frontend-skill

Create visually strong landing pages, websites, and app UIs with restrained composition. OpenAI's production frontend playbook.

Quality

48%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/frontend-skill/SKILL.md

Quality

Content

47%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 lean, well-structured catalogue pointer rather than an executable skill: it is concise and cleanly navigable but provides almost no actionable instruction for the stated task and only a loosely defined, gap-filled install workflow.

Suggestions

Replace the outward pointer with at least one copy-paste-ready example for the core task (e.g., a minimal restrained landing-page layout) to lift actionability.

Provide a concrete install command and exact paths instead of "install the upstream bundle into your active agent's skills directory" so the workflow sequence is well-defined.

Add a validation or verification step (e.g., confirming the skill is discoverable after install) to give the workflow a checkpoint.

Dimension	Reasoning	Score
Conciseness	The ~30-line body is efficient with clean section headers and assumes Claude's competence; only mild meta-padding about the catalogue/OpenDesign keeps it from a 5.	4 / 5
Actionability	The only concrete command is `open https://github.com/openai/skills`; the actual skill task (building UIs) has no executable guidance, and "install the upstream bundle" is a high-level hint rather than specific steps, placing it just above a fully vague level-1.	2 / 5
Workflow Clarity	A rough inspect-install-invoke sequence exists but with major gaps (no concrete install command, a deferral to "inspect the upstream README for exact paths") and no validation checkpoints, matching the level-2 "rough sequence, many gaps" anchor rather than the better-defined level-3.	2 / 5
Progressive Disclosure	Sections are well-organized and the upstream reference is a clearly signaled one-level-deep pointer; it is a 4 rather than 5 because the body is a thin pointer with almost no content actually split locally, so it does not fully demonstrate the overview-plus-detailed-materials split.	4 / 5
	Total	12 / 20 Passed

Description

50%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 clearly states what the skill produces but omits any explicit "when to use" guidance, capping completeness at 3, and its single composite action and broad scope keep specificity, trigger coverage, and distinctiveness at the same midpoint.

Suggestions

Add an explicit "Use when..." clause naming concrete triggers (e.g., building a landing page, marketing site, or app UI) to raise completeness above 3.

List several distinct concrete actions (compose sections, apply restrained layout, set typography/spacing) rather than one "create" verb to improve specificity.

Include a few more natural user phrases and synonyms (e.g., "web design", "homepage", "hero section") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Create visually strong landing pages, websites, and app UIs with restrained composition" names the domain and one concrete creation action, but offers only a single composite verb rather than the several specific actions of a level-4 anchor.	3 / 5
Completeness	The description gives a clear "what" but no "Use when..." clause or explicit trigger guidance, which the rubric caps at 3; it is not a 4 because the "when" is entirely absent.	3 / 5
Trigger Term Quality	Natural terms like "landing page", "websites", and "app UIs" are present (plus frontmatter triggers), but common variations users would say such as "web design", "homepage", or "hero section" are missing, so coverage is not quite good enough for a 4.	3 / 5
Distinctiveness Conflict Risk	The "frontend playbook / restrained composition" framing is a distinct niche, but the broad terms "websites" and "app UIs" create more than minor overlap with general web-design skills, so it sits at 3 rather than 4.	3 / 5
	Total	12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/frontend-skill/SKILL.md
Commit: 01169bc

Reviewed: about 18 hours 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.