Agent skill

Website Taste Pass

by tryproduck in tryproduck/produck-skills

Runs a category-first visual audit of a website, then a decisive design pass that raises credibility and conversion clarity, verified with screenshots instead of subjective opinion.

Apache-2.0Auto-check passedFrontend & Design

Install Website Taste Pass

skills CLI
$ npx skills add tryproduck/produck-skills --skill taste -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install tryproduck/produck-skills taste --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/tryproduck/produck-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/taste .claude/skills/taste && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
taste
GitHub stars
510
Token cost
~2.4k tokens
SKILL.md length
1,110 words
Files
5 (incl. references)
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

Runs a category-first visual audit of a website, then a decisive design pass that raises credibility and conversion clarity, verified with screenshots instead of subjective opinion.

  • Works in 5 steps: Outcome → Taste rules for agents → One-shot workflow → …
  • Making a functional-looking website feel more premium and credible
  • SKILL.md covers 1. Outcome, 2. Taste rules for agents, 3. One-shot workflow and 4. Agent guardrails, plus 1 more section
  • Calls npx

What it does

A finished pass should let a visitor answer six questions within five seconds: what the category idea is, why the product matters now, why they should care, what to do next, why to trust it, and where their eye should go. Before editing any CSS the agent writes down a one-line category thesis and a worldview sequence running from market shift to scarce resource to why the product exists, then maps the page to a sequence such as worldview, category thesis, domain artifact, proof and action, fixing that structure before touching styling if it is missing.

Copy should lead with the audience's existing tension rather than opening with dashboards, workflows or feature bullets, favoring short declarative lines. Four reference files back the pass: taste principles and a rubric, a step-by-step browser screenshot improvement loop, before-and-after benchmark notes, and guidance specifically for WebGL, animation and generated media on immersive landing pages.

When your agent uses it

  • Making a functional-looking website feel more premium and credible
  • Fixing a landing page's design without random decorative changes
  • Reviewing before-and-after screenshots of a design pass as proof

Example prompts

  • “Make this landing page feel more premium and credible, not just prettier.”
  • “Run a taste pass on our pricing page and verify the result with screenshots.”
  • “Our hero section has no clear thesis, help fix the structure before the styling.”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Outcome
  2. Taste rules for agents
  3. One-shot workflow
  4. Agent guardrails
  5. PR checklist

What it can do on your machine

Read from SKILL.md and the folder at commit 9a699eb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Website Taste Pass loads about 2.4k tokens when it runs, and up to ~6.8k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 1,110 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from tryproduck/produck-skills at commit 9a699eb, republished under its Apache-2.0 licence (© tryproduck). 1,110 words, ~2,371 tokens.

Download SKILL.mdSave it as .claude/skills/taste/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
taste
description
Use when improving the visual taste, positioning, polish, trust, and conversion clarity of a website or product UI. Runs a category-first visual audit, applies a decisive design pass, and verifies the result with screenshots rather than subjective vibes.
license
Apache-2.0
metadata.author
produck
metadata.version
1.0.0

Taste — Website Visual Improvement

Purpose: Upgrade a website from merely functional to visibly credible, high-intent, and conversion-ready in one focused pass.

This skill is for agents asked to "make this look better," "polish the site," "improve the landing page," "make it feel premium," or "fix the design." Do not make random decorative changes. Taste is a system: category, worldview, hierarchy, restraint, alignment, rhythm, contrast, proof, and visual verification.

Supporting files:


1. Outcome

A successful taste pass makes the page easier to believe before it makes the page prettier.

The finished page should answer these questions within five seconds:

  1. What is the category idea? The page has one memorable thesis, not a feature inventory.
  2. Why now? The hero opens with the market shift, tension, or newly scarce resource.
  3. Why should I care? The product exists because that tension matters.
  4. What should I do next? One primary CTA is visually dominant.
  5. Why should I trust it? Proof, research, recruiting seriousness, or domain artifacts appear early.
  6. Where should my eye go? The layout has an obvious reading order.

