better-icons

Search, compare, and extract SVG icons from Iconify collections. Use when the user needs production-ready UI icons, icon family consistency, or exact SVG markup.

Quality

73%

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 ./Skills/frontend-ui/better-icons/SKILL.md

Quality

Content

60%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 content is well-structured and concisely written with a clear validation-gated workflow, but it is materially weak on actionability: the actual Iconify search/extract mechanics are never specified, leaving Claude with process scaffolding instead of executable guidance.

Suggestions

Add at least one concrete Iconify command or API example (e.g., the `@iconify/json` lookup or `iconify-icon` extraction call) so the core action is executable, not just described.

Flesh out the Workflow steps with the specific Iconify operations each step performs rather than abstract directives like 'take the smallest action'.

Either reference the local bundle files (contract.yaml/evals.yaml) from the body or clarify how the archived directory relates to them, so progressive disclosure navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean, sectioned, and avoids explaining concepts Claude already knows, but the generic Philosophy and Anti-Patterns bullets are abstract boilerplate that could be trimmed, keeping it at 4 rather than 5.	4 / 5
Actionability	Inputs and outputs are enumerated, but the skill never provides a concrete Iconify command, API call, or extraction method — only high-level process hints ("Take the smallest action that advances the confirmed goal"), matching the 'minimal concrete guidance; missing specific steps to execute' anchor.	2 / 5
Workflow Clarity	The five-step workflow has explicit fail-fast checkpoints ("Stop at the first failed gate") and a rerun-validation feedback loop, but the individual steps are abstract rather than concrete, so it sits at 4 instead of 5.	4 / 5
Progressive Disclosure	A concise overview points one level deep to an archived context directory with a clear load-only-what-is-needed signal, but the local bundle files (contract.yaml, evals.yaml, task-profile.json) are not navigated from the body, leaving a minor organization gap.	4 / 5
	Total	14 / 20 Passed

Description

87%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 strong: third-person voice, explicit what-and-when structure, and a distinct Iconify niche. Its only weakness is slightly limited keyword breadth (no synonyms or file extensions).

Dimension	Reasoning	Score
Specificity	"Search, compare, and extract SVG icons from Iconify collections" names the domain plus three concrete actions, matching the 'several specific actions; minor gaps' anchor rather than the fully comprehensive 5-action example.	4 / 5
Completeness	It explicitly states both what ("Search, compare, and extract SVG icons from Iconify collections") and when ("Use when the user needs production-ready UI icons, icon family consistency, or exact SVG markup") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Phrases like "SVG icons", "production-ready UI icons", "icon family consistency", and "Iconify collections" are natural user language with good coverage, but common synonyms and file extensions are absent, landing at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	The Iconify-specific niche with distinct triggers (production-ready UI icons, family consistency, exact SVG markup) gives minimal overlap with other skills, fitting the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	18 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Skills/frontend-ui/better-icons/SKILL.md
Commit: f1f2f21

Reviewed: 2 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.