hook-storyline
Skill1 starsChanged 2 days agoMITView on GitHub
Storyline, hooks and splitting material into meaningful segments: how to find strong moments in the skeleton, build a beat list for the video's length and goal, and write a hook. Use when planning any video, when cutting, and when writing a script.
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ai-visualizationSkill
- approval-packSkill
- content-atomizationSkill
- dispatchSkill
- fact-checkSkill
- ffmpeg-skillSkill
- idea-diceSkill
- jurySkill
- memory-compactionSkill
- perf-loopSkill
- publish-kitSkill
- seamless-insertSkill
- setupSkill
- shoot-briefSkill
- sound-designSkill
- source-skeletonSkill
- style-memorySkill
- treg-gatewaySkill
- trend-scoutSkill
- utmSkill
- video-codeSkill
- weekly-cycleSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 36
No clickbait that the video does not deliver on.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Hooks and storyline
1. Split the material into meaningful segments
From packed.md: segments by complete thought (not by timer), 20–60 s. For each, record:
the thesis, the emotion, the benefit to the viewer, whether there is visual confirmation (a frame), and a 1–5 score on the axes
hook · completeness · emotion · density of value · payoff.
2. Choose a structure
| Goal | Structure |
| Product / object | Result or before/after first → 3 benefits → offer |
| Expert | Counterintuitive thesis → proof → one practical step |
| Object showcase | Strongest view as the first frame → route → next step |
| SaaS | Pain in one phrase → one task in the interface → result and metric → CTA |
| Story / film | Story spine: once upon a time → every day → but one day → because of that → and finally |
| Selling Reels | PAS (problem → agitation → solution) or BAB (before → after → bridge) |
3. Timing
- 15 s: hook 0–2 s → value → CTA.
- 30 s: hook 3 s / context and stakes 18 s / value 6 s / CTA 3 s.
- 60 s: hook + 3 mini-loops of 15 s each + CTA at about the 50th second.
- A pattern interrupt every 2–4 s (change of shot, zoom, text, sound).
- Leads come from videos watched past 15 s, so retention matters more than brevity.
4. The hook
- It is the same across three channels: what is said + what is seen + what is written.
- Types: contradiction · result first · "the mistake everyone makes" · visual shock / before-after · open loop · a number or a stake · direct address of a pain point ("Worried it won't survive the winter?").
- It is written last, once the whole story is known. 3–5 variants for the sighting round.
- Cold open: the strongest line can be pulled to the start from any point in the material.
- No clickbait that the video does not deliver on.
5. Output: beats.md
| # | t | beat | what is said | what is seen (source: asset/scene or gen) | on-screen text |
|---|---|---|---|---|---|
| 1 | 0–2 | hook | "…" | a1b2/s07 → f05 insert | "Built in one day?" |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.