2. Taste rules for agents

2.1 Decide before decorating

Before editing CSS, write these two lines:

markdown
Category thesis: [sharp category phrase, e.g. "the judgment layer for product feedback"]
Worldview sequence: [market shift] → [scarce resource] → [why this product exists]

Then map the page to a sequence:

markdown
Sequence: worldview → category thesis → domain artifact → proof → action

If the current page lacks a sequence, fix structure before styling.

2.2 Lead with worldview, not product mechanics

Do not open with dashboards, workflows, or feature bullets. Start with the tension the audience already feels.

Strong copy is short and declarative:

text
Creation is cheap. Judgment is scarce.
The challenge is not generating more. It is knowing what deserves to exist.
We make subjective quality measurable.

Avoid 10x, seamless, AI-powered, supercharge, generic productivity claims, and inflated adjectives unless the page proves them.

2.3 Create hierarchy with restraint

Use three hierarchy levers first:

  1. Scale: one dominant headline, clear section titles, smaller supporting text.
  2. Spacing: generous section rhythm, tight grouping inside components.
  3. Contrast: one strong CTA color or treatment, muted secondary content.

Avoid using many colors, gradients, font weights, or shadows to compensate for weak structure. Austerity can be a premium signal when the thesis is sharp.

2.4 Use domain artifacts instead of generic UI

Replace fake dashboards and generic cards with artifacts from the product's judgment domain:

  • Accepted/rejected examples.
  • Interface states.
  • Visual comparisons.
  • Brand systems.
  • Typography specimens.
  • Product shots.
  • Charts or evidence packs.
  • Research notes, lab entries, hiring briefs, or essays.

Artifacts should make the scope of judgment felt without explaining every feature.

2.5 Make the visual system embody the thesis

If the product is about judgment, the page itself must feel judged, edited, and restrained. Every decorative element should reinforce the category idea. Remove neon blobs, default purple-blue gradients, robots, chatbot visuals, floating sparkles, and checkmark confetti unless they are the product's real domain language.

2.6 Make motion bespoke, not templated

Premium motion is a product surface, not confetti. Prefer one or two signature interactions over many generic animations:

  • Hover or image trails.
  • Orbiting artifact systems.
  • Pointer-reactive layouts.
  • Scroll-driven editorial reveals.
  • Restrained canvas or WebGL moments.

Motion should express the thesis and respect static, mobile, and prefers-reduced-motion paths. See references/immersive-landing-pages.md before adding WebGL or generated media.

2.7 Upgrade credibility early

Add or elevate proof above the first long explanation:

  • Customer logos, user count, revenue/time saved, testimonial, case study metric, security/compliance note, founder/team credibility, recognizable integration, research program, hiring seriousness, or transparent product artifacts.
  • If no proof exists, do not invent metrics. Use clarity, polish, explicit limitations, research notes, and strong artifact quality to create credibility.
2.8 Keep accessibility intact

Animated typography and decorative artifacts must not pollute the accessibility tree. Add accessible labels where needed, hide purely decorative spans with aria-hidden="true", preserve semantic headings, keep contrast readable, and maintain keyboard focus states.


3. One-shot workflow

Step 1 — Capture the baseline

Use the browser to capture screenshots before editing:

bash
npx -y chrome-devtools-axi open http://localhost:3000
npx -y chrome-devtools-axi resize 1440 1100
npx -y chrome-devtools-axi screenshot /tmp/before.png

Also capture mobile if the task is responsive:

bash
npx -y chrome-devtools-axi resize 390 844
npx -y chrome-devtools-axi screenshot /tmp/before-mobile.png
Show full SKILL.md (464 more words)Show less
Step 2 — Score the page

Use the taste rubric from references/taste-principles.md.

Score 1–5:

  • Category idea
  • Worldview
  • Hierarchy
  • Clarity
  • Trust
  • Visual rhythm
  • CTA gravity
  • Domain specificity
  • Consistency
  • Motion restraint
  • Accessibility
  • Mobile scanability

Write the top three failures. Do not edit yet.

