mcpbeat Sign in

Premium Web Build Gate Skill for Codex

Premium website pre-build gate for cinematic, editorial, Squarespace-polished, Raycast/Linear/Vercel-precise, or motion-heavy web work. Use before implementing or redesigning a homepage, landing page, portfolio, product site, agency/studio site, or high-polish web app when the user wants non-generic visual quality, strong scroll/motion choreography, strict content scope, or an award-level result. Produces a build-ready UI spec, source-trust decisions, motion storyboard, and QA gates before code.

2k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
115
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/TheGoat395/Codex-Skills --skill premium-web-build-gate

What comes with it

238 bytes besides the instruction
agents/openai.yaml

The instruction itself

10 sections, as written by the author

Premium Web Build Gate

Overview

Use this skill to prevent generic website output by locking strategy, reference direction, content boundaries, visual system, motion behavior, stack decisions, and QA criteria before implementation. It is a gate: do not start code until the brief below is concrete enough that another design engineer could build from it without guessing.

Required Order

Follow this sequence for premium web work:

  • Inspect the current project, repo instructions, design docs, route structure, live/local render, assets, and existing copy.
  • Research or re-check current reference sources when the references, tools, product standards, or external sites may have changed.
  • Classify sources as use, distill, inspiration only, or avoid.
  • Produce the Build-Ready UI Spec.
  • Wait for user confirmation unless the user explicitly said to proceed, build, implement, continue, or fix.
  • Build version 1 using the approved spec.
  • Run local browser QA on desktop and mobile, then perform a second polish pass.
  • Report files changed, commands run, visual QA status, and anything blocked.

Build-Ready UI Spec

Before coding, write a concise spec with these headings:

  • Current System: framework, entry files, styling system, interaction/motion system, source vs generated assets, junk folders, and planned edit files.
  • Business Truth: what the organization actually does, stated without invented specifics, fake proof, or copied claims.
  • Page Scope: what belongs on this page, what belongs on later subpages, and what must be removed to avoid content crowding.
  • Reference Contract: 3-5 concrete reference behaviors to borrow, 3-5 to avoid, and which references are verified vs user shorthand.
  • Visual Lane: typography, color/material, layout rhythm, media/art direction, component vocabulary, and density rules.
  • Motion Storyboard: section-by-section motion beats with purpose, scroll relationship, trigger, duration feel, easing feel, reduced-motion fallback, and performance risk.
  • Implementation Stack: chosen framework/libraries, why each is needed, and whether it is project-local or global.
  • Acceptance Gates: desktop/mobile visual checks, interaction checks, accessibility checks, performance risks, and anti-generic checks.

Reference Rules

Use references as behavior contracts, not vibes:

  • Raycast-like means speed, keyboard/product clarity, sharp interaction states, and concrete product proof.
  • Linear-like means quiet precision, dense but readable product systems, low-noise hierarchy, and operational specificity.
  • Vercel-like means technical credibility, strong infrastructure language, crisp capability segmentation, and clean developer-facing surfaces.
  • Squarespace-polished means elegant business flow, strong first viewport, real category clarity, and polished templates without looking generic.
  • Viktor Oddy references must be treated as a named designer/source, not vague shorthand. When accessible, verify viktoroddy.com, x.com/viktoroddy, motionsites.ai, designrocket.io, and current public articles/videos, then extract concrete traits such as compact studio positioning, AI-site-builder workflows, premium hero/prompt libraries, motion-heavy hero previews, tight CTAs, GIF/video demonstrations, and disciplined type systems. Only use "Viktor-style" shorthand after the actual source has been checked or the user has supplied the traits.

Never copy a reference site. Extract structural rules, then adapt them to the product, brand, and content.

Content Discipline

Premium pages fail when they become content dumps. Enforce these rules:

  • Keep homepage content generalized: business model, promise, system, proof shape, and routes into deeper pages.
  • Move detailed services, project examples, process minutiae, and long proof lists to subpages unless the current page specifically needs them.
  • Use real copy from the repo/site/docs when available. If copy must be clarified, preserve truth and remove fluff.
  • No fake metrics, fake testimonials, fake client names, fake awards, or vague claims like "world-class" unless sourced.
  • Every section must have one job. If a section needs two paragraphs to explain why it exists, redesign the section.

Visual Rules

Prefer a few decisive moves over many decorative ones:

  • Use at most two type families unless a brand system already requires more.
  • Keep display type meaningful. Do not use huge words as filler or status noise.
  • Avoid repeated card grids, repeated circles, random dots, blobs, generic glowing lines, and decorative effects that do not support the concept.
  • Use visual assets, product UI, geometry, video, or spatial scenes when they clarify the business or motion idea.
  • Maintain responsive composition: mobile must be intentionally designed, not merely stacked.
  • Respect the current brand anchor when the user wants it preserved.

