CtrlK
BlogDocsLog inGet started
Tessl Logo

jbvc/frontend-patterns

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

49

Quality

49%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Discovery

32%

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 identifies the technology domain (React/Next.js frontend) but reads more like a topic list than an actionable skill description. It lacks concrete actions (verbs), has no 'Use when...' clause, and uses broad category terms rather than specific capabilities. It would benefit significantly from specifying what actions the skill performs and when Claude should select it.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about React components, Next.js routing, frontend performance, or building UI interfaces.'

Replace abstract category names with concrete actions, e.g., 'Creates React components, configures Next.js routing and SSR, implements state management with hooks/Redux, and optimizes frontend performance (code splitting, lazy loading).'

Include more natural trigger terms users would say, such as 'components', 'hooks', 'SSR', 'client-side rendering', 'CSS', 'Tailwind', 'responsive design', '.tsx files'.

DimensionReasoningScore

Specificity

Names the domain (frontend development) and lists some areas (React, Next.js, state management, performance optimization, UI best practices), but these are categories rather than concrete actions. No specific verbs describing what the skill does (e.g., 'creates components', 'optimizes bundle size').

2 / 3

Completeness

Describes the 'what' at a high level (frontend development patterns) but completely lacks any 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent, which per the rubric should cap completeness at 2, and the 'what' itself is weak enough to warrant a 1.

1 / 3

Trigger Term Quality

Includes relevant keywords like 'React', 'Next.js', 'state management', 'performance optimization', and 'UI' that users might naturally mention. However, it misses common variations and related terms like 'components', 'hooks', 'CSS', 'rendering', 'TypeScript', 'Redux', 'Tailwind', etc.

2 / 3

Distinctiveness Conflict Risk

Mentioning React and Next.js specifically provides some distinctiveness, but 'frontend development patterns' and 'UI best practices' are broad enough to overlap with general coding skills, CSS skills, or other web development skills.

2 / 3

Total

7

/

12

Passed

Implementation

42%

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 React patterns cookbook that teaches Claude things it already knows well — standard composition patterns, hooks, memoization, error boundaries, and accessibility. While the code examples are high quality and executable, the sheer volume (~500+ lines of common React patterns) wastes context window without providing project-specific value. The content would benefit enormously from being condensed to project-specific conventions and splitting detailed examples into referenced files.

Suggestions

Reduce to project-specific conventions only (e.g., 'We use Zustand over Context for global state', 'Our Card components follow this specific API') rather than teaching generic React patterns Claude already knows.

Split detailed code examples into separate referenced files (e.g., HOOKS.md, COMPONENTS.md, ACCESSIBILITY.md) and keep SKILL.md as a concise overview with navigation links.

Add a decision framework or flowchart for when to use which pattern (e.g., 'Use Context+Reducer for <3 consumers, Zustand for global state') to provide actual workflow guidance.

Remove patterns that are standard React knowledge (ErrorBoundary, useDebounce, React.memo usage) unless there are project-specific conventions around them.

DimensionReasoningScore

Conciseness

This is extremely verbose at ~500+ lines, mostly consisting of well-known React patterns (composition, compound components, render props, context+reducer, error boundaries, memoization, debounce hooks) that Claude already knows thoroughly. Almost every pattern here is standard React documentation material that adds no novel project-specific knowledge.

1 / 3

Actionability

The code examples are fully executable TypeScript/React components with complete implementations, proper typing, and usage examples. Every pattern includes copy-paste ready code.

3 / 3

Workflow Clarity

The 'When to Activate' section provides clear triggers, and patterns are logically grouped. However, there's no guidance on when to choose one pattern over another, no decision tree for complexity levels, and no validation/testing steps for the patterns being implemented.

2 / 3

Progressive Disclosure

This is a monolithic wall of code examples with no references to external files. The massive amount of inline code (error boundaries, form handling, animations, accessibility, state management, hooks) should be split into separate reference files with a concise overview in the main SKILL.md.

1 / 3

Total

7

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (642 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

Passed

Reviewed

Table of Contents