svelte-code-writer

Use the Svelte CLI to check any Svelte component or module that you create, edit, or analyze.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%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.

The content is a model of brevity and actionability for a simple single-purpose skill, with an executable command, flag guidance, and an explicit fix-the-cause feedback loop. Structure and references are clean and one level deep.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it never explains what Svelte is or how the CLI works, and every line is actionable guidance that earns its place.	5 / 5
Actionability	Provides a copy-paste-ready executable command with concrete flags (--svelte-version 4, --async) and specific handling notes for file paths and $-runes quoting, covering the common cases.	5 / 5
Workflow Clarity	As a simple single-purpose skill it states when to run the autofixer (reviewing/debugging and before returning changes) and includes an explicit validate-fix feedback loop ("Fix the cause of reported warnings").	5 / 5
Progressive Disclosure	Well-organized short body with clearly signaled one-level-deep cross-skill references (svelte-core-bestpractices, svelte-docs) and no nested or buried references; no bundle files are present to misorganize.	5 / 5
	Total	20 / 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.

The description is concise, third-person, and clearly scoped to Svelte, with a concrete action and embedded trigger contexts. Its main weakness is the lack of an explicit standalone "Use when..." clause and missing file-extension trigger terms.

Suggestions

Add an explicit "Use when..." clause (e.g., "Use when creating, editing, or analyzing Svelte components or modules") to make the trigger guidance standalone rather than embedded.

Include natural file-extension terms (".svelte", ".svelte.ts", ".svelte.js") so the description matches how users name these files.

Optionally enumerate the concrete check actions the CLI performs to lift specificity beyond a single verb.

Dimension	Reasoning	Score
Specificity	Names the domain (Svelte components/modules) and one concrete action ("check" via the CLI), but does not enumerate multiple distinct capabilities, matching the 1-2 concrete actions anchor.	3 / 5
Completeness	Clearly states what (use the Svelte CLI to check components/modules) and gives when via the embedded "that you create, edit, or analyze" trigger contexts, though a standalone "Use when..." clause would make the trigger more explicit.	4 / 5
Trigger Term Quality	Includes natural terms ("Svelte component", "Svelte module", "create, edit, or analyze") users would say, but omits file-extension synonyms like ".svelte", ".svelte.ts".	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to Svelte components/modules with Svelte-CLI-specific triggers, creating a clear niche with minimal overlap risk against non-Svelte skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: chattocorp/chatto
Path: .agents/skills/svelte-code-writer/SKILL.md
Commit: 5cbd584

Reviewed: 3 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.