agentleFS
rediumvexrediumvex/viral-hooks-skill/SKILL.md

viral-hooks

Skill93 starsChanged 6 months agoMITView on GitHub

Generate 3 scroll-stopping hook variants for short-form video scripts (Reels, TikTok, YouTube, LinkedIn, X). Use when the user is writing a script for short-form video, asks for hook ideas, needs an opening line for a Reel/post, or pastes a script and wants alternative hooks. Pulls from a library of 100 hook formulas across 10 psychology triggers (curiosity, contrarian, authority, emotional, listicle, question, story, negation, specificity, confession).

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the script or topic: If the user only gave a topic (no script), ask one short question about the audience or angle, then proceed.

    line 20
  2. Distinctive:

    After the 3 hooks, give a one-sentence recommendation on which to lead with and why.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Viral Hooks — 100 formulas, 10 psychology triggers

A library of battle-tested hook structures for short-form video and social posts.

When this skill activates

Activate this skill when the user:

  • Pastes a script for a Reel / TikTok / YouTube short / LinkedIn post and wants a hook
  • Asks "give me hooks for [topic]" or "write opening lines about [topic]"
  • Is brainstorming short-form content and needs scroll-stoppers
  • Says /hooks <topic> or /viral-hooks <topic>

Workflow

  1. Read the script or topic. If the user only gave a topic (no script), ask one short question about the audience or angle, then proceed.
  2. Identify the emotional beat the script naturally fits — curiosity, contrarian, authority, emotional, listicle, question, story, negation, specificity, or confession.
  3. Pick 3 candidate hooks from hooks-database.md. Best practice: mix one stop-scroll category (negation / specificity / question) with one retention category (story / confession / emotional). The third is free pick.
  4. Fill the brackets with the script's specific topic, number, pain point, or audience. Keep filled hooks under 12 words. Make them native to the target platform:
    • TikTok / IG → casual, conversational
    • LinkedIn → punchy, declarative
    • YouTube → title-style, search-friendly
    • X → short, contrarian
  5. Return all 3 with category labels and a one-line "best for" note so the user can A/B test or pick the strongest fit.

Output format

HOOK 1 — Cat XX [Category Name] · best for [reason]
"<filled-in hook>"

HOOK 2 — Cat XX [Category Name] · best for [reason]
"<filled-in hook>"

HOOK 3 — Cat XX [Category Name] · best for [reason]
"<filled-in hook>"

After the 3 hooks, give a one-sentence recommendation on which to lead with and why.

Resources

  • hooks-database.md — the 100 hook formulas, organized by category, with examples and best-platform tags. Always read this when the skill activates.
  • preview.html — a styled HTML reference users can open in a browser or send to writers.

Workflow tip

The two best hooks per video are usually from different categories. Mix one stop-scroll hook (negation, specificity, question) with one retention hook (story, confession, emotional). The first stops the thumb; the second keeps them watching past 3 seconds.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.