story-engineering
Skill3 starsChanged 11 days agoMITView on GitHub
Use when creating a storyline, script, or narrative for short-form video (60-90 seconds): story hooks, beat sheets, story frameworks, real-based/true-story structure, retention rules. Not for coding tasks.
In this repository72 other files it gives its agents.
- workflow/AGENTS.mdAGENTS.md
- docs/llms.txtllms.txt
- llms.txtllms.txt
- ai-video-prompt-engineerSkill
- api-contract-designSkill
- api-hardeningSkill
- brainstormingSkill
- cavecrewSkill
- caveman-commitSkill
- caveman-compressSkill
- caveman-helpSkill
- caveman-reviewSkill
- cavemanSkill
- councilSkill
- database-migrationsSkill
- deep-researchSkill
- dependency-auditSkill
- deployment-patternsSkill
- e2e-testingSkill
- error-handlingSkill
- exa-searchSkill
- finishing-a-development-branchSkill
- frontend-securitySkill
- github-opsSkill
- graphifySkill
- graphyloop-wavesSkill
- graphyloop-workflowSkill
- gsap-coreSkill
- gsap-frameworksSkill
- gsap-performanceSkill
- gsap-pluginsSkill
- gsap-reactSkill
- gsap-scrolltriggerSkill
- gsap-timelineSkill
- gsap-utilsSkill
- high-end-visual-designSkill
- image-to-codeSkill
- last30daysSkill
- minimalist-uiSkill
- postgres-patternsSkill
- prisma-patternsSkill
- receiving-code-reviewSkill
- redesign-existing-projectsSkill
- remotion-video-creationSkill
- requesting-code-reviewSkill
- search-firstSkill
- secrets-hygieneSkill
- security-reviewSkill
- security-scanSkill
- short-video-productionSkill
- supabase-setupSkill
- swarm-memorySkill
- systematic-debuggingSkill
- tdd-workflowSkill
- terminal-opsSkill
- threejs-animationSkill
- threejs-fundamentalsSkill
- threejs-geometrySkill
- threejs-interactionSkill
- threejs-lightingSkill
- The first 60 shown.
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 56
No connective tissue between points
≈ “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
Story Engineering
Overview
Short video wins on retention, not prose. Every 60s story = hook → tension → payoff → CTA.
Frameworks
| Framework | Essence | Best for | 60s mapping |
| Mini Hero's Journey | ordinary world → challenge → transformation → new reality | documentary/true-story | setup → tension → payoff |
| Open Loop | question unresolved until final 5s, "I'll show you X, but first..." | best completion rate, TikTok | hook → payoff |
| Problem-Solution | name problem in 1 sentence, agitate cost ~5s, 70% on the fix | explainers/motivation | hook + solution |
| Stacked Micro-Payoffs | small payoff every 8-10s | listicles/facts | entire middle |
| Before-After-Bridge | show AFTER first, then bridge | transformations/results | payoff-first |
The 60-Second Beat Sheet
| Time | Beat | Rule |
| 0-3s | Hook | recognition/tension, text overlay for sound-off |
| 3-8s | Context | name the problem or open the loop |
| 8-45s | Body | ONE promise only, micro-payoff every 8-10s, no dead air |
| 45-55s | Payoff | close the loop / reveal |
| 55-60s | CTA | one ask — save/follow/part 2, never generic "like and comment" |
Word target ~150-160.
Hook Science
Hook strength = relevance × clarity × tension × credibility. Sequence: Recognition → Tension → Proof → Reward.
Formulas: curiosity gap; stakes-first; POV flashback ("On [date], I..."); loss/stakes ("lost everything because of one..."); contrarian; open loop; specific number ("$8,400. One mistake."); visual proof.
Real-Based Story Rules
Real beats fiction:
- Loss stories beat win stories — stakes are instant
- Specificity creates credibility — real numbers/dates/places
- POV/turning-point hooks drop viewer inside the event
- Honest messy details build trust
- One promise only
- Manufactured drama gets called out fast
Validation Checklist
- Hook ≤3s
- One promise
- Stakes/conflict in first 10s
- Payoff before 80%
- CTA in last 10%
- 130-180 words
- Real story: ≥1 verifiable anchor (number/date/place)
Common Mistakes
- Cold open on logo/intro
- No connective tissue between points
- Multiple promises
- Payoff after CTA
- Invented quotes in true stories
Cross-Reference
REQUIRED SUB-SKILL: video-ai-automation for niche/monetization; short-video-production to render.
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.