Motion Rules

Motion must clarify sequence, depth, focus, or tactility:

  • Create fewer, stronger scroll scenes rather than many small ambient animations.
  • Each motion beat needs a reason: reveal hierarchy, transform context, guide attention, compare states, or resolve a scene.
  • Avoid motion that competes with reading, causes overlap, jitters, drags too long, or looks like a generic template effect.
  • Use GSAP/ScrollTrigger/Lenis/Motion/R3F only when they serve the storyboard.
  • Always provide prefers-reduced-motion behavior and preserve anchor navigation.
  • Animate transform, opacity, clip/mask, shader uniforms, or canvas state where possible. Avoid layout-thrashing properties.

Tool And Skill Trust Gate

Before installing or adopting a new tool/skill:

  • Prefer official docs, official skills, reputable maintainers, active repos, clear licenses, and small focused tools.
  • Treat community skill lists as lead sources, not install instructions.
  • Do not install broad style packs that overlap existing skills unless they add a clear missing gate.
  • Install frontend libraries per project, not globally, unless the tool is a CLI or Codex skill.
  • Explain why the new dependency or skill materially improves the result.

Final QA

Before final delivery after implementation:

  • Run the site locally when possible.
  • Inspect rendered desktop and mobile views when possible.
  • Check text overflow, visual overlap, awkward wraps, content density, hover/focus states, reduced motion, console errors, and performance risks.
  • Perform an anti-generic pass: remove anything that could belong to any random SaaS/agency template.
  • Be honest about anything not tested, especially browser/screenshot QA if tooling or credits blocked it.

Other skills for the same job

different authors, same section of the catalogue
Workflow Patterns
by ComeOnOliver
×2

Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.

6k tokens
Iso Standards Readiness
by K-Dense-AI
×1

Prepares and structurally reviews readiness evidence for ISO management-system and laboratory-competence standards - ISO 13485 medical device QMS, ISO 14971 device risk management, ISO/IEC 17025 testing and calibration laboratories, and ISO 15189 medical laboratories. Use when organizing declared scope, controlled documents, risk-management files, scope of accreditation, traceability, CAPA, external-provider controls, or bounded local evidence manifests, and when separating ISO certification from laboratory accreditation, FDA QMSR inspection, CLIA certification, MDSAP, and EU MDR/IVDR evidence boundaries. Not for legal applicability, compliance, certification, or accreditation decisions; contains no clause text.

67k tokens scripts
Statistical Power
by K-Dense-AI
×1

Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers closed-form power for t-tests, ANOVA, proportions, correlations, chi-square, and regression, plus simulation-based (Monte Carlo) power for designs with no formula — logistic/Poisson regression, mixed models, cluster-randomized trials, survival, and interactions. Use this skill even when the request only mentions an effect size, alpha, or "80% power" without saying "power analysis" explicitly. For laying out the study (randomization, blocking, factorial/DOE, crossover, sequential designs) use experimental-design; for analyzing data already collected and reporting it use statistical-analysis.

13k tokens scripts
General Figure Guide
by BioTender-max
×1

Universal QA checklist for generated scientific plots: overlapping labels, clipped text, missing axes/legends, overcrowded data, and cross-journal resolution/format guidance.

2k tokens
Nerdzao Elite
by ComeOnOliver
×1

Senior Elite Software Engineer (15+) and Senior Product Designer. Full workflow with planning, architecture, TDD, clean code, and pixel-perfect UX validation.

3k tokens
Pinchbench
by ComeOnOliver
×1

Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Use when testing model capabilities, comparing models, submitting benchmark results to the leaderboard, or checking how well your OpenClaw setup handles calendar, email, research, coding, and multi-step workflows.

2096k tokens scripts
Workflow Patterns
by ComeOnOliver
×1

Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.

6k tokens
Powertoys Verification
by microsoft
vendor

Verify PowerToys behavior end-to-end with the winapp CLI across two scenarios: (A) a module's release checklist against the installed build; (B) PR validation — derive each PR's checklist from its description + diff, then drive it against the installed build (a merged/shipped PR, or a whole release/hotfix set) or by building + sideloading the module when the PR isn't in the build yet (unmerged or not-yet-released). Drive each item via UIA invoke / Named Events / settings.json edits / clipboard / GPO / SendInput, and emit a structured PASS / FAIL / BLOCKED verdict per item with evidence (FAIL distinguishes product defects from stale/ambiguous checklist items). Use when asked to verify a module checklist, validate a PR, sign off a release/hotfix's PRs, or QA installed/sideloaded PowerToys bits. Combines generic winapp ui mechanics (references/winapp-ui-testing.md) with PT-specific recipes, per-scenario playbooks (references/scenarios/), and the helper .ps1 files shipped with this skill.

86k tokens scripts

How to use it

Copy the folder

Take thegoat395/premium-web-build-gate from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.