CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frontend-app-builder

Use for new frontend applications, dashboards, games, creative websites, hero sections, and visually driven UI from scratch, or when the user explicitly asks for a redesign/restyle/modernization. Builds from clean, airy, high-taste, readable image-generated concept design with section-specific references, faithful implementation, and browser testing.

62

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 ./plugins/build-web-apps/skills/frontend-app-builder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%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 delivers an unusually rigorous, well-sequenced design-to-verification workflow with real validation gates, but it is bloated by systematic repetition of the same prohibitions across sections and keeps detail inline that should be pushed into reference files. It reads more like an accumulated policy document than a lean skill overview.

Suggestions

State each prohibition once in a single canonical rules section (or a rules reference file) and reference it elsewhere; the hero eyebrow/kicker/badge ban, white-vs-cream color lock, icon fidelity, and game asset guidance are each repeated 3-6 times and could be cut to one statement each.

Move the Design Quality Bar, Visual Direction Defaults, and Surface Gates sections into dedicated reference files (like the existing imagegen-website-concepts.md) and keep SKILL.md as a lean workflow overview that links to them.

Convert judgment-call aesthetic directives ('one clear creative idea', 'feel designed as one system') into checkable criteria or concrete good/bad examples so every line of the verification pass is actionable.

DimensionReasoningScore

Conciseness

The same prohibitions are systematically restated: hero eyebrow/kicker/badge bans appear roughly six times across Hard Rules, Image Gen Workflow, Design Quality Bar, Implementation, Verification, and Hard stops, with white-vs-cream color locks, icon fidelity rules, and game asset passes each repeated about three times. This is noticeable padding, not occasional looseness, though it adds non-obvious domain policy rather than explaining concepts Claude already knows.

2 / 5

Actionability

Highly directive for an instruction-only skill: named tools (view_image, Browser/IAB, Playwright Chromium, React + Vite, lucide), a required fidelity ledger with 'at least five comparison points', an above-the-fold copy diff, and hard-stop checklists. Held below 5 because a subset of guidance is judgment-call aesthetic phrasing ('one clear creative idea', sections that 'feel designed as one system') with no concrete examples.

4 / 5

Workflow Clarity

A clear ordered sequence (concept brief → generation → approval gate → design-system extraction → sliced implementation → verification → final response) with explicit validation checkpoints and feedback loops ('keep fixing until', 'Do not final-answer with fixable visual issues') enforced as hard gates.

5 / 5

Progressive Disclosure

The single reference (references/imagegen-website-concepts.md) exists, is clearly signaled, and is one level deep, but the ~185-line body inlines large sections (Design Quality Bar, Visual Direction Defaults, Surface Gates, repeated fidelity rules) that belong in reference files, and parts duplicate the reference file's content.

3 / 5

Total

14

/

20

Passed

Description

83%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 strong description with an explicit trigger clause, natural user phrasing, and a clear what/when pairing. Its only weaknesses are decorative adjectives in the what-clause and a few missing common synonyms.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — 'image-generated concept design with section-specific references, faithful implementation, and browser testing' — though 'high-taste' is decorative fluff and the what-clause compresses the pipeline into adjectives.

4 / 5

Completeness

Both what and when are explicit: 'Use for new frontend applications... or when the user explicitly asks for a redesign/restyle/modernization' gives concrete triggers, and 'Builds from... concept design... faithful implementation, and browser testing' states the what clearly.

5 / 5

Trigger Term Quality

Natural phrases users would say are well covered ('new frontend applications, dashboards, games, creative websites, hero sections... redesign/restyle/modernization'), but common synonyms like 'landing page' or 'mockup' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (visual-first frontend builds from generated concept specs) with pointed triggers, but the broad 'visually driven UI' and 'redesign' phrasing creates minor overlap risk with general web-development or design-system skills.

4 / 5

Total

17

/

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

openai/plugins

Path

plugins/build-web-apps/skills/frontend-app-builder/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.