CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-ref-react-patterns

React/Next.js component design patterns, state management strategies, and project structure reference for frontend development. Agent-extending skill that amplifies frontend domain work (spawned via Agent(general-purpose) with frontend instructions) with production-grade React patterns. NOT for: backend API design, database modeling, DevOps, mobile apps.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/moai-ref-react-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A lean, well-organized reference skill: dense tables, a concrete decision flow for state management, explicit quality standards, and verification checklists, with no fluff or background exposition. Its main gaps are the complete absence of code examples and mild duplication of rules across the standards, red-flags, and rationalizations sections.

Suggestions

Add one minimal executable snippet (e.g., a compound-component Context pattern or a custom hook extraction) so the most important patterns are copy-paste ready rather than described.

Deduplicate rules that appear in multiple sections — the 5-prop limit, memoization, and design-token rules each appear in Component Quality Standards, Red Flags, and/or Common Rationalizations.

DimensionReasoningScore

Conciseness

Dense tables, terse checklists, and a directory tree with no padding and no explanation of concepts Claude already knows, matching the 'efficient; minor instances that could be trimmed' anchor. Not anchor 5 because the 5-prop rule, memoization guidance, and design-token rule each recur across Component Quality Standards, Red Flags, and Common Rationalizations — a modest duplication of tokens.

4 / 5

Actionability

Concrete, named tooling per scenario (Zustand, React Query, nuqs, React Hook Form + Zod, @tanstack/react-virtual) plus a decision tree and numeric thresholds ('Under 200 lines', '5 or fewer props') make the guidance actionable without code. It falls short of anchor 5 because there are no code or snippet examples anywhere (e.g., a compound-component Context sketch), and is above anchor 3 because nothing is pseudocode or vague.

4 / 5

Workflow Clarity

The state-management Decision Flow is an ordered, unambiguous procedure and the Verification section supplies an explicit end-state checklist. Not anchor 5 because there are no error-recovery/feedback loops, though none are required since the skill involves no destructive or batch operations; it is above anchor 3 because checkpoints (verification checklist, HTTP error handling table) are explicit rather than implicit.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so the single self-contained file with clear section headers, a table of pattern sections, and in-content evolvable markers is the correct structure. Anchor 4 rather than 5 because everything is inlined with no signaled reference structure, though the ~165-line body is compact enough that splitting is arguably unnecessary.

4 / 5

Total

16

/

20

Passed

Description

70%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.

A specific, well-bounded description with strong distinctiveness thanks to an explicit NOT-for clause, weakened by the absence of any 'Use when...' trigger guidance inside the description field itself. Third-person voice is maintained throughout. The trigger sentence exists only in a separate when_to_use frontmatter key rather than in the description that gets surfaced for skill matching.

Suggestions

Fold a 'Use when...' clause into the description field itself (e.g., 'Use when designing React or Next.js components, choosing state management, or structuring a frontend project'), rather than relying solely on the separate when_to_use key.

Add one or two concrete action verbs (e.g., 'Selects state management libraries', 'Structures Next.js App Router projects') to shift the description from topic labels toward operations.

Include a couple of natural synonyms such as 'hooks' or 'component composition' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names 'component design patterns, state management strategies, and project structure' — several specific capability areas with only minor gaps. It falls short of anchor 5 because capabilities are stated as topics ('patterns', 'strategies', 'reference') rather than the multiple concrete operations of the top example, and above anchor 3 because it covers more than 1-2 actions.

4 / 5

Completeness

The 'what' is clear (React/Next.js component patterns, state management, project structure), but the description field contains no 'Use when...' clause or equivalent trigger phrase — trigger guidance lives only in the separate when_to_use frontmatter key. Per the judging guideline, missing explicit trigger guidance caps this at 3; it is above anchor 2 because the 'what' is specific, not vague.

3 / 5

Trigger Term Quality

'React/Next.js', 'component design', 'state management', 'frontend' are natural phrases a user would say, giving good keyword coverage. Not anchor 5 because common synonyms and related trigger words (e.g., 'hooks', 'props', file/module terms) are missing from the description field itself.

4 / 5

Distinctiveness Conflict Risk

A tightly-scoped React/Next.js frontend niche plus an explicit exclusion list ('NOT for: backend API design, database modeling, DevOps, mobile apps') gives clear, distinct triggers with minimal conflict risk, matching anchor 5. It is not anchor 4 because the negative boundary makes overlap with adjacent skills even less likely than the 'PDF and Word' example.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

modu-ai/moai-adk

Path

.claude/skills/moai-ref-react-patterns/SKILL.md

Reviewed

Table of Contents

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.