vue-skills is a collection of add-ons that provide guidance for developing Vue 3 applications, covering APIs, routing, state management, testing, JSX, and debugging. Vue developers use them to help AI agents apply framework-specific patterns and address common implementation problems. The catalogue entries are individual Vue development skills and instructions.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vuejs-ai/skills --skill vue-debug-guidesgit clone --depth 1 https://github.com/vuejs-ai/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vuejs-ai/skills/vue-debug-guides)<a href="https://agentmods.dev/skills/vuejs-ai/skills/vue-debug-guides"><img src="https://agentmods.dev/badge/skills/vuejs-ai/skills/vue-debug-guides/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vuejs-ai/skills/vue-debug-guides"><img src="https://agentmods.dev/badge/skills/vuejs-ai/skills/vue-debug-guides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.04393 |
| Opus 5 | $0.00018 | $0.02197 |
| Sonnet 5 | $0.00007 | $0.00879 |
| Haiku 4.5 | $0.00004 | $0.00439 |
Grade A, and why
vue-debug-guides scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vue 3 debugging and error handling for runtime issues, warnings, async failures, and hydration bugs.
For development best practices and common gotchas, use vue-best-practices.
Reactivity
- Tracing unexpected re-renders and state updates → See reactivity-debugging-hooks
- Ref values not updating due to missing .value access → See ref-value-access
- State stops updating after destructuring reactive objects → See reactive-destructuring
- Refs inside arrays, Maps, or Sets not unwrapping → See refs-in-collections-need-value
- Nested refs rendering as [object Object] in templates → See template-ref-unwrapping-top-level
- Reactive proxy identity comparisons always return false → See reactivity-proxy-identity-hazard
- Third-party instances breaking when proxied → See reactivity-markraw-for-non-reactive
- Watchers only firing once per tick unexpectedly → See reactivity-same-tick-batching
Computed
- Computed getter triggers mutations or requests unexpectedly → See computed-no-side-effects
- Mutating computed values causes changes to disappear → See computed-return-value-readonly
- Computed value never updates after conditional logic → See computed-conditional-dependencies
- Sorting or reversing arrays breaks original state → See computed-array-mutation
- Passing parameters to computed properties fails → See computed-no-parameters
Watchers
- Async operations overwriting with stale data → See watch-async-cleanup
- Creating watchers inside async callbacks → See watch-async-creation-memory-leak
- Watcher never triggers for reactive object properties → See watch-reactive-property-getter
- Async watchEffect misses dependencies after await → See watcheffect-async-dependency-tracking
- DOM reads are stale inside watcher callbacks → See watch-flush-timing
- Deep watchers report identical old/new values → See watch-deep-same-object-reference
- watchEffect runs before template refs update → See watcheffect-flush-post-for-refs
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/animation-key-for-rerender.md 4.5 KB
- reference/animation-transitiongroup-performance.md 5.7 KB
- reference/async-component-error-handling.md 3.2 KB
- reference/async-component-keepalive-ref-issue.md 2.8 KB
- reference/async-component-suspense-control.md 2.1 KB
- reference/async-component-vue-router.md 2.8 KB
- reference/attrs-event-listener-merging.md 4.6 KB
- reference/checkbox-true-false-value-form-submission.md 3.4 KB
- reference/cleanup-side-effects.md 4.2 KB
- reference/click-events-on-components.md 4.6 KB
- reference/component-naming-conflicts.md 4.4 KB
- reference/component-ref-requires-defineexpose.md 4.1 KB
- reference/composable-avoid-hidden-side-effects.md 5.7 KB
- reference/composable-call-location-restrictions.md 4.8 KB
- reference/composable-naming-return-pattern.md 3.9 KB
