svelte5

Mental-model reset for Svelte 5. Use when writing or reviewing Svelte components to shift from "it works" to "thinks in Svelte." Triggers on Svelte code review, "is this idiomatic", "Svelte way", Svelte 5 migration, or smells carried over from React/Vue/Svelte 4 — 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.

1.35x

Quality

80%

Does it follow best practices?

Impact

100%

1.35x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./svelte5/SKILL.md

Quality

Discovery

89%

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 a strong skill description with excellent trigger term coverage and clear scope boundaries. Its main weakness is that the core capability is described somewhat abstractly ('mental-model reset') rather than listing concrete actions the skill performs. The extensive anti-pattern enumeration serves as excellent trigger terms but partially compensates for the lack of explicit action verbs describing what the skill outputs or produces.

Suggestions

Replace the abstract 'mental-model reset' framing with concrete actions like 'Reviews Svelte components for idiomatic patterns, identifies anti-patterns carried from React/Vue/Svelte 4, and suggests Svelte 5 refactorings.'

Dimension	Reasoning	Score
Specificity	The description names the domain (Svelte 5 components) and mentions several specific anti-patterns and code smells (effect assigns state, prop copied to $state, etc.), but the core action is vaguely described as 'mental-model reset' rather than listing concrete actions like 'refactor components', 'identify anti-patterns', or 'migrate syntax'. The specificity is in the triggers, not in what the skill actually does.	2 / 3
Completeness	Clearly answers both 'what' (mental-model reset for Svelte 5, shifting from 'it works' to 'thinks in Svelte') and 'when' with an explicit 'Use when' clause and detailed trigger conditions. It also clarifies scope boundaries by noting delegation to 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', 'Svelte code review', plus an extensive list of specific anti-patterns and legacy syntax (export let, on:click, createEventDispatcher, slot-shaped APIs) that users would naturally mention when seeking help with Svelte modernization.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche (Svelte 5 idiomatic component review) and explicit boundary-drawing with related skills (delegates to sveltekit for routes/load/actions). The extensive list of Svelte-specific anti-patterns and the 'general-purpose entry point' framing make it very unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Implementation

70%

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

This is a well-structured mental-model skill that clearly articulates Svelte 5 idioms and anti-patterns with excellent progressive disclosure to reference files. Its main weakness is the triple/quadruple repetition of the same concepts across numbered principles, common mistakes, the quick reference table, and the review checklist — which inflates token cost substantially. Adding a few concrete before/after code examples would significantly improve actionability for a skill about writing code.

Suggestions

Add 2-3 concrete before/after code examples for the most common failure modes (e.g., $effect writing state → $derived, prop mirroring → derivation, createEventDispatcher → callback prop) to improve actionability.

Consolidate the four overlapping sections (principles, common mistakes, quick reference table, review checklist) — consider merging common mistakes into the quick reference table and trimming the review checklist to only items not already covered, to reduce redundancy and token cost.

Dimension	Reasoning	Score
Conciseness	The skill is well-organized and avoids explaining basic Svelte syntax, but there is significant repetition across the three sections (numbered principles, common mistakes, and quick reference table) that cover largely the same ground three times. The review checklist adds a fourth pass over the same material. This redundancy inflates token count without proportional value.	2 / 3
Actionability	The skill provides clear, specific guidance on what to do and what to avoid (e.g., 'use $derived not $effect for computed state', 'use callback props not createEventDispatcher'), but lacks executable code examples. For a skill about writing Svelte components, concrete before/after code snippets would significantly improve actionability. The guidance is specific but descriptive rather than executable.	2 / 3
Workflow Clarity	The review checklist provides a clear, sequenced workflow for reviewing Svelte components with 20 explicit checkpoints. Each step is a concrete yes/no question with a clear action. The skill also clearly delineates its scope (component-level) vs. delegation to sveltekit for server concerns. For a review/mental-model skill (not a destructive batch operation), this level of workflow clarity is excellent.	3 / 3
Progressive Disclosure	The skill is an exemplary overview document that provides concise principles inline and delegates detailed explanations to 18+ well-named reference files via clear one-level-deep links. Navigation is supported by both inline references and a comprehensive quick-reference table mapping code smells to reference files. Cross-references to related skills (sveltekit) are explicit. However, no bundle files were provided to verify the references actually exist.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: joshuadavidthomas/agent-skills
Commit: 40067f1

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.