hook-generator
Skill5 starsChanged 15 days agoMITView on GitHub
Generates scroll-stopping hooks for short videos, posts, threads, emails, ads, and YouTube intros using proven psychological frameworks, then scores and ranks them for a specific audience and platform. Use when the user asks for hooks, opening lines, headlines, attention grabbers, or "how should I start this video or post".
9 other projects use a version of this.
Adopted by
Most recently taken up by
- surfmind-space/awesome-surfmindtheir own version, first seen Nov 8, 2026
- milad-ahmd/hook-generatorword for word, first seen Nov 1, 2026
- charlie947/social-media-skillstheir own version, first seen Sep 15, 2026
- aurelioagency/skillstheir own version, first seen Aug 17, 2026
- alebgl77/claude-inctheir own version, first seen Jul 28, 2026
- wltn7810-dotcom/claude-skilltheir own version, first seen Jul 13, 2026
Used with
Projects with it also use reels-scripting, voice-builder and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
mahiunfilteredSkillreels-scripting
Turn a reference Instagram Reel into a script for your own Reel, tuned to your voice and repurposed from your newsletter content. Takes a Reel URL or Notion reference link, uses Apify to scrape the video, sends it to Gemini 2.5 Flash for full transcript + hook + structure analysis, then writes a new script applying the same patterns to your newsletter topic. Use this skill whenever the user says "script a reel", "reels scripting", "turn this into a reel", pastes an Instagram Reel URL, or references their Notion outlier reels database. Requires APIFY_API_TOKEN and GOOGLE_AI_API_KEY environment variables.
Also in 3 projects that use this
mahiunfilteredSkillvoice-builder
Build a personalised voice profile inside a Cowork project from a short interview plus 3 to 5 sample pieces of writing. Works for any content format: LinkedIn posts, newsletters, essays, emails, blog posts, tweets, or any other published writing. Use this skill at the start of any Cowork project where the user wants Claude to learn who they are and how they write before drafting new content. Trigger whenever the user says "build my voice", "learn my voice", "set up my content system", "onboard me", "train on my writing", "train on my posts", "I want Claude to sound like me", or drops a batch of writing samples into chat at the start of a project. Also trigger for first-time Cowork users who need a voice foundation before writing anything. Always produces two files (about-me.md and voice.md) saved into the project root.
Also in 3 projects that use this
FlavioZanoniSkillprofile-optimizer
Audit and optimize a LinkedIn profile for recruiter discoverability using browser automation. Fixes Open to Work settings, headline keywords, location, top skills, languages, projects, About section, and experience descriptions. Use when user wants to improve their LinkedIn profile for job searching or increase inbound recruiter messages. Part of the Mercury job search toolkit.
Also in 3 projects that use this
Other versions9 projects use a version of this.
Word for word · 1
- milad-ahmd/hook-generator★ 0100% same
Edited · 0
None found.
Wrote their own version · 8
- charlie947/social-media-skills★ 4.4ksame name
- alebgl77/claude-inc★ 21same name
- OpenAnalystInc/10x-Content-Expert★ 15same name
- surfmind-space/awesome-surfmind★ 8same name
- aiimpactagency/social-media-team★ 3same name
- aurelioagency/skills★ 1same name
- mahiunfiltered/claude-code-skills★ 1same name
- wltn7810-dotcom/claude-skill★ 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 repository56 other files it gives its agents.
- docs/llms.txtllms.txt
- a11y-fixerSkill
- ad-copy-generatorSkill
- agent-guardrailsSkill
- agent-memory-keeperSkill
- ai-slop-detectorSkill
- api-to-sdkSkill
- app-store-optimizerSkill
- architecture-doctorSkill
- brand-voice-guideSkill
- bug-detectiveSkill
- changelog-from-gitSkill
- codebase-explainerSkill
- codebase-time-machineSkill
- commit-craftSkill
- competitor-spySkill
- content-repurposerSkill
- cost-cutterSkill
- demo-recorderSkill
- dependency-doctorSkill
- dockerize-anythingSkill
- durable-agent-workflowsSkill
- e2e-flow-testerSkill
- email-campaign-writerSkill
- env-secrets-guardSkill
- gh-actions-auditorSkill
- incident-commanderSkill
- influencer-outreachSkill
- instagram-growth-managerSkill
- landing-page-roasterSkill
- launch-post-writerSkill
- meeting-notes-to-ticketsSkill
- merge-conflict-resolverSkill
- migration-wizardSkill
- plan-grillerSkill
- prompt-injection-scannerSkill
- pr-reviewer-proSkill
- readme-glow-upSkill
- roast-my-githubSkill
- screenshot-to-componentSkill
- seo-blog-writerSkill
- skill-creator-proSkill
- skill-finderSkill
- skills-doctorSkill
- social-analytics-reporterSkill
- social-media-calendarSkill
- social-media-managerSkill
- sql-optimizerSkill
- startup-idea-validatorSkill
- tdd-loopSkill
- terse-modeSkill
- test-gap-hunterSkill
- tiktok-viral-creatorSkill
- ui-tasteSkill
- youtube-script-writerSkill
- youtube-seo-optimizerSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
Never promise what the content doesn't deliver.
- Very specific: line 36
Use real numbers from the user only.
- Distinctive: line 38
Avoid clichés ("In today's fast-paced world", "Did you know…" without a payoff).
“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.
Files
Hook Generator
The first line decides whether anyone reads or watches the rest.
Input
The topic or content, the platform (TikTok, Reels, Shorts, YouTube intro, X, LinkedIn, email subject, ad), the audience and their main pain or desire, and the tone (bold, friendly, professional, funny).
Frameworks (produce at least 2 hooks per framework, about 20 in total)
- Curiosity gap: "Nobody talks about the real reason X happens…"
- Contrarian: "Unpopular opinion: X is a waste of time"
- Negative / warning: "Stop doing X if you want Y"
- Specific result: "How I got [specific number] in [timeframe] with [unexpected method]"
- Callout: "If you're a [specific person] who [specific situation], this is for you"
- Story drop-in: "I almost quit last Tuesday."
- List or promise: "3 tools that save me 10 hours a week"
- Question: "Why do 90% of X fail at Y?", but only with a real stat or attribution.
- Before/after: "From X to Y. Here's what changed."
- Myth-bust: "You've been told X. That's wrong."
For video, pair each hook with a visual hook (the action or shot in the first second) and the on-screen text.
Score and rank
Score each hook from 1 to 5 on: clarity, curiosity, relevance to the audience, specificity, and whether the content can deliver on the promise. Return the top 5 with a short explanation of why each works, followed by the rest.
Rules
- Never promise what the content doesn't deliver. Clickbait kills retention and trust.
- Use real numbers from the user only. Otherwise use placeholders like
[X]. - Match the length to the platform: a video hook is spoken in 2 seconds or less, email subjects are 50 characters or fewer, and the first line of a LinkedIn post is 12 words or fewer.
- Avoid clichés ("In today's fast-paced world", "Did you know…" without a payoff).
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.

