CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

Quality

68%

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 ./skills/creative/popular-web-designs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 body is a well-organized, actionable index: an exact template-loading command, a concrete HTML generation pattern tied to numbered template sections, a non-obvious font-substitution table, and selection heuristics — capped by an explicit screenshot verification step. Its gaps are minor: HTML boilerplate that could be trimmed, a placeholder font URL with no fully worked example, and no explicit fix-and-reverify loop.

DimensionReasoningScore

Conciseness

Efficient overall: the font-substitution table and catalog rows carry non-obvious information Claude cannot know, and there is no concept-teaching padding. The full HTML5 boilerplate skeleton ("meta charset", "viewport", an empty "<body>") is over-explanation Claude does not need; trimming it to the :root custom-property pattern would earn a 5.

4 / 5

Actionability

Concrete, mostly executable guidance: the exact load command "skill_view(name=\"popular-web-designs\", file_path=\"templates/<site>.md\")", specific tools ("write_file", "browser_exec", "capture_screenshot()"), and a complete HTML pattern with section-mapped comments ("Apply the template's color palette as CSS custom properties"). Not 5 because the Google Fonts link is a placeholder ("family=...") and there is no single worked example with real token values.

4 / 5

Workflow Clarity

A clear numbered sequence (pick a design → load it → apply tokens → serve via cloudflared tunnel) plus an explicit verification step: "verify the result with browser_exec: open the page, capture_screenshot(), and inspect the image to confirm visual accuracy." Not 5 because there is no explicit error-recovery loop telling Claude what to fix and re-verify when the screenshot does not match.

4 / 5

Progressive Disclosure

Well-structured index: the body is an overview with a catalog of 54 one-level-deep template references, each reachable via the documented skill_view call, and the font table is a compact quick-reference with details deferred to the templates. Not 5 because the ~100-line catalog is somewhat heavy inline, and no templates/ files were present in the provided bundle to verify that the referenced paths resolve.

4 / 5

Total

16

/

20

Passed

Description

48%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 and concrete about what the skill contains, but it is a noun-phrase inventory rather than a capability statement: no actions, no "use when" guidance, and few of the natural trigger phrases users would actually say. The brand names give it good distinctiveness, but completeness and trigger coverage lag.

Suggestions

Rewrite as a capability statement with action verbs, e.g., "Generate HTML/CSS pages styled after 54 real design systems (Stripe, Linear, Vercel), applying each brand's palette, typography, and component styles." (specificity)

Add an explicit "Use when..." clause, e.g., "Use when the user wants a page or UI that looks like a known brand — landing pages, dashboards, or marketing sites in a recognizable design language." (completeness)

Fold natural user phrasings from the triggers list into the description itself — "web design", "landing page", "dashboard design", "make it look like" — so it matches how users actually ask. (trigger_term_quality)

DimensionReasoningScore

Specificity

"54 real design systems (Stripe, Linear, Vercel) as HTML/CSS" names the domain and format concretely but contains no action verbs — it never states what Claude does with the systems (e.g., generate or style pages). This matches anchor 2 ("names the domain but actions are minimal or generic") rather than 3, which requires 1-2 concrete actions.

2 / 5

Completeness

The "what" is clear as a concrete content inventory ("54 real design systems ... as HTML/CSS"), but the "when" is entirely absent — no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3. Not 4 because "when" is missing rather than merely imprecise; not 2 because the "what" is concrete, not vague.

3 / 5

Trigger Term Quality

The description includes some natural keywords users would say ("Stripe", "Linear", "Vercel", "design systems", "HTML/CSS"), but misses the most common phrasings ("web design", "landing page", "styled like", "dashboard"), which appear only in the frontmatter triggers list, not the description. Anchor 3 ("some relevant keywords but missing common variations or synonyms") is the closest fit.

3 / 5

Distinctiveness Conflict Risk

Naming specific brands ("Stripe, Linear, Vercel") carves a clear niche unlikely to trigger for unrelated skills, but it overlaps with general web-design and design-system skills and offers no guidance on when to prefer it over closely related design skills. Anchor 4 ("mostly distinct; minor overlap risk with closely related skills") fits best.

4 / 5

Total

12

/

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

NousResearch/hermes-agent

Path

skills/creative/popular-web-designs/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.