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 vyralcontent/content-skills --skill viral-youtube-shortsgit clone --depth 1 https://github.com/vyralcontent/content-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/vyralcontent/content-skills/viral-youtube-shorts)<a href="https://agentmods.dev/skills/vyralcontent/content-skills/viral-youtube-shorts"><img src="https://agentmods.dev/badge/skills/vyralcontent/content-skills/viral-youtube-shorts/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/vyralcontent/content-skills/viral-youtube-shorts"><img src="https://agentmods.dev/badge/skills/vyralcontent/content-skills/viral-youtube-shorts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00145 | $0.02889 |
| Opus 5 | $0.00072 | $0.01444 |
| Sonnet 5 | $0.00029 | $0.00578 |
| Haiku 4.5 | $0.00015 | $0.00289 |
Grade A, and why
viral-youtube-shorts 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 12d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Viral YouTube Shorts
Help the user write Shorts that survive the first 3 seconds on the Shorts Feed, hold the retention curve long enough to get pushed wider, and convert feed scrollers into long-form watchers. This skill is YouTube Shorts only. It assumes you already know what a hook is and focuses on what YouTube specifically rewards and punishes.
For cross-platform hook craft, see viral-hooks. For ideation systems, see
viral-short-form-ideas. For caption and on-screen text craft, see
viral-captions-and-ctas. For TikTok or Reels, see those skills.
Operating principles (read these first, apply throughout)
- Shorts runs on its own algorithm. The Shorts feed and long-form recommendations live in separate lanes. A Short does not drag or boost the channel's long-form, and channel size barely counts on the Shorts Feed. Each Short is judged on its own.
- VVSA is the top-of-funnel signal. "Viewed vs Swiped Away" replaced CTR as the gate. Under ~60% tends to flop. 70 to 90% tends to break out. The first 3 seconds decide it.
- The retention curve is the diagnosis. In Studio it's a blue line over a gray band of channel-typical retention. A cliff in the first 3 seconds means the opening is losing people. A later cliff means the payoff stalled.
- Loops are free retention. A Short that loops cleanly (end matches the beginning) can push percentage viewed past 100% and gets weighted as a re-watch. Design the last beat to invite the first.
- The Short to long-form click is the most valuable signal you can earn. Because the algorithms are decoupled, that bridge no longer happens by accident. The right CTA on Shorts is "watch the full video on my channel," not "subscribe."
- Views are inflated. Engaged Views are the truth. A "View" registers the moment a Short starts playing or loops. Only Engaged Views count for YPP and monetization. Read the right number.
- Pattern-matching, not prediction. Say what tends to work and why. Never promise a Short will go viral.
What ships with it
9 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.
- assets/shorts-script-template.md 3.8 KB
- assets/shorts-to-longform-bridge.md 4.8 KB
- assets/shorts-vvsa-checklist.md 2.7 KB
- references/shorts-algorithm.md 5.0 KB
- references/shorts-anti-patterns.md 5.3 KB
- references/shorts-monetization.md 5.1 KB
- references/shorts-retention.md 4.8 KB
- references/shorts-search-and-shelf.md 4.5 KB
- references/shorts-to-longform-funnel.md 5.3 KB
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.
- 12d ago First seen · 182 lines · 145 tokens per session scan A 871db69fc7fb
viral-youtube-shorts is a skill published in the GitHub repository vyralcontent/content-skills (106 stars, last pushed 2mo ago), licensed MIT. It adds 145 tokens to every session and 2,889 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
self-media-short-video
A planning and production guide for vertical short videos on platforms such as TikTok, Xiaohongshu, and WeChat Channels.
self-media-wechat-publisher
A publishing workflow that turns approved Markdown into formatted WeChat articles or image posts and saves them as drafts.
citedy-video-shorts
Generate and publish branded AI avatar lip-sync video shorts to Instagram Reels and YouTube Shorts. Create 15-second talking-head videos with custom avatars, auto-generated scripts, burned-in subtitles, and one-click social publishing for $1.99.
Instagram Post Builder
Interactively builds a complete, copy-paste-ready Instagram post package - three hook variants using distinct patterns, a caption body, one clear CTA, a 15-20 hashtag set across reach tiers, alt text, and a visual direction with shot list or slide breakdown - through a one-question-at-a-time interview, optionally…
citedy-video-shorts
Stateful MCP-first producer for branded AI UGC shorts. Generates scripts, reuses brand/avatar memory, renders vertical talking-head videos, and optionally publishes to Instagram Reels and YouTube Shorts.
image-prompt-engineer
Craft optimized prompts for AI image and short video generation across major models, visual formats, aspect ratios, and content goals. Triggers on image prompts, video prompts, prompt optimization, Flux, DALL-E, Midjourney, and Genfeed visual prompts.