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 Ad-Superpowers/ad-superpowers-plugin --skill tiktok-hook-optimization-guidegit clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-pluginWrote 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/ad-superpowers/ad-superpowers-plugin/tiktok-hook-optimization-guide)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/tiktok-hook-optimization-guide"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/tiktok-hook-optimization-guide/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/ad-superpowers/ad-superpowers-plugin/tiktok-hook-optimization-guide"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/tiktok-hook-optimization-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00115 | $0.05848 |
| Opus 5.5 | $0.00046 | $0.02339 |
| Sonnet 5.5 | $0.00023 | $0.01170 |
| Haiku 4.5 | $0.00012 | $0.00585 |
Grade A, and why
tiktok-hook-optimization-guide 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 1mo 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 — 586 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TikTok Hook Optimization Guide
Purpose
The first 2 seconds of a TikTok ad determine everything. If the hook fails, nothing else matters — the user swipes, your money is spent, and no one sees your message, offer, or CTA. This skill provides a systematic framework for creating, testing, and optimizing hooks that stop the scroll. TikTok's own data shows that ads with strong hooks (>30% hook rate) deliver 2-3x better CPA than weak hooks (<15%).
When to Use This Skill
Invoke when user mentions:
- Hooks: "How do I make a better hook for TikTok?"
- First 2 seconds: "People scroll past my ad immediately"
- Hook rate: "What's a good hook rate on TikTok?"
- Scroll-stopping: "How do I stop the scroll?"
- Video retention: "My watch time is terrible"
- Opening frames: "What should I show in the first frame?"
Required Tools
| Tool | Purpose |
|---|---|
tiktok_get_report |
Pull video performance metrics including view rates and retention |
tiktok_get_ads_with_creatives |
Retrieve ad creatives to analyze hook content and style |
Part 1: Hook Rate Fundamentals
What Is Hook Rate?
Hook Rate = (3-second video views / Impressions) × 100
Alternative definition (TikTok-specific):
Hook Rate = (2-second video views / Impressions) × 100
Note: TikTok reports "2-second video views" and "6-second video views" in its reporting.
The 2-second metric is the truest hook measurement.
Hook Rate Benchmarks
| Hook Rate (2-sec) | Rating | Interpretation |
|---|---|---|
| >40% | Excellent | Top 10% of TikTok ads; scale aggressively |
| 30-40% | Good | Strong performer; optimize other elements |
| 20-30% | Average | Room for improvement; test new hooks |
| 15-20% | Below average | Hook is weak; prioritize hook testing |
| <15% | Poor | Creative is not TikTok-native; rebuild from scratch |
Hook Rate by Industry (Benchmarks)
| Industry | Average Hook Rate | Good Hook Rate | Excellent |
|---|---|---|---|
| Fashion / Apparel | 28-35% | 36-42% | >42% |
| Beauty / Skincare | 30-38% | 39-45% | >45% |
| Food / Beverage | 32-40% | 41-48% | >48% |
| Tech / Apps | 22-28% | 29-35% | >35% |
| Finance / Insurance | 18-24% | 25-30% | >30% |
| Education | 25-32% | 33-38% | >38% |
| E-commerce (general) | 26-34% | 35-42% | >42% |
| SaaS / B2B | 18-25% | 26-32% | >32% |
| Gaming | 30-38% | 39-46% | >46% |
| Health / Fitness | 28-36% | 37-44% | >44% |
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.
- 1mo ago First seen · 586 lines · 115 tokens per session scan A 3eb878a55c6f
tiktok-hook-optimization-guide is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 29d ago), licensed MIT. It adds 115 tokens to every session and 5,848 once invoked, about $0.0005 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 2026-09-11.
Other skills, from other repositories
analytics
Growth analytics authority — GA4 event tracking, conversion funnels, attribution models, cohort analysis, A/B testing, Supabase analytics queries, and revenue reporting patterns.
creative-generate
A workflow for creating advertising images and banners from a strategy brief. It separates the main visual artwork from the accurately typeset text and produces variants for display or social formats.
cro-optimizer
CRO specialist that pulls live analytics data via the Humblytics MCP, analyzes conversion funnels, identifies drop-off points, and generates prioritized A/B test hypotheses. Use when analyzing conversion rates, diagnosing funnel leaks, optimizing signup flows, or creating test roadmaps. Triggers: CRO, conversion rate…
learn
Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all platforms. Use when the user runs /learn, explicitly teaches the agent a marketing insight, corrects the agent's analysis, or asks to remember/record an operational learning for next time. Also use…
lead-form-create
Create a Meta Instant Form (Lead Ad form) through a one-question-at-a-time interview. Use when the user asks to create a lead form, Instant Form, CV form, or similar. The agent collects required parameters via a guided dialogue, confirms, then calls metaadsleadformscreate. Also use when the user asks in Japanese…
ai-hive-simulate-dn-samuel
A research and content-planning workflow that studies DN-Samuel's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.