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 shaomingchan/whiteboard --skill youtube-cover-generatorgit clone --depth 1 https://github.com/shaomingchan/whiteboardWrote 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/shaomingchan/whiteboard/youtube-cover-generator)<a href="https://agentmods.dev/skills/shaomingchan/whiteboard/youtube-cover-generator"><img src="https://agentmods.dev/badge/skills/shaomingchan/whiteboard/youtube-cover-generator/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/shaomingchan/whiteboard/youtube-cover-generator"><img src="https://agentmods.dev/badge/skills/shaomingchan/whiteboard/youtube-cover-generator.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 | $0.00058 | $0.00520 |
| Opus 5.5 | $0.00023 | $0.00208 |
| Sonnet 5.5 | $0.00012 | $0.00104 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
youtube-cover-generator 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.
What it actually says
YouTube Cover Generator
Generate covers through the repository wrapper instead of writing a new prompt or calling an image API directly.
Workflow
- Confirm the repository was bootstrapped and
AI302_KEYis configured. - Extract a concise title, one optional numeric/hook badge, a central subject, an origin scene, a modern consequence scene, and up to six timeline labels from the transcript.
- Run
scripts/generate_cover.pyfrom this skill directory. Default toyoutubewhen the user does not name a platform. - Check that the image and
.prompt.txtfile exist. Report both absolute paths.
python skills/youtube-cover-generator/scripts/generate_cover.py `
--platform youtube `
--title "Main Chinese title" `
--subtitle "Core hook or number" `
--topic "Short content summary" `
--subject "central visual subject" `
--left-context "historical origin scene" `
--right-context "modern consequence scene" `
--timeline "Milestone 1|Milestone 2|Milestone 3|Today" `
--output output/covers/example_youtube.png
Use --dry-run --print-prompt to validate the prompt without spending API credits.
Locked Style
- Keep a flat warm off-white
#F6F1E3background. - Use dark charcoal marker lines and restrained amber accents.
- Use abstract faceless circular-headed people with no hair or facial features.
- Let the illustration dominate; use only one title, one optional badge, and short timeline labels.
- Do not add paragraphs, dense Chinese text, photorealism, 3D, gradients, texture, white patches, or cutout boxes.
- Change only composition and canvas dimensions between platforms; do not invent a new art direction.
Platform Presets
youtube,bilibili,wechat:1280x720xiaohongshu:1440x1920douyin,kuaishou:1080x1920
Use explicit --width and --height only when the delivery platform requires a different size.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 48 lines · 58 tokens per session scan A 9e484a38a8f3
youtube-cover-generator is a skill published in the GitHub repository shaomingchan/whiteboard (50 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 520 once invoked, about $0.0002 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 2026-08-30.
youtube-cover-generator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| youtube-cover-generatorshaomingchan/whiteboard | Skill | 50 | 3mo ago | MIT | A | 58 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |