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 nataliacorrea03/claude-code-skills --skill viral-hook-creatorgit clone --depth 1 https://github.com/nataliacorrea03/claude-code-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/nataliacorrea03/claude-code-skills/viral-hook-creator)<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/viral-hook-creator"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/viral-hook-creator/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/nataliacorrea03/claude-code-skills/viral-hook-creator"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/viral-hook-creator.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 | $0.00092 | $0.01423 |
| Opus 5 | $0.00046 | $0.00711 |
| Sonnet 5 | $0.00018 | $0.00285 |
| Haiku 4.5 | $0.00009 | $0.00142 |
Grade A, and why
viral-hook-creator 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Viral Hook Creator
Purpose
Two modes over the same knowledge base:
- GENERATE: produce 3-5 strong hook options for a topic.
- GRADE: score a hook the user pastes, explain why it works or doesn't, and hand back stronger rewrites.
Hooks are optimized for short-form platforms (X/Twitter, LinkedIn, Instagram, TikTok). Never auto-send or auto-publish. Output is a draft.
Step 0: Determine Mode
- If the user pasted a hook (or a few) and is asking whether it's good / to score / strengthen / rewrite it → GRADE mode.
- Otherwise → GENERATE mode.
- If
$ARGUMENTSis empty and no hook was pasted, respond"viral-hook-creator loaded, proceed with additional instructions"and wait.
Step 1: Load the Library FIRST (both modes)
BLOCKING REQUIREMENT: do this before generating or grading anything.
Read the bundled reference files. These ship with the skill and always work offline:
./references/hook-patterns.md: 19 proven hook patterns with psychology and a selection matrix./references/trigger_words.md: four categories of viral trigger words (Insider, Helper, Thinker, Amplifier)
Optional richer source: if you keep a fuller hooks library as a Notion page (structures, swipe file, interest piques, performance data), set its page ID here and fetch it as the primary source, falling back to the bundled files if the fetch fails:
- Notion page ID:
390f3b91-c73d-81a8-99d6-d77e7f63753e
Swap that ID for your own page, or delete this block to run purely off the bundled files. Do not proceed until the library is loaded.
GENERATE Mode
1. Analyze input
Extract: topic/theme, target platform, goal (awareness, education, engagement, conversion), audience, available social proof. For anything missing, use Defaults & Assumptions.
If FOUNDER_CONTEXT.md exists in the project root, read it and personalize with that business context.
2. Select and draft
- Pick patterns using the selection matrix (match goal + platform). Each of the 3-5 hooks uses a DIFFERENT pattern.
- Draft each hook from the pattern template, adapted to the user's topic.
- Integrate 1-2 trigger words per hook, matched to the pattern.
- If the goal is conversion or a full video, also name the structure each hook would open (if your library has structures).
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.
- 12d ago First seen · 136 lines · 92 tokens per session scan A ca9483a35e9c
viral-hook-creator is a skill published in the GitHub repository nataliacorrea03/claude-code-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,423 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
content-engine
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.