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.
npx skills add minhnv0807/ai-business-skills --skill 50-asset-resize-globalgit clone --depth 1 https://github.com/minhnv0807/ai-business-skillsWrote 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.
[](https://agentmods.dev/skills/minhnv0807/ai-business-skills/50-asset-resize-global)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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:
- What is the master? Link to the source file (Canva, Figma, Adobe Express), plus its original size and channel.
- Which channels and sizes are needed? List them all, or pull them from the asset list.
- Which elements cannot be lost? Text, CTA, logo, faces, product — is anything sitting close to an edge?
- Is cropping content allowed, or must everything stay in frame?
Principles
- Always resize from the master. Never resize an already-resized file — quality degrades each pass.
- Critical elements are never cropped at any size — focal point, CTA, and logo stay intact.
- Each ratio needs its own strategy. One approach does not fit all.
- If the content will not fit, escalate to the lead to decide what to drop. Do not decide unilaterally.
- Repurpose winners immediately after the campaign (D+2) — context fades fast.
- 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 |
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.
- 9d ago First seen · 223 lines · 179 tokens per session scan A b2a8ad78a084
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.
Other skills, from other repositories
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
tldraw-offline
Drive and script tldraw offline canvases with an agent.
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
baoyu-infographic
An infographic generator that turns supplied content into a visual summary using different information layouts and visual styles. It supports standard and custom image proportions and multiple languages.
excalidraw
Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).
adversarial-ux-test
Roleplay a hostile user to find and triage UX pain points.