CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-domain-frontend

Frontend development specialist covering React 19, Next.js 16, Vue 3.5, and modern UI/UX patterns with component architecture. Use when building web UIs, implementing components, optimizing frontend performance, or integrating state management.

Quality

72%

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-domain-frontend/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 body is well-sectioned and list-based, with a useful Red Flags/Verification pairing, but it reads as a catalog: no executable code anywhere despite being a code-centric domain, no workflow sequence, and no reference files to carry the detailed material it alludes to. The core fix is converting the prose quickstarts into code blocks and moving deep material (Vercel rules, pattern catalogs) into referenced files.

Suggestions

Replace the prose 'Implementation Quickstart' sections with actual executable code blocks — a React 19 server component, a Next.js server action with zod, a useUser composable, and a CVA Button — so the guidance is copy-paste ready instead of narrated.

Move the Vercel React Best Practices (45 rules) and the framework pattern catalogs into files under references/ and link to them explicitly (e.g., 'See [vercel-react-rules.md](references/vercel-react-rules.md)'), turning the currently dangling summary into a well-signaled one-level-deep reference.

Add a short sequenced workflow for common tasks (e.g., build component → verify accessibility/state handling via the checklist → re-run checks after fixes) that wires the Verification checklist into an explicit validate-and-retry loop.

DimensionReasoningScore

Conciseness

The body is mostly terse lists, but the 'Implementation Quickstart' sections spend prose describing code that terse code blocks would convey ("Create an async page component that uses the cache function from React to memoize data fetching. Import Suspense for loading states..."), and the 'Vercel React Best Practices' section summarizes 45 rules in eight bullet lines without pointing anywhere. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 4, which expects only minor trims.

3 / 5

Actionability

The quickstart gives detailed, specific guidance (named functions, validation rules, variant options like "sm (h-9, px-3, text-sm)") but contains zero executable code blocks — the code is narrated in prose ("The createPost function accepts FormData, validates with safeParse, returns errors on failure"), which is effectively pseudocode with missing key details. Not 2 because the prose is far more specific than high-level hints; not 4 because nothing is copy-paste ready for a code-centric skill.

3 / 5

Workflow Clarity

There is no sequenced multi-step workflow at all — the body is reference material organized by topic — and while the 'Verification' checklist supplies explicit checkpoints, there is no validate→fix→retry feedback loop connecting it to any process. This matches 'sequence present but checkpoints missing or implicit' territory; it is above 2 only because the section ordering (capabilities → patterns → implementation → verification) gives a coherent reading order.

3 / 5

Progressive Disclosure

Section structure is present and reasonably organized, but the skill ships no bundle files (no references/, scripts/, or assets/), and content that clearly belongs in separate files is inlined or dangled: the 'Vercel React Best Practices' section advertises "45 rules across 8 categories from Vercel Engineering" with no link or file to read them from, and the pattern lists (~100 lines of catalog) sit entirely in SKILL.md. This fits 'some structure but could be better organized; content that should be separate is inline' rather than 4's 'most content is appropriately placed'.

3 / 5

Total

12

/

20

Passed

Description

83%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 strong description: third-person voice, explicit 'what' and 'when', concrete trigger phrases, and named frameworks. The main residual gaps are a slightly generic action list and missing common synonym/extension trigger terms.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "building web UIs, implementing components, optimizing frontend performance, or integrating state management" — plus named frameworks (React 19, Next.js 16, Vue 3.5), matching the 'several specific actions; minor gaps in coverage' anchor. It falls short of 5 because the actions stay at the level of activity categories rather than varied concrete deliverables (e.g., no mention of hooks, SSR migration, styling systems).

4 / 5

Completeness

Both halves are explicit: the 'what' ("Frontend development specialist covering React 19, Next.js 16, Vue 3.5, and modern UI/UX patterns with component architecture") and a concrete 'when' clause ("Use when building web UIs, implementing components, optimizing frontend performance, or integrating state management"). This mirrors the anchor-5 example's structure of a clear what plus explicit trigger phrases, so 4's caveat ('when' could be more explicit) does not apply.

5 / 5

Trigger Term Quality

Natural user phrasings like "building web UIs", "implementing components", "frontend performance", and "state management" are present alongside framework names (React, Next.js, Vue), giving good keyword coverage. Not 5: misses common synonyms and file-level cues users would say (e.g., "web app", "SPA", .tsx/.jsx, "responsive", "landing page").

4 / 5

Distinctiveness Conflict Risk

The frontend-development niche with named frameworks and explicit triggers is mostly distinct. It stays at 4 rather than 5 because the domain is broad and overlaps with closely related skills the body itself acknowledges (moai-ref-ui-polish for UI/UX and component libraries, moai-workflow-testing), so a generic styling or web-development skill could still compete for the same triggers.

4 / 5

Total

17

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

modu-ai/moai-adk

Path

.claude/skills/moai-domain-frontend/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.