taste

taste is a skill for Claude Code from alebgl77/claude-inc. It costs 106 tokens per session (993 once invoked), scanned A, original, MIT.

A structured critic for screens, mockups, and websites. It reviews visual hierarchy, spacing, contrast, typography, colors, and common generic design patterns.

In plain words
What is it for?
Use it before launch or when comparing visual directions to score a design and rank its five most important fixes.
Why use it?
It helps identify why a design feels unclear, cheap, or repetitive and turns that judgment into specific evidence and priorities.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-inc plugin — 50 skills, 3 commands, 8 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/alebgl77/claude-inc/taste
Any agent
npx skills add alebgl77/claude-inc --skill taste
Clone the repo
git clone --depth 1 https://github.com/alebgl77/claude-inc

Made for: Claude Code.

Or install claude-inc, the plugin that ships this one along with the rest of its 50 skills, 3 commands, 8 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for taste

README.md
[![agentmods](https://agentmods.dev/badge/skills/alebgl77/claude-inc/taste.svg)](https://agentmods.dev/skills/alebgl77/claude-inc/taste)
Your own site
<a href="https://agentmods.dev/skills/alebgl77/claude-inc/taste"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/taste.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 993 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.00993
Opus 5 $0.00053 $0.00496
Sonnet 5 $0.00021 $0.00199
Haiku 4.5 $0.00011 $0.00099

Measured 6d ago against content hash 7d297f0918dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

taste scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/taste/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Taste — Taste Maker

"Design-taste critic"

When to use

  • Something visual exists and needs honest judgment — "critique this screen", "review my mockup".
  • The user senses mediocrity but cannot name it — "why does this look cheap / generic / off?"
  • Pre-ship gate — "last look before launch"; run on every sibling skill's output.
  • AI-slop suspicion — "does this look like every other AI-generated site?"
  • Two directions compete — "which of these headers is stronger, and why?"

Workflow

  1. Inventory before judging. List what is actually on the screen: sections, type sizes in play, colors in play, competing focal points. Critique the artifact, not an imagined version.
  2. Score five axes, /10 each, with one sentence of pointable evidence per score.
    • Hierarchy — does the eye land where the business needs it to land?
    • Spacing rhythm — one consistent scale, or ad-hoc gaps everywhere?
    • Contrast — figure/ground separation; AA compliance on text pairs.
    • Typography pairing — pairing logic, scale discipline, line length 45–75ch.
    • Color discipline — roles versus decoration; count the hues doing no work.
  3. Run cliché detection and flag every hit: purple/indigo gradient hero, glassmorphism-by-default, emoji soup as bullet decoration, the cookie-cutter centered hero with three feature cards, drop-shadow-on-everything, fake five-star social proof, Inter-on-white sameness, "Supercharge your workflow" copy.
  4. Name the missing idea. The one distinctive move this design lacks — or has and should push harder. A design with zero clichés can still be forgettable; say so.
  5. Rank the top 5 fixes by leverage (impact over effort). Each gets a before → after direction concrete enough to execute without a follow-up question.
  6. Deliver the verdict. Average the five axes, write the one-line headline, and make the call: SHIP at 7.0 or above, otherwise DO NOT SHIP.

Output format

# Taste Report — <artifact>
**Verdict: <x.x>/10 — <one-line headline>. <SHIP | DO NOT SHIP>.**

| Axis | /10 | Evidence |
|---|---|---|
| Hierarchy | 4 | CTA competes with three same-weight headings |
| Spacing rhythm | <n> | <evidence> |
| Contrast | <n> | <evidence> |
| Typography pairing | <n> | <evidence> |
| Color discipline | <n> | <evidence> |

**Strengths:** <what genuinely works — always name at least one>
**Clichés detected:** <list, or "none">
**The missing idea:** <the one distinctive move this design needs>

## Top 5 fixes, by leverage
1. <fix> — before: <current state> → after: <specific direction>
2. <next four fixes, same shape, descending leverage>

Read the full file on GitHub · 79 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 79 lines · 106 tokens per session scan A 7d297f0918dd

Subscribe to this mod's changes

taste is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed 3d ago), licensed MIT. It adds 106 tokens to every session and 993 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

mcp-lark

Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.

aahl/skills · 45 tokens

checklist

Activate when: user says 'let's make sure we don't skip anything', 'we need a pre-flight', 'build me a checklist for X', 'we keep missing steps in our deployment / close / launch', 'Gawande / Pronovost / checklist manifesto'. Do NOT activate when: the task is simple and one-off with no recurrence; the user is asking…

deciqAI/knowledge-skills · 105 tokens

deep-work

Activate when: user says 'I can never find time for focused work', 'I feel busy but produce nothing', 'I keep getting interrupted', 'I want to protect my focus time', 'flow state', 'deliberate practice', 'Cal Newport', or asks how to make progress on hard cognitive work (research, writing, engineering, strategy). Do…

deciqAI/knowledge-skills · 123 tokens

dichotomy-of-control

Activate when: user says "I can't stop worrying about something I can't control," "I'm anxious about how this will turn out," "I keep replaying what went wrong," "I need them to change," "this uncertainty is paralyzing me," or is processing a setback, preparing for a high-stakes unknown outcome, or stuck in…

deciqAI/knowledge-skills · 143 tokens

intrinsic-drive

Activate when: user says 'I've lost motivation', 'I'm burning out', 'the excitement is gone', 'I keep starting things but can't sustain them', 'I'm going through the motions', 'I don't know what drives me anymore', or describes a flat feeling after achieving a major goal. Do NOT activate when: person shows signs of…

deciqAI/knowledge-skills · 107 tokens

knowing-and-doing-as-one

Activate when: user says 'I know I should but I haven't', a team is stuck in analysis paralysis going in circles, you need to assess whether someone actually learned from a past experience, a strategy or lessons-learned doc has produced no operational change, or an organization keeps repeating the same mistake. Do NOT…

deciqAI/knowledge-skills · 118 tokens