hook-formats
Skill23 starsChanged 18 days agoMITView on GitHub
Rewrites one video idea as hooks in six formats (Fortune Teller, Experimenter, Teacher, Investigator, Contrarian, and Magician as a visual layer), each built on a real contrast and real proof. Use when someone needs hook options that are genuinely different, not ten versions of the same line.
In this repository8 other files it gives its agents.
- four-failures-checkSkill
- hook-masterSkill
- lock-inSkill
- niche-tunerSkill
- the-councilSkill
- viewer-panelSkill
- viral-scoutSkill
- visual-matchSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 12
Write it in one line before any hook: "Viewers think [A].
- Distinctive: line 15
If you can't find a contrast the video can prove, the idea is weak.
- Distinctive: line 40
No fake experiments, no invented numbers, no "scientists say".
≈ “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 Formats
Ten hooks in one shape are one hook. Six formats give six real choices. Every format needs a contrast underneath it: what the viewer believes or does now, versus what this video shows.
Step 1: Find the contrast
Write it in one line before any hook: "Viewers think [A]. This video shows [B]."
- Explicit contrast says both sides ("Not more practice. Slower practice.").
- Implied contrast says only B, and the viewer supplies A ("The one setting that fixed my blurry photos").
- If you can't find a contrast the video can prove, the idea is weak. Say so instead of dressing it up.
Step 2: Build the core
A strong hook usually carries these jobs, not as fixed slots but as meanings: a subject (what or who), an action (what happened or what to do), an objective (the result the viewer wants), the contrast, and where the creator has them, proof (a number or a visible result) and time (how fast). Not every hook needs all six. The first four do most of the work.
Step 3: The six formats
| Format | What it does | Shape | Needs |
| Fortune Teller | Says what is coming or what will change for the viewer | "Soon / next time you [situation], [what will be different]" | A real, supportable change. No invented future |
| Experimenter | Shows a test the creator ran and its result | "I tried [x] for [time]. [Surprising part]" | The creator actually did it, in the footage |
| Teacher | Gives a lesson with a clear outcome | "How to [result] without [the thing they hate]" | A real method shown in the video |
| Investigator | Uncovers why something happens | "Why your [thing] [problem], and it's not [the usual guess]" | A real cause the video explains |
| Contrarian | Challenges a common belief | "Stop [common habit]. [What works instead]" | The creator can show the alternative works. No straw man |
| Magician | A visual surprise that stops the thumb. A layer on top of another format, not a hook on its own | Open on the most striking frame, a reveal, a before and after | The frame exists in the footage |
For each format, write: the spoken line, the on-screen text, and the first shot. Drop a format if it needs proof the creator doesn't have, and say why in one line.
Step 4: Pick
Choose the top pick by: clearest topic, strongest true contrast, best match to the first shot, and the payoff closest to the start. Name the runner-up from a different format.
Rules
- No fake experiments, no invented numbers, no "scientists say". Proof is theirs or a [placeholder].
- Contrarian must be fair. Don't attack a belief nobody holds.
- Questions as hooks are fine only if the viewer can't answer "no" and swipe. "Do your photos look blurry?" invites a no. "Why your phone photos look blurry at night" doesn't.
See references/format-bank.md for one idea rewritten in all six formats.
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.