CtrlK
BlogDocsLog inGet started
Tessl Logo

svelte5

Reviews Svelte components for idiomatic patterns, identifies anti-patterns carried over from React/Vue/Svelte 4, and suggests Svelte 5 refactorings. Use when writing or reviewing Svelte components, asking "is this idiomatic", "Svelte way", doing Svelte 5 migration, or encountering smells like: effect assigns state, prop copied to $state, global store by default, $bindable everywhere, clickable div, createEventDispatcher, export let, on:click, slot-shaped APIs, lifecycle-driven code, imperative DOM wiring, immutable-update ceremony, context value replacement, shadcn-svelte form structure, Field.* components, bits-ui form controls, or component APIs that hide ownership. This is the general-purpose entry point for Svelte component review; delegates to sveltekit for routes/load/actions/server concerns and to focused references for details.

100

1.12x
Quality

100%

Does it follow best practices?

Impact

100%

1.12x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is an exceptionally well-crafted skill that serves as a model for how to structure a review-oriented SKILL.md. It is concise yet comprehensive, with numbered principles that each link to deeper references, concrete before/after code examples, a clear review workflow, and a scannable smell index. The progressive disclosure is excellent — the main file changes Claude's defaults while delegating detailed guidance to focused reference files.

DimensionReasoningScore

Conciseness

The skill is remarkably efficient — it assumes Claude already knows Svelte syntax and focuses entirely on changing defaults and identifying anti-patterns. Every section earns its place: principles are numbered and terse, code examples are minimal but illustrative, and the smell index is a compact lookup table rather than verbose prose.

3 / 3

Actionability

Each principle includes concrete before/after Svelte code examples that are executable and copy-paste ready. The 'Running a Review' section gives a specific 4-step process with clear instructions (check package.json, scan smell index, judge performance on evidence, shape output by priority). The smell index maps specific code patterns to specific references.

3 / 3

Workflow Clarity

The 'Running a Review' section provides a clear 4-step sequence: detect version → apply principles and scan smells → judge performance on evidence → shape output with priority ordering. The workflow includes validation (check package.json first, open linked reference before proposing rewrites) and appropriate guardrails (don't recommend Svelte 5 syntax in Svelte 4 projects, judge performance only on evidence).

3 / 3

Progressive Disclosure

The skill is an exemplary overview document: each principle is a concise summary with a link to a dedicated reference file for details. The smell index serves as a second navigation layer mapping symptoms to references. Cross-references to the sveltekit skill are clearly signaled. Content is appropriately split — the main file teaches defaults while references carry the depth. However, no bundle files were provided to verify the references actually exist, but the structure itself is well-designed.

3 / 3

Total

12

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that thoroughly covers what the skill does, when to use it, and how it relates to adjacent skills. It provides an extensive list of specific trigger terms and anti-patterns that would help Claude accurately select this skill. The explicit delegation note to sveltekit for related but distinct concerns further reduces conflict risk.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: reviews components for idiomatic patterns, identifies anti-patterns from React/Vue/Svelte 4, suggests Svelte 5 refactorings. Also enumerates many specific code smells like 'effect assigns state', 'prop copied to $state', 'createEventDispatcher', 'export let', etc.

3 / 3

Completeness

Clearly answers both 'what' (reviews Svelte components, identifies anti-patterns, suggests refactorings) and 'when' with an explicit 'Use when...' clause listing multiple trigger scenarios. Also clarifies delegation boundaries to other skills (sveltekit for routes/load/actions).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'is this idiomatic', 'Svelte way', 'Svelte 5 migration', plus very specific code-level terms like 'createEventDispatcher', 'export let', 'on:click', 'slot-shaped APIs', '$bindable', 'shadcn-svelte', 'bits-ui'. These are terms a developer would naturally use when seeking Svelte review help.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche (Svelte 5 component review specifically), and explicitly delineates boundaries by noting it delegates to 'sveltekit for routes/load/actions/server concerns'. The extensive list of Svelte-specific anti-patterns and terms makes it very unlikely to conflict with other skills.

3 / 3

Total

12

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
joshuadavidthomas/agent-skills
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.