CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

svelte-core-bestpractices

Guidance on writing fast, robust, modern Svelte code. Load this skill whenever in a Svelte project and asked to write/edit or analyze a Svelte component or module. Covers reactivity, event handling, styling, integration with libraries and more.

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-crafted best-practices skill body: lean, directive, with do/don't code contrasts and a comprehensive legacy-to-modern mapping. Its structure is exemplary — core guidance inline with nine clearly signaled, verified, one-level-deep references. The only improvements are minor: a few sections could trade definitional sentences for examples, and the Context section lacks a code sample.

DimensionReasoningScore

Conciseness

The body is lean and directive — short sections, minimal code, do/don't contrasts — with only minor over-explanation (definitional openers like 'Snippets are a way to define reusable chunks of markup' and 'The CSS in a component's <style> is scoped to that component'). The '5.36 or higher' version mention is time-sensitive but legitimately gates an experimental feature, so it stays at 'efficient; minor instances that could be trimmed' rather than anchor 5.

4 / 5

Actionability

Mostly executable guidance: do/don't code pairs for $derived and $props, concrete syntax for events, snippets, style: directives, and a complete modern-replacement mapping list ('use $state instead of implicit reactivity', 'use {@attach ...} instead of use:action'). Minor gaps keep it below anchor 5 — the Context section names createContext without an example, and several snippets use {...} placeholders rather than copy-paste-ready code.

4 / 5

Workflow Clarity

This is a topic-reference skill, not a multi-step process, and it involves no destructive or batch operations, so the validation cap does not apply. Each section gives unambiguous directives ('Only use the $state rune for variables that should be reactive', 'Never wrap the contents of an effect in if (browser)'), and the 'Avoid legacy features' section is a clear checklist. It sits at 'clear guidance with minor gaps' rather than 5 because a few sections (Context, Async Svelte) are pointers/guidance without concrete sequencing or examples.

4 / 5

Progressive Disclosure

Core guidance is inline while nine detailed topics are split into one-level-deep reference files, each clearly signaled as an inline markdown link at its point of use (e.g. 'use [{@attach ...}](references/attach.md)', '[keyed each blocks](references/each.md)'). All referenced paths exist in references/ and contain no nested local references (only external svelte.dev links), matching the anchor 'clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation'.

5 / 5

Total

17

/

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 solid description with an explicit, well-targeted trigger clause and clear Svelte-specific distinctiveness. Its main weakness is the 'what' side: generic verbs and a padded topic list ('and more') instead of concrete capabilities. Trigger coverage is good but misses common variations like '.svelte' or 'SvelteKit'.

Suggestions

Replace 'Guidance on writing fast, robust, modern Svelte code' with concrete capabilities, e.g. 'Write Svelte 5 components using runes ($state, $derived, $effect, $props), snippets, and modern event/style syntax instead of legacy features'.

Drop the vague 'and more' from the coverage list; either enumerate the remaining topics or end the list cleanly.

Add natural trigger variations users would say, such as '.svelte files', 'SvelteKit', or 'Svelte 5', to strengthen trigger matching.

DimensionReasoningScore

Specificity

The verbs are generic ('write/edit or analyze') rather than concrete capabilities, and while topic areas are named ('reactivity, event handling, styling, integration with libraries'), the trailing 'and more' leaves coverage open-ended. This matches 'names domain and 1-2 concrete actions, but not comprehensive' better than anchor 4, which expects several specific listed actions.

3 / 5

Completeness

Both parts are present: an explicit when-clause ('Load this skill whenever in a Svelte project and asked to write/edit or analyze a Svelte component or module') and a what ('Guidance on writing fast, robust, modern Svelte code... Covers reactivity, event handling, styling, integration with libraries'). The what is somewhat general and 'fast, robust, modern' edges toward buzzword, keeping it below the fully concrete anchor 5.

4 / 5

Trigger Term Quality

Includes natural terms users would say — 'Svelte project', 'Svelte component', 'Svelte module' — plus topic keywords (reactivity, event handling, styling, libraries). A few natural terms are missing (e.g. '.svelte', 'SvelteKit', 'Svelte 5'), so it does not reach comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The description is firmly scoped to Svelte components/modules in Svelte projects, a clear niche with distinct triggers; overlap risk is limited to other Svelte-specific skills. It clearly matches 'clear niche with distinct triggers; minimal conflict risk'.

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

chattocorp/chatto

Path

.agents/skills/svelte-core-bestpractices/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.