agentmods.dev

47-design-review-global

47-design-review-global is a skill for Claude Code from minhnv0807/ai-business-skills. It costs 160 tokens per session (2,319 once invoked), scanned A, original, MIT.

A checklist for scoring a finished design and giving specific feedback. It checks brand consistency, visual hierarchy, readability, accessibility, conversion elements, and fit for the intended platform.

In plain words
What is it for?
It helps review social posts, ads, carousels, landing pages, and emails and decide whether to approve them, request minor fixes, or redo them.
Why use it?
Vague opinions do not tell a designer what to change, while a design can look good but fail its business purpose. The review links each issue to a concrete fix and a clear decision.

Skill for Claude Code

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

Part of the ai-business-skills plugin — 147 skills, 6 agents, 10 MCP servers shipped together

not rated 668repo +25 8d ago A scan SkillSpector: warn 160 tokens original MIT

Good fit It helps review social posts, ads, carousels, landing pages, and emails and decide whether to approve them, request minor fixes, or redo them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/minhnv0807/ai-business-skills/47-design-review-global
View source ↗ minhnv0807/ai-business-skills opa.business
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.

Any agent
npx skills add minhnv0807/ai-business-skills --skill 47-design-review-global
Clone the repo
git clone --depth 1 https://github.com/minhnv0807/ai-business-skills

Made for: Claude Code.

Or install ai-business-skills, the plugin that ships this one along with the rest of its 147 skills, 6 agents, 10 MCP servers.

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 47-design-review-global

README.md
[![agentmods](https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/47-design-review-global/github.svg)](https://agentmods.dev/skills/minhnv0807/ai-business-skills/47-design-review-global)
Your own site
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/47-design-review-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/47-design-review-global/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for 47-design-review-global

Your own site · 80×15
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/47-design-review-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/47-design-review-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 160 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 32
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00160 $0.02319
Opus 5.5 $0.00064 $0.00928
Sonnet 5.5 $0.00032 $0.00464
Haiku 4.5 $0.00016 $0.00232

Measured 2mo ago against content hash eef0747a2744, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

47-design-review-global 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 2mo 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/en/47-design-review-global/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Review (Global)

Reviewing design is not about liking it. It is checking whether the design does its job. Beautiful work that does not convert has failed. Converting work that breaks the brand has also failed. Feedback must be specific enough for the designer to act without asking.

Information gathering

Read the brand guideline (46-brand-guideline-global) and the originating brief. If information is missing, ask up to 4 questions:

  1. What is being reviewed? File, screenshot, or share link — and what type (social post, ad banner, carousel, landing page, email)?
  2. Objective and funnel stage? Awareness, trust, or conversion — TOFU, MOFU, or BOFU?
  3. Which channel does it run on? Meta, TikTok, Instagram, LinkedIn, Pinterest, email, or website?
  4. Which brand guideline applies? If none exists, the brand section can only be scored loosely — propose running 46-brand-guideline-global first.

Principles

  1. Feedback specific enough to fix without a follow-up. "It doesn't feel right" is not feedback.
  2. Separate must-fix (blocker) from should-fix (suggestion).
  3. Never reject on personal taste — every deduction cites a checklist item.
  4. Review within 24 hours. Do not let a designer wait and block the workflow.
  5. Once approved, do not reopen after the designer exports.
  6. If more than 50% needs rebuilding, rewrite the brief instead of looping revisions.

Workflow

1. Look at the whole thing first (3 seconds)

View it as a real user would — do not zoom into detail yet. Answer two questions: within three seconds, is it clear what this design is saying? Where does the eye land first?

2. Score the 4 criteria groups

Each group is worth 10 points, 40 total. Score against the checklist below; deduct in proportion to the impact of each failure.

3. Write feedback in the standard format

Every issue is written as [Issue] -> [Why it is wrong] -> [Exactly how to fix it].

4. Give a verdict and an action summary

Read the full file on GitHub · 183 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. 2mo ago First seen · 183 lines · 160 tokens per session scan A eef0747a2744

Subscribe to this mod's changes

47-design-review-global is a skill published in the GitHub repository minhnv0807/ai-business-skills (668 stars, last pushed 8d ago), licensed MIT. It adds 160 tokens to every session and 2,319 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-03.

Claude CodeDesign and UXMarketing and SEOagent-skillsai-agentsanthropicchatgptclaude-plugin
Related

47-design-review-global compared with skills from other repositories

47-design-review-global next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
47-design-review-globalminhnv0807/ai-business-skillsSkill6688d agoMITA160Claude Code
anatomyNousResearch/hermes-agentSkill263ktodayMITA15Claude Code, Codex
claude-designNousResearch/hermes-agentSkill263ktodayMITA16Claude Code, Codex
ip-as-logoNousResearch/hermes-agentSkill263ktodayMITA16Claude Code, Codex
tldraw-offlineNousResearch/hermes-agentSkill263ktodayMITA19Claude Code, Codex
sketchNousResearch/hermes-agentSkill263ktodayMITA18Claude Code, Codex
baoyu-infographicNousResearch/hermes-agentSkill263ktodayMITA23Claude Code, Codex