Skip to content
cccskills
FreePublished on GitHub

viral-hooks

Generate platform-native hooks optimized for engagement, curiosity, and audience tension. Use when creating social media hooks, launch post openings, thread starters, video intros, founder story angles, or campaign first lines.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md3.0 KB
  • agents/openai.yaml231 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Viral Hooks

Create hooks that make the right audience want the next sentence. Do not chase generic virality. Optimize for relevance, tension, credibility, and platform fit.

Inputs

  • audience: who should care
  • platform: X, Instagram, Facebook, LinkedIn, TikTok, YouTube, Pinterest, Threads, or Bluesky
  • asset: product, announcement, idea, story, opinion, data point, demo, or lesson
  • desired action: read, reply, click, follow, share, try, join waitlist, or book demo
  • proof: screenshot, metric, user quote, failure, before/after, demo, or specific experience

If no platform is provided, produce hooks for X and LinkedIn by default.

Taste Rules

  • Lead with a specific tension, not a category claim.
  • Make the reader feel "this is about my problem" before asking for attention.
  • Prefer concrete nouns, numbers, stakes, and tradeoffs.
  • Avoid fake contrarianism, engagement bait, vague inspiration, and "game changer" language.
  • Do not overpromise. A hook should create curiosity the post can satisfy.
  • Do not use hashtags unless the user asks.

Workflow

  1. Identify the strongest tension: pain, surprise, status, proof, urgency.

  2. Pick hook families: observation, confession, result, teardown, behind-the-scenes, warning, open loop.

  3. Generate in batches: 10 hooks for the primary platform, 5 safer variants, 5 sharper variants, and 3 anti-hooks to avoid.

  4. Score the best hooks from 1-5 on: audience specificity, curiosity, credibility, platform fit, and follow-through potential.

  5. Return the top 5 with one-line rationale and the post angle each hook implies.

Platform Adjustments

  • X: compressed, opinionated, high information density.
  • Instagram: visual-first, caption supports the creative instead of carrying all context.
  • Facebook: accessible, conversational, clear enough for broader mixed audiences.
  • LinkedIn: clear professional stakes, less irony, more context.
  • TikTok/YouTube: first 1-2 seconds must be visual or spoken plainly.
  • Pinterest: outcome-led, searchable, and tied to a concrete visual promise.
  • Threads: conversational, casual, founder/personality-led.
  • Bluesky: concise, specific, and less sales-coded.

Output Format

## Recommended Hooks
1. "[hook]"
   Angle: [post angle]
   Why it works: [one sentence]
   Score: [x]/25
## Safer Variants
...
## Sharper Variants
...
## Avoid
- "[anti-hook]" - [why]

AgentReacher Notes

This skill works well inside AgentReacher campaign workflows where one product moment becomes scheduled variants across X, Instagram, Facebook, LinkedIn, TikTok, YouTube, Pinterest, Threads, and Bluesky.

Example usage in AgentReacher: "Create hooks for a launch campaign announcing autonomous social posting from ChatGPT and Claude."

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.

The English summary is being prepared. Showing the original description.

ComeOnOliver/skillshub64Updated Jun 24, 2026

Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

The English summary is being prepared. Showing the original description.

ComeOnOliver/skillshub64Updated Jun 24, 2026

Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

The English summary is being prepared. Showing the original description.

ComeOnOliver/skillshub64Updated Jun 24, 2026

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

The English summary is being prepared. Showing the original description.

ComeOnOliver/skillshub64Updated Jun 24, 2026

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

The English summary is being prepared. Showing the original description.

ComeOnOliver/skillshub64Updated Jun 24, 2026

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

The English summary is being prepared. Showing the original description.

ComeOnOliver/skillshub64Updated Jun 24, 2026

See all skills by ComeOnOliver

Report a problem with this skill