Step 3 — Apply the smallest complete design system

Make one coherent pass:

  1. Write the category thesis and worldview sequence.
  2. Establish tokens or reuse existing tokens.
  3. Redesign the hero around the thesis.
  4. Replace generic UI with domain artifacts.
  5. Move proof, research, recruiting, or credibility signals above dense explanation.
  6. Convert feature lists into scan-first decision units.
  7. Use one visual motif repeatedly.
  8. Add one bespoke interaction only if it expresses the thesis.
  9. Remove decorative elements that do not guide attention.
  10. Keep page weight and accessibility in view.
Step 4 — Verify visually

Re-run screenshots and inspect them side-by-side:

bash
npx -y chrome-devtools-axi screenshot /tmp/after.png

The after screenshot must show at least three visible improvements from the baseline:

  • The category thesis is the strongest element.
  • The page starts with worldview before mechanics.
  • The primary CTA is obvious.
  • Domain artifacts replace generic SaaS UI.
  • Trust or proof is visible without hunting.
  • The page feels less noisy at thumbnail size.
Step 5 — Do not ship until the page wins at thumbnail size

Open before and after screenshots as thumbnails. If the improved page does not have a clearer reading order when small, keep iterating. Good taste survives zooming out.


4. Agent guardrails

Do not:

  • Add generic gradients, blobs, glassmorphism, fake dashboards, robots, sparkles, or stock emojis by default.
  • Invent customer logos, testimonials, metrics, security claims, or press quotes.
  • Start the hero with product mechanics when a worldview is needed.
  • Hide real information behind vague manifesto copy.
  • Use visual novelty where clarity is missing.
  • Ship without screenshots.
  • Add WebGL, Three.js, video, or generated visuals without a static fallback.
  • Let animation obscure the headline, CTA, proof, or accessibility tree.

Do:

  • Preserve existing brand tokens unless they are demonstrably harming hierarchy.
  • Prefer fewer stronger sections over many weak sections.
  • Make one action primary and all others visibly secondary.
  • Use real product UI, real customer language, real workflow screenshots, or clearly illustrative domain artifacts.
  • Integrate research, lab notes, essays, or recruiting when they strengthen category ownership.
  • Keep accessibility: readable contrast, focus states, semantic headings, tap targets.
  • Pause or simplify animation on mobile, reduced motion, idle tabs, and weak connections.

5. PR checklist

Before opening a PR:

  • Baseline screenshot captured.
  • After screenshot captured at the same viewport.
  • Taste rubric scores improved.
  • Category thesis and worldview sequence are explicit.
  • No fake proof or unsupported claim added.
  • No default AI aesthetic added by reflex.
  • No unrelated UI was redesigned.
  • Mobile still scans correctly, if mobile is in scope.
  • Decorative animation is hidden from screen readers.
  • The PR includes screenshots or a link to screenshots.

© tryproduck, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/taste of tryproduck/produck-skills.

  • SKILL.md
  • references/benchmark-notes.md
  • references/immersive-landing-pages.md
  • references/taste-principles.md
  • references/website-improvement-loop.md

Open the folder on GitHubat commit 9a699eb

Compare with similar skills

Website Taste Pass next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Website Taste Pass compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Website Taste Pass this skilltryproduck/produck-skills510—~2.4kAutomated safety check: PassApache-2.0
Create Websitewondelai/skills2.4k—~5.7kAutomated safety check: PassMIT
UI UX Pro Maxsaoudi-h/solar-icons18618 repos~11kAutomated safety check: NotesCustom licence
Frontend Designanthropics/skills180k38 repos~2.3kAutomated safety check: PassApache-2.0
UI/UX Design System AdvisorGalaxy-Dawn/claude-scholar5.7k1 repos~1.1kAutomated safety check: PassMIT
Cc DesignZeroZ-lab/cc-design827—~2.2kAutomated safety check: NotesNone

Similar skills

  • Create Website

    wondelai/skills

    Guided journey from a blank page to a live, high-converting website, built message-first, then design, then conversion.

    2.4k GitHub stars~5.7k tokensUpdated 29 days ago
    Frontend & DesignAuto-check passed
  • UI UX Pro Max

    saoudi-h/solar-icons

    UI/UX design intelligence for web and mobile. An agent skill from saoudi-h/solar-icons.

    186 GitHub starsUsed in 18 repos~11k tokens
    Frontend & DesignAuto-check: notes
  • Frontend Design

    anthropics/skills

    Official

    Pushes the agent toward distinctive visual design for new or reworked UI: a clear aesthetic direction, deliberate typography and choices rooted in the subject.

