CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

vue-best-practices

MUST be used for Vue.js tasks. Strongly recommends Composition API with `<script setup>` and TypeScript as the standard approach. Covers Vue 3, SSR, Volar, vue-tsc. Load for any Vue, .vue files, Vue Router, Pinia, or Vite with Vue work. ALWAYS use Composition API unless the project explicitly requires Options API.

Quality

78%

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 ./skills/vue-best-practices/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured, well-routed instruction skill with concrete Vue-specific rules, a clear required workflow, and exemplary progressive disclosure (real, one-level-deep, condition-gated references). Its weaknesses are repetition of the boundary/decomposition philosophy across multiple sections and the absence of any code examples or explicit error-recovery steps in the self-check.

Suggestions

Consolidate the boundary/decomposition guidance (§1.2, 'Choose useful boundaries' in §2, and the related §5 checklist items) into a single section or a dedicated reference file — the same 'split by responsibility, hide useful complexity' idea currently appears three times.

Add one short executable verification step to the final self-check, e.g. 'type-check with vue-tsc and run the project's tests' with the actual commands, so the checklist has an explicit feedback loop rather than only criteria.

DimensionReasoningScore

Conciseness

Mostly efficient — no tutorials on what Vue is, and rules are stated as directives — but the decomposition/boundary philosophy is repeated across three places (§1.2 'Sketch responsibilities, state owners, and the contracts that cross their boundaries', §2 'Choose useful boundaries', and §5 'Both sides of the boundary review pass...'), and lines like 'Judge cohesion by behavior that changes together or maintains a shared invariant' restate general design knowledge Claude already has. Anchor 3 fits: could be tightened; not anchor 2 because there are no heavily padded sections or basic-concept explanations, and not anchor 4 because ~40 lines of repeated boundary philosophy could be consolidated.

3 / 5

Actionability

Concrete, API-level directives throughout: 'Keep SFC sections in this order: `<script>` → `<template>` → `<style>`', 'Keep source state minimal (`ref`/`reactive`), derive everything possible with `computed`', 'Keep contracts explicit and typed with `defineProps`, `defineEmits`, and `InjectionKey`', plus condition-to-reference routing for optional features. It is below anchor 5 because the body contains no code examples and portions of the boundary guidance are abstract process direction, but above anchor 3 because the written guidance is specific and directly executable for an instruction-only skill.

4 / 5

Workflow Clarity

Clear ordered sequence ('Follow the workflow in order unless the user explicitly asks for a different order') with numbered required/optional phases, must-read references up front, and an explicit final checklist (§5 'Final self-check before finishing', 'Use the project's applicable tests'). Below anchor 5 because there is no error-recovery loop (what to do when a self-check fails) and no concrete verification command (e.g. running vue-tsc); not a destructive/batch skill, so no cap applies.

4 / 5

Progressive Disclosure

The body is a well-organized router: four must-read core references clearly signaled in §1.1, optional features mapped by requirement in §3 ('Do not add these by default. Load the matching reference only when the requirement exists'), and perf references keyed to symptoms in §4. All 22 referenced files exist in references/ and are exactly one level deep (reference files link only to external vuejs.org docs, not to each other), matching anchor 5.

5 / 5

Total

16

/

20

Passed

Description

73%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, trigger-rich description with explicit 'when' guidance and a distinct Vue-ecosystem niche. Its main weakness is that it states recommendations and coverage areas rather than enumerating the concrete capabilities the skill provides, and it ends with a redundant restatement of the Composition API policy.

Suggestions

Replace the policy phrasing ('Strongly recommends...') with one or two concrete capability statements, e.g. 'Provides best-practice guidance for Vue 3 components, reactivity, SFC structure, and composables using `<script setup>` + TypeScript.'

Drop the redundant trailing 'ALWAYS use Composition API unless the project explicitly requires Options API' sentence — it repeats the earlier recommendation and adds token cost without new trigger or capability information.

DimensionReasoningScore

Specificity

Names the domain and its recommended stack ('Strongly recommends Composition API with `<script setup>` and TypeScript', 'Covers Vue 3, SSR, Volar, vue-tsc') but lists coverage topics and policy stances rather than concrete actions the skill performs. It is above anchor 2 (which only names a domain) because the stack recommendation is concrete, but below anchor 4 because no several specific actions are enumerated.

3 / 5

Completeness

The 'when' is explicit and concrete ('MUST be used for Vue.js tasks... Load for any Vue, .vue files, Vue Router, Pinia, or Vite with Vue work'), and a 'what' is present via the recommended approach, but the what is phrased as a recommendation/policy rather than a clear statement of what the skill does (best-practices instruction for Vue development). Anchor 4 fits; anchor 5 requires the 'what' to be equally explicit, and the trailing 'ALWAYS use Composition API...' clause repeats earlier content instead.

4 / 5

Trigger Term Quality

Good natural keyword coverage: 'Vue', 'Vue.js tasks', '.vue files', 'Vue Router', 'Pinia', 'Vite with Vue', 'Composition API', 'Options API' — terms users would naturally say. Below anchor 5 because common variations like Nuxt, Vuex, Vue 2, or 'VueJS' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct ecosystem triggers ('Vue Router', 'Pinia', 'Vite with Vue') and even an explicit carve-out for the Options API exception, minimizing conflict with a sibling options-API skill. Anchor 4 would require notable overlap risk with closely related skills, which is not the case here.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

vuejs-ai/skills

Path

skills/vue-best-practices/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.