs, including layout rules, accessibility standards, and styling conventions.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when building UI components, designing layouts, creating frontends, or when the user asks about interface design patterns.'

Specify the type of interfaces (web, mobile, desktop) and any frameworks or technologies involved to reduce overlap with other skills.

Dimension	Reasoning	Score
Specificity	The description is entirely vague with no concrete actions. 'Opinionated, evolving constraints to guide agents' does not describe any specific capability like 'generates components', 'applies design patterns', or 'validates layouts'. It reads as abstract meta-language.	1 / 5
Completeness	The 'what' is extremely vague ('constraints to guide agents') and there is no 'when' clause at all. It fails to answer either question concretely — what does this skill do, and when should Claude use it?	1 / 5
Trigger Term Quality	The only potentially useful trigger term is 'interfaces', which is extremely broad. Terms like 'opinionated', 'evolving constraints', and 'guide agents' are not phrases a user would naturally say when requesting UI/interface help. Missing natural terms like 'UI', 'frontend', 'components', 'design system', 'React', etc.	2 / 5
Distinctiveness Conflict Risk	'Building interfaces' is very broad and could overlap with any UI, frontend, design system, or component library skill. The term 'constraints' is unusual but doesn't help distinguish it since it doesn't clarify what kind of interfaces or what the constraints cover.	2 / 5
	Total	6 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/ui-skills/SKILL.md
Commit: debb2ec

Reviewed: 12 hours 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.