hooks
Skill3 starsChanged 34 days agoMITView on GitHub
Hook formulas (YouTube, Instagram, short-form) with Korean patterns; read by the writing skills, not called directly.
22 other projects use a version of this.
Adopted by
Most recently taken up by
- opus-pro/reel-runbooktheir own version, first seen Nov 8, 2026
- Data-Wise/crafttheir own version, first seen Oct 31, 2026
- AI-Answer/ContentRepurposeSystemtheir own version, first seen Oct 28, 2026
- MacHatter1/bb-plugin-hookstheir own version, first seen Oct 25, 2026
- parcadei/Continuous-Claudetheir own version, first seen Oct 17, 2026
- captkernel/claude-writing-toolstheir own version, first seen Oct 15, 2026
Used with
Projects with it also use yt-titles, outlines 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.
Samin12Skillyt-titles
Generate high-performing YouTube title ideas based on the user's video content description, cross-referenced with your recent top-performing videos. Use this skill whenever the user wants YouTube title suggestions, asks "what should I title this video", "give me title ideas", "title options for my video about...", "help me name this video", brainstorming video titles, or any request involving YouTube title generation or optimization. Also trigger when the user mentions titling, naming, or headlining a YouTube video even casually.
Also in 3 projects that use this
Clay-HHKSkilloutlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
Also in 3 projects that use this
BlockSkillfrontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Also in 3 projects that use this
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- duncan-buildroom/freeskills★ 65same name
- nimadorostkar/Claude-Skills-collection★ 33same name
- AI-Answer/ContentRepurposeSystem★ 26same name
- duncan-buildroom/profit-room-skills★ 18same name
- coopersimson96/ai-content-system★ 17same name
- issue-orchestrator/issue-orchestrator★ 10same name
- Samin12/skills★ 8same name
12 more not listed
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 repository50 other files it gives its agents.
- automationsSkill
- commentsSkill
- ig-auditSkill
- ig-captionSkill
- ig-carouselSkill
- ig-dmSkill
- ig-humanSkill
- ig-profileSkill
- ig-reelSkill
- ig-storySkill
- ig-viralSkill
- inboxSkill
- linkedin-comment-drafterSkill
- linkedin-content-plannerSkill
- linkedin-employee-advocacySkill
- linkedin-engager-analyticsSkill
- linkedin-hook-extractorSkill
- linkedin-humanizerSkill
- linkedin-interviewerSkill
- linkedin-post-writerSkill
- linkedin-profile-optimizerSkill
- linkedin-reply-handlerSkill
- linkedin-repurposerSkill
- linkedin-thread-monitorSkill
- naver-ai-citeSkill
- naver-draftsSkill
- naver-engageSkill
- naver-keywordsSkill
- naver-postSkill
- performance-reviewSkill
- publishSkill
- repurposeSkill
- schedule-weekSkill
- setupSkill
- threadsSkill
- troubleshootSkill
- voice-profileSkill
- yt-auditSkill
- yt-benchmarkSkill
- yt-chaptersSkill
- yt-commentSkill
- yt-editSkill
- yt-packageSkill
- yt-planSkill
- yt-retentionSkill
- yt-scriptSkill
- yt-seoSkill
- yt-shortsSkill
- yt-uploadSkill
- yt-viralSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
4
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
- Distinctive: line 25
Read the draft or the topic and who it is for.
- Distinctive: line 29
Keep a filled hook short enough to take in at a glance, and native to the channel: conversational on Threads and Instagram, searchable on …
- Distinctive: line 34
Never invent a number, a result, a named person, a quote or a deadline.
- Distinctive: line 38
Do not open with who the person is or with a request to follow or subscribe.
“Common” is measured: kept by at least 6 in 10 of the 21 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
Adapted from rediumvex/viral-hooks-skill (MIT). Not affiliated with the original author.
Hooks
Shared reference for opening lines: the first seconds of a video, the first line of a post or chain, a carousel cover, the first line of a caption. The writing skills (yt-script, threads, repurpose, schedule-week and the channel skills) read it when they write an opening. It is not a task on its own and it publishes nothing.
The formulas are in references/formulas.md, with their sources and licenses at the top. The YouTube and Instagram lists, and some of the rules below, come from Jakeschincariol/youtube-agent-skill and Jakeschincariol/instagram-agent-skill (both MIT); the short-form list and the way of choosing below from rediumvex/viral-hooks-skill (MIT); the Korean patterns were written for Uplika.
Pick a section
| Writing | Section of references/formulas.md |
| The opening of a YouTube video | YouTube |
| A Reel, Short or other vertical video (spoken line and on-screen line) | |
| A text post, a Threads post or chain, a carousel cover, a caption's first line | Short-form |
| Anything in Korean | Korean patterns first; the other sections for the shape |
How to use
- Read the draft or the topic and who it is for. If there is only a topic, ask one question about the audience or the angle, then go on.
- Choose three formulas from different families: one that stops the scroll (a negation, a number, a question) and one that keeps people reading (a story, a confession, an admission). The third is free.
- Fill each one with the person's own specifics: their number, their reader, their situation. A hook that would fit anyone in the niche is not theirs.
- For video, write the spoken line and the on-screen line separately. The on-screen line is shorter and blunter, because it is read before it is heard.
- Keep a filled hook short enough to take in at a glance, and native to the channel: conversational on Threads and Instagram, searchable on YouTube.
- Return the three with the formula name and section, a line on what each is best for, and which one to lead with and why. The writing skill shows them to the person with the rest of the draft.
Rules
- Never invent a number, a result, a named person, a quote or a deadline. If the person cannot give a real one, pick a formula that does not need it.
- Specific beats big: the number, the time, the reader.
- One idea per hook. A hook carrying two promises keeps neither.
- Deliver what the hook promises early. A promise paid off late loses the people it brought in.
- Do not open with who the person is or with a request to follow or subscribe.
- Across a week of posts, vary the formulas. The same shape every day reads as automated.
- In Korean, write natively from the Korean patterns; do not translate an English hook word for word.
Tools
None. This is reference material; the writing skills that read it call the tools.
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.

