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-hooksgit 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-hooks)<a href="https://agentmods.dev/skills/vyralcontent/content-skills/viral-hooks"><img src="https://agentmods.dev/badge/skills/vyralcontent/content-skills/viral-hooks/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-hooks"><img src="https://agentmods.dev/badge/skills/vyralcontent/content-skills/viral-hooks.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 | $0.00164 | $0.02476 |
| Opus 5 | $0.00082 | $0.01238 |
| Sonnet 5 | $0.00033 | $0.00495 |
| Haiku 4.5 | $0.00016 | $0.00248 |
Grade A, and why
viral-hooks 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 10d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Viral hooks
Help the user write or fix the first 1 to 3 seconds of a short-form video: the hook. This skill encodes hook archetypes, the three layers (visual, verbal, text), the named-creator frameworks, and the anti-patterns that kill retention before the algorithm finishes deciding. It does not predict virality. It gives the user proven openings instead of a blank frame.
For full script structure, see viral-short-form. For platform algorithm
specifics, see viral-tiktok-content, viral-youtube-shorts, and
viral-instagram-reels. For caption and CTA craft, see
viral-captions-and-ctas.
Operating principles (read these first, apply throughout)
- The hook is the gate, not an ornament. TikTok, Reels, and Shorts decide within roughly 1.5 to 3 seconds whether to keep distributing. If the hook fails, nothing else in the video matters.
- Hand back a batch, not a single line. One hook is a guess. Six to ten across at least three archetypes is a strategy. The user picks the angle, not just the wording.
- Hooks have three layers. Visual, verbal, and on-screen text work together in the first 1 to 2 seconds. A clever verbal line on a flat opening frame is half a hook.
- Specific beats clever. Concrete nouns, odd numbers, and named stakes beat vague intrigue. "I spent $400 on coffee gear" lands. "You won't believe what happened" doesn't.
- Match the promise to the payoff. A hook that oversells what the video delivers gets the click and tanks the satisfaction signal underneath it. Bait-and-switch is the fastest way to get demoted.
- Pattern-matching, not prediction. Hooks raise the odds. They don't guarantee anything. Say what tends to work and why, never that a video will go viral.
- If you can't write the hook, the idea is probably weak. Treat hook writing as idea validation, not final polish. An idea that resists a clean opening line usually has a deeper problem.
What ships with it
8 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.
- 10d ago First seen · 180 lines · 164 tokens per session scan A 4a9548a9c906
viral-hooks is a skill published in the GitHub repository vyralcontent/content-skills (100 stars, last pushed 2mo ago), licensed MIT. It adds 164 tokens to every session and 2,476 once invoked, about $0.0008 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.