CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

svelte-frontend

Svelte coding guidelines for the Windmill frontend. MUST use when writing or modifying code in the frontend directory.

Quality

82%

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

82%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 strong, highly actionable skill body that front-loads repo-specific knowledge (existing component discovery, deprecated sizing system, telemetry allowlist coupling) and defers bulk detail to external documents with precise navigation aids. Weaknesses are minor: one unresolvable 'recipe's step 3' reference and slight redundancy between the barrel export list and the instruction to read the barrel in full.

DimensionReasoningScore

Conciseness

The body is dense with Windmill-specific knowledge Claude cannot already know (barrel paths, deprecated 'size'/'xs2' props, telemetry allowlist) and assumes competence throughout, matching 'Efficient; minor instances of over-explanation that could be trimmed'. Not 5: the full export list partially duplicates 'read it in full' instructions, and emphatic asides like 'not after, and not only when something looks unfamiliar' could be tightened.

4 / 5

Actionability

Fully executable guidance: exact import paths ('$lib/components/common', '$lib/components/select/Select.svelte'), runnable Svelte snippets with full prop signatures, and concrete commands like `grep -n '^#' frontend/brand-guidelines.md`. The examples (Button, TextInput, Select, lucide icons) cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

A clear phase order exists: a 2-step pre-work checklist ('Do both of these before the first line of markup'), an explicit feedback loop ('svelte-autofixer: MUST use... keep calling until no issues'), and post-change verification via Playwright MCP. Not 5: the end-to-end flow is distributed across sections rather than one explicit sequence, and verification details are deferred to frontend/AGENTS.md rather than inline.

4 / 5

Progressive Disclosure

Strong deferral of bulk detail: 'Don't load all 34k chars — jump to the section' with a build-type-to-section table and grep-based line ranges, plus one-level-deep references (brand-guidelines.md, AGENTS.md, docs/feature-telemetry.md). Not 5: the reference 'see the recipe's step 3' is dangling — no recipe is identified anywhere, so the pointer cannot be resolved.

4 / 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 crisp, third-person description that explicitly states both what it covers and when to use it, with strong trigger guidance tied to the frontend directory. Its main weakness is that the 'what' stays at the domain level — it never enumerates the concrete capabilities (design-system components, brand guidelines, telemetry, browser verification) that the body actually delivers.

Suggestions

Enumerate 2-3 concrete capabilities in the description — e.g., 'Apply Windmill's design-system components, follow brand guidelines, and verify UI changes in the browser' — so the 'what' goes beyond naming the domain.

Add natural trigger variations such as 'UI', 'components', or '.svelte files' so the description matches the ways users actually phrase frontend work.

DimensionReasoningScore

Specificity

The description only names the domain — 'Svelte coding guidelines for the Windmill frontend' — without listing any concrete action, matching 'Names the domain but actions are minimal or generic'. Not 3: no capability beyond providing 'guidelines' is explicitly stated (e.g., applying design-system components or following brand rules is only inferable).

2 / 5

Completeness

It explicitly answers both what ('Svelte coding guidelines for the Windmill frontend') and when ('MUST use when writing or modifying code in the frontend directory') with a concrete trigger phrase, matching the top anchor. Not 4: the 'when' clause is already explicit and specific, so nothing more could be asked of it.

5 / 5

Trigger Term Quality

Natural terms a user would say are present — 'Svelte', 'Windmill', 'frontend', 'writing or modifying code' — giving good keyword coverage. Not 5: common variations such as 'UI', 'component', or '.svelte files' are missing.

4 / 5

Distinctiveness Conflict Risk

'Svelte' plus 'Windmill frontend' pins a clear niche, but the trigger 'writing or modifying code in the frontend directory' could minorly overlap a generic Svelte or frontend skill — 'Mostly distinct; minor overlap risk with closely related skills'. Not 5: the overlap risk, while small, is not minimal.

4 / 5

Total

15

/

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

windmill-labs/windmill

Path

.agents/skills/svelte-frontend/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.