    180k GitHub starsUsed in 38 repos~2.3k tokens
    Frontend & DesignAuto-check passed
  • UI/UX Design System Advisor

    Galaxy-Dawn/claude-scholar

    Turns a vague UI request into a concrete design system with style, palette, typography and layout guidance from a search script, plus stack-specific implementation advice.

    5.7k GitHub starsUsed in 1 repo~1.1k tokens
    Frontend & DesignAuto-check passed
  • Cc Design

    ZeroZ-lab/cc-design

    High-fidelity HTML design and prototype creation. An agent skill from ZeroZ-lab/cc-design.

    827 GitHub stars~2.2k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check: notes
  • Web Design

    xiaopu-ai/web-design

    Web 视觉设计 SKILL。输入 PRD / 参考 URL / 截图 / 关键词(任意组合),先产出一份标准化 DESIGN.md 设计规范,用户确认后据此生成 UI/UX、视觉、动效、响应式全部达标的 web 代码。专攻 web 端:Landing Page、Portfolio、产品页、博客、个人站、SaaS 介绍页等。当用户说"帮我做个网站""设计一个页面""参考 XX…

    783 GitHub stars~3k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed

More from tryproduck/produck-skills

  • Produck Feedback To Build

    tryproduck/produck-skills

    Pulls full in-context user feedback tickets through the Produck MCP server and turns them into an aligned product change instead of a guess.

    510 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed
  • User Alignment and Agent-Ready PRDs

    tryproduck/produck-skills

    Turns a vague feature request into a written spec with scope, phases, acceptance criteria and do-not-do limits that a coding agent can follow without guessing.

    510 GitHub stars~5.3k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Website Taste Pass

What does Website Taste Pass do?

Runs a category-first visual audit of a website, then a decisive design pass that raises credibility and conversion clarity, verified with screenshots instead of subjective opinion. A finished pass should let a visitor answer six questions within five seconds: what the category idea is, why the product matters now, why they should care, what to do next, why to trust it, and where their eye should go. Before editing any CSS the agent writes down a one-line category thesis and a worldview sequence running from market shift to scarce resource to why the product exists, then maps the page to a sequence such as worldview, category thesis, domain artifact, proof and action, fixing that structure before touching styling if it is missing.

When should I use Website Taste Pass?

Website Taste Pass fits situations like: making a functional-looking website feel more premium and credible; fixing a landing page's design without random decorative changes; reviewing before-and-after screenshots of a design pass as proof.

How do I install Website Taste Pass in Claude Code?

Run `npx skills add tryproduck/produck-skills --skill taste -a claude-code`. Or copy the skill folder (skills/taste in tryproduck/produck-skills) into .claude/skills/taste in your project. Claude Code loads it when a task matches its description.

How do I install Website Taste Pass in Codex?

Run `npx skills add tryproduck/produck-skills --skill taste -a codex`. Or copy the skill folder (skills/taste in tryproduck/produck-skills) into .agents/skills/taste in your project. Codex loads it when a task matches its description.

Can I use Website Taste Pass in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tryproduck/produck-skills --skill taste -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/taste, .gemini/skills/taste, .github/skills/taste and .opencode/skills/taste in your project.

What does Website Taste Pass need to run?

Going by SKILL.md and its folder, Website Taste Pass needs the command-line tools its instructions call (npx).

Does Website Taste Pass access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Website Taste Pass safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Website Taste Pass use?

Website Taste Pass is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Website Taste Pass use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.4k tokens, read only when the agent opens those files.

What are the alternatives to Website Taste Pass?

Skills that share tags, products or a category with Website Taste Pass: Create Website (wondelai/skills, 2.4k stars), UI UX Pro Max (saoudi-h/solar-icons, 186 stars), Frontend Design (anthropics/skills, 180k stars) and UI/UX Design System Advisor (Galaxy-Dawn/claude-scholar, 5.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Website Taste Pass?

tryproduck (a GitHub organization) maintains it in tryproduck/produck-skills, which has 510 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on August 14, 2026.

Source: tryproduck/produck-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.