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-resizegit 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)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/50-asset-resize"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/50-asset-resize/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"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/50-asset-resize.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 | $0.00189 | $0.02618 |
| Opus 5 | $0.00095 | $0.01309 |
| Sonnet 5 | $0.00038 | $0.00524 |
| Haiku 4.5 | $0.00019 | $0.00262 |
Grade A, and why
50-asset-resize 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset Resize
Resize khong phai keo to keo nho — moi ti le can re-compose de hierarchy van dung. 1 master design tot → 10+ variants: day la khau tiet kiem thoi gian nhieu nhat cua design production, va la viec dau tien sau campaign (repurpose winner o D+2).
Thu thap thong tin
Doc asset list (41-campaign-asset-list) neu co. Neu thieu, hoi toi da 4 cau:
- Master design la gi? Link file goc (Canva/Figma) + kich thuoc va kenh ban dau?
- Can resize ra kenh / kich thuoc nao? Liet ke het — hay lay theo asset list?
- Element nao khong duoc mat? Text, CTA, logo, khuon mat, san pham — co element nao gan canh khong?
- Duoc phep crop noi dung khong, hay phai giu nguyen toan bo?
Nguyen tac
- Luon resize tu file goc (master) — khong resize tu file da resize (chat luong giam dan).
- Element quan trong khong duoc crop o bat ky kich thuoc nao — focal point, CTA, logo phai con nguyen.
- Moi ratio can chien luoc rieng — khong ap 1 cach cho tat ca.
- Khong giu du noi dung sau resize → bao Leader quyet dinh bo element nao, khong tu quyet.
- Repurpose winner ngay sau campaign (D+2) — de lau mat context.
- Cap nhat trang thai vao asset list sau moi kich thuoc xong.
Quy trinh
Buoc 1 — Phan tich master
Xac dinh: focal point la gi; safe zone cua tung element (text, CTA, logo cach canh bao nhieu); dieu gi CO THE crop (background, texture) va KHONG DUOC crop (message, khuon mat, san pham, CTA).
Buoc 2 — Chon strategy cho tung kich thuoc dich
| Strategy | Khi nao dung | Cach lam |
|---|---|---|
| Scale & Crop | Ratio gan nhau (1:1 → 4:5, 16:9 → 1.91:1) | Giu nguyen layout, crop bot background |
| Re-compose | Ratio khac vua (1:1 → 16:9, landscape → cover) | Dich chuyen element de fit ratio moi, giu hierarchy |
| Rebuild | Ratio khac han (1:1 → 9:16, feed → email) | Lam lai tu dau tren canvas moi, giu concept + mau + copy |
Buoc 3 — Resize theo thu tu uu tien
Lam kich thuoc kenh chinh truoc (thuong Feed 1:1), sau do den cac kich thuoc con lai theo priority trong resize map.
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 · 195 lines · 189 tokens per session scan A ef8a5b1b92c2
50-asset-resize is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 189 tokens to every session and 2,618 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.