frontend-perf

성능 최적화 에이전트. 프론트엔드 성능을 분석하고 최적화합니다.

Quality

22%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/frontend-perf/SKILL.md

Quality

Content

22%

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

This skill content reads as a job description rather than actionable guidance. It lists what the agent does (bundle analysis, rendering optimization, Core Web Vitals) but provides zero concrete instructions, code examples, or tools for accomplishing these tasks. Claude already knows what performance optimization concepts are - this skill adds no new actionable knowledge.

Suggestions

Add executable code examples for each task (e.g., webpack-bundle-analyzer commands, React.memo patterns, Lighthouse CLI usage)

Define a clear workflow: analyze -> identify bottlenecks -> apply fixes -> validate improvements with specific tool commands

Include concrete metrics thresholds and validation steps (e.g., 'LCP should be under 2.5s, verify with: npx lighthouse --only-categories=performance')

Reference or create detailed guides for each optimization area (BUNDLE_ANALYSIS.md, RENDERING.md, etc.) with specific techniques

Dimension	Reasoning	Score
Conciseness	The content is brief but lacks substance - it's more of a role description than actionable skill content. While not verbose, it doesn't provide enough value to justify its tokens.	2 / 3
Actionability	Extremely vague with no concrete code, commands, or examples. Lists tasks like 'bundle size analysis' and 'memoization' without any executable guidance on how to perform them.	1 / 3
Workflow Clarity	No workflow or process defined. Simply lists responsibilities without any sequence, steps, or validation checkpoints for performance optimization tasks.	1 / 3
Progressive Disclosure	Mentions output location (docs/performance/) but provides no actual references to detailed guides, tools, or examples. Structure exists but content is missing.	2 / 3
	Total	6 / 12 Passed

Description

22%

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 brief and vague to effectively guide skill selection. It lacks specific concrete actions, natural trigger terms users would say, and most critically has no 'Use when...' clause to indicate when Claude should select this skill. The Korean language is fine but the content needs substantial improvement.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user mentions slow page loads, Core Web Vitals, lighthouse scores, bundle size, or render performance'

List specific concrete actions such as 'Analyzes bundle sizes, identifies render-blocking resources, optimizes images, implements lazy loading, improves Core Web Vitals scores'

Include natural trigger terms users would say: 'slow website', 'page speed', 'lighthouse', 'performance audit', 'load time', 'FCP', 'LCP', 'CLS'

Dimension	Reasoning	Score
Specificity	The description uses vague language like '분석하고 최적화합니다' (analyzes and optimizes) without listing any concrete actions. No specific capabilities like 'bundle size reduction', 'lazy loading', or 'render optimization' are mentioned.	1 / 3
Completeness	Only weakly addresses 'what' (analyzes and optimizes frontend performance) and completely lacks a 'when' clause. No explicit trigger guidance like 'Use when...' is provided.	1 / 3
Trigger Term Quality	Contains '프론트엔드 성능' (frontend performance) and '최적화' (optimization) which are relevant domain keywords, but lacks common variations users might say like 'slow page', 'load time', 'Core Web Vitals', 'lighthouse', or 'bundle size'.	2 / 3
Distinctiveness Conflict Risk	Specifies 'frontend performance' which narrows the domain somewhat, but could still overlap with general code optimization skills, build tools, or debugging skills. Not distinct enough to avoid conflicts.	2 / 3
	Total	6 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: shaul1991/shaul-agents-plugin
Commit: 9242c58

Reviewed: 4 months 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.