CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frontend-design

Product-specific interface design for an Agent-Native app. Use when creating or changing any user-facing UI, including screenshot feedback, copy or density cleanup, settings, controls, or a visual redesign.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/frontend-design/SKILL.md
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 lean, highly directive design-policy skill with specific thresholds, explicit do/don't rules, and a closing review checklist. The one structural defect is the orphaned bundle reference: references/visual-direction.md exists but no section of the body ever points to it.

Suggestions

Link the reference from the body where it is relevant, e.g. in 'Choose a direction': "For a new app with no established brand, work through [references/visual-direction.md](references/visual-direction.md) and record the result in DESIGN.md."

Make the build sequence explicit as a short ordered flow (direction → build → review) so the section order reads as a process rather than a topic list.

Add one compact before/after sketch of a focused starting view to make the abstract directives ('Every visible element should orient the user...') concrete.

DimensionReasoningScore

Conciseness

The body is dense directive prose with no padding and no explanations of concepts Claude already knows — e.g., "Never use browser `alert`, `confirm`, or `prompt` dialogs", "Density should come from useful data, not extra chrome", "aiming for 100 ms". Every sentence is product-specific policy, so every token earns its place.

5 / 5

Actionability

For an instruction-only skill the guidance is largely concrete and executable: explicit do/don't lists ("Do not add a page title that repeats the selected navigation item, a subtitle or eyebrow under a title, a count strip..."), numeric thresholds ("aiming for 100 ms", "within 400 ms"), and routing rules ("Read `shadcn-ui` when implementing or composing a standard control"). It stops short of 5 because some directives remain abstract judgment calls ("Pick a visual direction that fits the product's brand and domain") with no compact good-vs-bad example to anchor them.

4 / 5

Workflow Clarity

The sections form a coherent implicit sequence — choose a direction, build the focused view, use the design system, coordinate with the agent, then an explicit validation pass: "Check that the main job and next action are obvious. Look at the default, loading, empty, error, and success states... and check a narrow viewport." It is below 5 because the sequence is implicit (no ordered steps) and there is no feedback loop instructing what to do when the review finds problems.

4 / 5

Progressive Disclosure

The body itself is well organized at the right altitude (~93 lines, clear section headers), but the bundle contains references/visual-direction.md (102 lines of direction-choosing guidance) that is never linked or mentioned anywhere in SKILL.md, so it is undiscoverable rather than merely 'not clearly signaled'. This matches the level-3 anchor ('references present but not clearly signaled') and is above level 2 because nothing that belongs in a separate file is inlined.

3 / 5

Total

16

/

20

Passed

Description

70%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 well-formed description with an explicit and well-triggered 'Use when' clause and natural keywords. Its main weakness is an abstract 'what' — it names the domain rather than enumerating the concrete actions the skill performs.

Suggestions

Replace the abstract 'Product-specific interface design' with 2-3 concrete verbs, e.g., 'Apply a visual direction, trim and restructure existing UI, and review all interaction states for user-facing surfaces in an Agent-Native app.'

Add common trigger synonyms such as 'frontend', 'layout', 'component styling', or 'mockup' so users phrasing the need differently still hit the skill.

DimensionReasoningScore

Specificity

The 'what' is a single abstract capability — "Product-specific interface design" — with only generic verbs ("creating or changing any user-facing UI"); the enumerated items (screenshot feedback, copy or density cleanup, settings, controls, visual redesign) are trigger contexts rather than distinct concrete actions, matching 'Names domain and 1-2 concrete actions, but not comprehensive'. It falls short of 4 because no list of several specific capabilities is given.

3 / 5

Completeness

Both parts are present: 'what' ("Product-specific interface design for an Agent-Native app") and an explicit 'when' ("Use when creating or changing any user-facing UI, including...") with concrete trigger phrases. It is below the 5 anchor because the 'what' remains abstract — it does not state concrete actions the way the anchor-5 example does ("Extract text and tables... fill forms, merge documents").

4 / 5

Trigger Term Quality

Good natural-keyword coverage: "user-facing UI", "screenshot feedback", "copy", "density", "settings", "controls", "visual redesign" are phrases a user would plausibly say. A few common terms are missing (e.g., "frontend", "layout", "styling", "components"), so it does not reach comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Scoping to "an Agent-Native app" plus specific triggers (screenshot feedback, density cleanup, settings/controls changes) makes it mostly distinct with only minor overlap risk against closely related frontend/design skills. It is not a clear 5 because 'interface design' is a broad category that other design-skill descriptions could also claim.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

BuilderIO/agent-native

Path

.agents/skills/frontend-design/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.