hook-factory
Skill6 starsChanged 4 months agoMITView on GitHub
Generates 20 scroll-stopping hooks for one topic, built structure-first across five proven hook categories, then ranked with the reasoning shown. Use when writing posts, ads, emails, or video openers and the first line has to earn the rest.
In this repository29 other files it gives its agents.
- ad-scriptsSkill
- battlecardSkill
- brand-voiceSkill
- campaign-debriefSkill
- case-study-writerSkill
- channel-pickerSkill
- cmoSkill
- competitor-teardownSkill
- content-calendarSkill
- creative-briefSkill
- customer-deep-diveSkill
- email-sequenceSkill
- experiment-backlogSkill
- funnel-mapSkill
- kpi-treeSkill
- landing-pageSkill
- launch-planSkill
- lead-magnet-builderSkill
- marketing-auditSkill
- market-research-sprintSkill
- message-mapSkill
- objection-mapSkill
- offer-builderSkill
- onboardSkill
- positioning-workshopSkill
- pricing-testSkill
- repurposeSkill
- research-to-briefSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 17
Write 4 hooks in each of these five structures (20 total):
- Distinctive: line 23
Write each hook in the audience's own language (pull from the voice-of-customer bank where available), not marketing language.
- Distinctive: line 28
All 20 hooks grouped by structure, then the ranked top 5 with reasoning, then the #1 hook with its second line.
- Distinctive: line 32
No engagement-bait fingerprints: no "unpopular opinion:", no "I'm going to say it:", no rhetorical "What if I told you".
≈ “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.
Files
Hook Factory — 20 hooks, structure first
Weak content is usually strong content with a dead first line. Hooks are not phrasing exercises — they are structural choices. This skill picks structures first, then writes into them, which is how you get 20 genuinely different hooks instead of 20 rewordings of one.
Inputs
- The topic, angle, or draft the hooks are for, plus who it is aimed at: $ARGUMENTS
- From
marketing-brief.mdif present: the audience's language bank (voice-of-customer), top pains, desired outcomes, and the banned-phrases list.
Do this
- Name the one payoff the content delivers. Every hook must promise this payoff or set up the tension it resolves. If the payoff is fuzzy, sharpen it before writing a single hook.
- Write 4 hooks in each of these five structures (20 total):
- Specific number / result — a concrete stat or outcome, no adjectives doing the work.
- Curiosity gap — open a loop the reader can only close by continuing; never clickbait that the content cannot pay off.
- Bold claim / contrarian take — challenge what the audience believes, only if the content actually backs it.
- Pattern interrupt — say the thing nobody says out loud, or start mid-scene.
- Story open — a moment, not a summary. First line puts the reader somewhere.
- Write each hook in the audience's own language (pull from the voice-of-customer bank where available), not marketing language.
- Rank the 20. Score each on: stops the scroll (1–5), matches the content's real payoff (1–5), sounds like a person (1–5). Show the top 5 with one line of reasoning each.
- For the #1 hook, write the second line too — the hook's job is to get the second line read, and the second line loses most writers.
Output
All 20 hooks grouped by structure, then the ranked top 5 with reasoning, then the #1 hook with its second line. Flag any hook that over-promises what the content delivers.
Rules
- The hook may exaggerate curiosity, never facts. If the content cannot cash the cheque, the hook does not get written.
- No engagement-bait fingerprints: no "unpopular opinion:", no "I'm going to say it:", no rhetorical "What if I told you".
- Specificity beats cleverness. "247 replies" beats "a flood of replies".
- One idea per hook. A hook carrying two ideas is two weak hooks.
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
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.

