agentleFS
Sign inStart free
lumizonelumizone/social-content-os-claude-skill/skills/hook-lab/SKILL.md

hook-lab

Skill0 starsChanged 5 months agoMITView on GitHub

Generate and rank scroll-stopping hooks for a single content idea. Use when the user wants hooks, openers, first lines, video first-3-seconds, thumbnail text, or says "wymysl hooki", "hook na X", "10 wariacji haka", "scroll-stopper", "give me hooks", "first line for this post", "how should I open this". Takes one idea and produces 10+ hook variations across the full taxonomy (Curiosity Gap, Pattern Interrupt, Challenge a Common Belief, Negation, Number/Result, Before/After), each tagged with its technique and why it works, then ranks them and recommends a top 3 with the visual/written/audio treatment for the winner.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. hongfamonvAI/hook-lab★ 88same name
    2. metaflora-app/metaflora-content-machine★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    No fluff, no jargon, no AI tells (no em-dashes, no "unlock/elevate/dive in").

    line 42
  2. Distinctive:

    Keep them short enough to survive as on-screen text in a "safe zone".

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

hook-lab

One idea in, a batch of ranked hooks out. This is the G(enerate) step of SGTMS applied to attention. Default output: English. Reference: hook taxonomy + Triple-Threat in ../social-content-os/reference/frameworks.md §4. Load ../social-content-os/brand.json for voice and audience.

Inputs

  • The one idea / insight / claim (rooted in an audience problem).
  • Platform + format (Reel hook, carousel slide 1, LinkedIn first line, X post).
  • Optional: the specific pain point or belief to attack.

Method

Generate at least 10 hooks, spread across the taxonomy so the user has real variety to test (not 10 versions of the same technique):

  • Curiosity Gap — open a loop the brain must close.
  • Pattern Interrupt — contrast / unexpected pairing.
  • Challenge a Common Belief — negate industry dogma (strongest trigger).
  • Negation — "Why you should NOT do X."
  • Number / Result — concrete outcome in concrete time.
  • Before / After — transformation.

Rules for every hook:

  • Clear over clever. A specific pain or bold promise beats wordplay.
  • First words do the work — front-load the tension, no warm-up.
  • No fluff, no jargon, no AI tells (no em-dashes, no "unlock/elevate/dive in").
  • Keep them short enough to survive as on-screen text in a "safe zone".

Output

  1. A numbered list of 10+ hooks. Each line: the hook, then — [technique] and a 3–6 word note on the psychological trigger.
  2. Top 3 ranked, with one sentence each on why it will out-test the others for this audience.
  3. For the #1 pick, the Triple-Threat treatment: the Visual (decluttered frame / focal point), the Written (the on-screen text), and the Audio (the spoken first line or sonic cue).
  4. Offer the next step: send the winner to carousel-builder (slide 1) or caption-writer (post body), or run Best of Nine (recreate 3 formats x3).

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.

Check your setup, free