50-asset-resize-global

50-asset-resize-global is a skill for Claude Code from minhnv0807/ai-business-skills. It costs 179 tokens per session (2,916 once invoked), scanned A, original, MIT.

A guide for adapting one design into the different shapes and sizes required by social feeds, stories, reels, covers, and ads. It covers cropping, rearranging, safe areas, and naming the resulting files.

In plain words
What is it for?
It helps turn a master design into platform-specific variants while keeping important content visible and choosing whether to crop, rearrange, or rebuild each version.
Why use it?
Simply stretching or cropping a design can hide the logo, message, call to action, or important parts of an image. Each aspect ratio needs its own layout decision.

Skill for Claude Code

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

Part of the ai-business-skills plugin — 144 skills, 6 agents, 10 MCP servers shipped together

Good fit It helps turn a master design into platform-specific variants while keeping important content visible and choosing whether to crop, rearrange, or rebuild each version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/minhnv0807/ai-business-skills/50-asset-resize-global
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 50-asset-resize-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 144 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 50-asset-resize-global

README.md
[![agentmods](https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/50-asset-resize-global/github.svg)](https://agentmods.dev/skills/minhnv0807/ai-business-skills/50-asset-resize-global)
Your own site
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/50-asset-resize-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/50-asset-resize-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 50-asset-resize-global

Your own site · 80×15
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/50-asset-resize-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/50-asset-resize-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,916 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 pass 7 Sept 2026
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 $0.00179 $0.02916
Opus 5 $0.00089 $0.01458
Sonnet 5 $0.00036 $0.00583
Haiku 4.5 $0.00018 $0.00292

Measured 9d ago against content hash b2a8ad78a084, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

50-asset-resize-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 9d 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/50-asset-resize-global/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Asset Resize (Global)

Resizing is not stretching. Every ratio needs re-composition so the hierarchy still works. One good master becomes 10+ variants — the single biggest time saver in design production, and the first job after a campaign ends when winners get repurposed at D+2.

Information gathering

Read the asset list (41-campaign-asset-list-global) if available. If information is missing, ask up to 4 questions:

  1. What is the master? Link to the source file (Canva, Figma, Adobe Express), plus its original size and channel.
  2. Which channels and sizes are needed? List them all, or pull them from the asset list.
  3. Which elements cannot be lost? Text, CTA, logo, faces, product — is anything sitting close to an edge?
  4. Is cropping content allowed, or must everything stay in frame?

Principles

  1. Always resize from the master. Never resize an already-resized file — quality degrades each pass.
  2. Critical elements are never cropped at any size — focal point, CTA, and logo stay intact.
  3. Each ratio needs its own strategy. One approach does not fit all.
  4. If the content will not fit, escalate to the lead to decide what to drop. Do not decide unilaterally.
  5. Repurpose winners immediately after the campaign (D+2) — context fades fast.
  6. Update the status in the asset list as each size is completed.

Workflow

1. Analyze the master

Identify the focal point; the safe distance of each element (text, CTA, logo) from the edges; and what CAN be cropped (background, texture) versus what CANNOT (message, faces, product, CTA).

2. Pick a strategy per target size

Strategy When How
Scale and crop Close ratios (1:1 to 4:5, 16:9 to 1.91:1) Keep the layout, trim background
Re-compose Moderately different ratios (1:1 to 16:9, landscape to cover) Move elements to fit the new frame, preserving hierarchy
Rebuild Very different ratios (1:1 to 9:16, feed to email) Build fresh on the new canvas, keeping concept, colors, and copy

Read the full file on GitHub · 223 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. 9d ago First seen · 223 lines · 179 tokens per session scan A b2a8ad78a084

Subscribe to this mod's changes

50-asset-resize-global is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 179 tokens to every session and 2,916 once invoked, about $0.0009 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 2026-09-03.