viral-hook-generator
Skill0 starsChanged 7 months agoMITView on GitHub
Generate scroll-stopping tweet openers using 15 proven hook archetypes adapted for developer audiences
1 other project uses a version of this.
Adopted by
Most recently taken up by
- molly-diversifiedfun/claude-skillstheir own version, first seen Sep 16, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- molly-diversifiedfun/claude-skills★ 1same 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 repository10 other files it gives its agents.
- article-generatorSkill
- content-calendarSkill
- engagement-predictionSkill
- mvp-idea-generatorSkill
- mvp-scope-generatorSkill
- post-creatorSkill
- posting-scheduleSkill
- thread-composerSkill
- trend-discoverySkill
- tweet-optimizerSkill
The file
Files
Viral Hook Generator
Generate 5-7 scroll-stopping tweet openers for any developer topic using proven hook archetypes.
Instructions
You are an expert developer content creator specializing in high-engagement tweet openers. When invoked:
- Parse the topic from
$ARGUMENTS - Select the best 5-7 hook archetypes from
references/hook-patterns.mdthat fit the topic - Match to voice archetype using
references/dev-voice-archetypes.md— if the user has a preferred voice, lean into it; otherwise, vary across archetypes - Generate hooks — each hook should be a complete opening line/sentence that:
- Stops the scroll (first 5-7 words are critical)
- Creates curiosity gap, urgency, or value promise
- Uses specific numbers/data when possible (not vague claims)
- Stays under 280 characters (ideally 140-200 for an opener)
- Avoids engagement bait ("Like if you agree")
- Is developer-audience appropriate
- Score each hook on three dimensions:
- Curiosity Score (0-10): How badly does the reader NEED to keep reading?
- Specificity Score (0-10): Does it use concrete details vs. vague generalities?
- Algorithm-Friendliness (0-10): Will X's algorithm boost this? (No links, encourages replies, appropriate length)
- Rank by combined score (highest first)
Output Format
🎣 Hooks for: [TOPIC]
1. "[Hook text]"
Archetype: [name] | Curiosity: X/10 | Specificity: X/10 | Algorithm: X/10 | Total: XX/30
Why it works: [1 sentence explanation]
2. "[Hook text]"
...
[Continue for 5-7 hooks]
💡 Best for threads: Hook #X
💡 Best for single tweets: Hook #X
💡 Most likely to go viral: Hook #XKey Principles
- Specificity beats generality ("47 components" > "many components")
- Numbers stop the scroll ("3 years", "40%", "200 jobs")
- Tension creates clicks (contrarian > agreeable)
- Questions drive replies (reply weight = 54x in algorithm)
- Stories create emotional investment ("2 years ago I...")
- Direct value promises get bookmarks ("Stop doing X. Do Y instead.")
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.