- reference/composable-tovalue-inside-watcheffect.md 5.1 KB
- reference/composition-api-not-functional-programming.md 3.8 KB
- reference/composition-api-script-setup-async-context.md 5.2 KB
- reference/composition-api-vs-react-hooks-differences.md 4.8 KB
- reference/computed-array-mutation.md 4.3 KB
- reference/computed-conditional-dependencies.md 4.3 KB
- reference/computed-no-parameters.md 4.4 KB
- reference/computed-no-side-effects.md 3.2 KB
- reference/computed-return-value-readonly.md 4.0 KB
- reference/configure-app-before-mount.md 2.7 KB
- reference/declare-emits-for-documentation.md 5.0 KB
- reference/define-expose-before-await.md 4.2 KB
- reference/define-model-default-value-sync.md 4.0 KB
- reference/defineEmits-must-be-top-level.md 4.1 KB
- reference/defineEmits-no-runtime-and-type-mixed.md 4.2 KB
- reference/definemodel-object-mutation-no-emit.md 4.0 KB
- reference/dom-update-timing-nexttick.md 2.7 KB
- reference/dynamic-argument-constraints.md 4.2 KB
- reference/dynamic-component-registration-vite.md 4.2 KB
- reference/event-modifier-order-matters.md 2.7 KB
- reference/exact-modifier-for-precise-shortcuts.md 4.3 KB
- reference/fallthrough-attrs-overwrite-vue3.md 3.8 KB
- reference/in-dom-template-parsing-caveats.md 4.4 KB
- reference/inheritattrs-false-for-wrapper-components.md 4.4 KB
- reference/keepalive-router-nested-double-mount.md 5.0 KB
- reference/keepalive-transition-memory-leak.md 3.5 KB
- reference/keyup-modifier-timing.md 4.2 KB
- reference/lifecycle-dom-access-timing.md 5.1 KB
- reference/lifecycle-hooks-synchronous-registration.md 3.8 KB
- reference/lifecycle-ssr-awareness.md 5.0 KB
- reference/local-components-not-in-descendants.md 3.7 KB
- reference/mount-return-value.md 2.6 KB
- reference/multi-root-component-class-attrs.md 2.4 KB
- reference/native-event-collision-with-emits.md 4.4 KB
- reference/no-passive-with-prevent.md 3.7 KB
- reference/no-v-if-with-v-for.md 3.8 KB
- reference/perf-computed-object-stability.md 4.7 KB
- reference/perf-props-stability-update-optimization.md 3.7 KB
- reference/plugin-global-properties-sparingly.md 3.4 KB
- reference/plugin-install-before-mount.md 3.1 KB
- reference/plugin-prefer-provide-inject-over-global-properties.md 3.4 KB
- reference/plugin-typescript-type-augmentation.md 4.1 KB
- reference/prop-defineprops-scope-limitation.md 3.6 KB
- reference/provide-inject-debugging-challenges.md 5.5 KB
- reference/provide-inject-default-value-factory.md 5.6 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 203 lines · 36 tokens per session scan A c39cee74b0b6
vue-debug-guides is a skill published in the GitHub repository vuejs-ai/skills (2,836 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 4,393 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
error-tracking-svelte
PostHog error tracking for Svelte.
vite-mcp-next
Use when debugging Vite + Vue local pages with vite-plugin-vue-mcp-next MCP, including DOM, screenshots, console logs, network requests, Vue components, router, or Pinia state.
vite-browser-core-debug
Core troubleshooting workflow for Vue/React/Svelte Vite apps using vite-browser. Use this for first-pass debugging when the user reports broken UI behavior, wrong component state, router/store confusion, or a vague "page is broken" symptom and the dominant failure mode is not yet known.
solid-core-reactivity-model
Use when reasoning about SolidJS reactivity, debugging tracking issues, or understanding why components run once. Prevents React mental model contamination such as expecting re-renders, virtual DOM diffing, or stale closure patterns. Covers reactive dependency graph, tracking contexts, ownership tree, synchronous…
error-tracking-nuxt
PostHog error tracking for Nuxt.
nuxt4-patterns
Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData. Use when building or reviewing a Nuxt 4 app, or debugging hydration mismatches and SSR-safe data fetching.