YouTube Script — Built for Retention
Hook → reframe → 3 acts → payoff. Designed to hold 60%+ retention.
Prompt
**Role:** Top-decile YouTube editor who has analyzed 1,000+ retention graphs. You know exactly where viewers drop and why — and you've shipped 80+ videos that hold past 60% retention. **Context:** Topic: [specific angle, not "video about X"]. Audience: [channel persona — what they already know, what they don't, what they care about]. Target length: [N minutes]. Differentiator: [the take only YOU can make on this topic]. **Task:** Write the full script with timecodes and b-roll cues. 1. First 8 seconds: a specific image or concrete claim that earns the scroll. NOT "Today we're going to talk about X." Show, don't preview. 2. Reframe (by 0:30): challenge the obvious answer. "Most people think X. Here's why that's not actually the problem." 3. Act 1 (0:30 - target/3): establish the real problem. End with a mini-payoff — a takeaway, a result, a number. 4. Act 2 (target/3 - 2target/3): the meat — the framework, the data, the story. End with another mini-payoff. 5. Act 3 (2target/3 - end): the synthesis or counter-intuitive insight. 6. Final payoff (last 30 seconds): tie back to the hook image. Earn the close. 7. Pattern interrupts every 20-30 sec: cuts, b-roll cues, callouts. Mark them with [b-roll: ...] in the script. **Constraints:** - No "Hey guys / Hi everyone" - No "Don't forget to like and subscribe" - No recap of previous video - Word count = target length × ~150 words per minute **Output format:** Timecoded script · b-roll cues in [brackets] · ≤target length × 150 words.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueSets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.
Learn this techniqueAsks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Content
YouTube Script — 8-min Retention-built
**Role:** Top-decile YouTube creator with 1M+ subs. **Context:** Topic: [SPECIFIC ANGLE]. Audience: [PERSONA]. Target length: 8 min. Differe…
YouTube Short Script (60s)
**Role:** Short-form creator with multi-million viewed Shorts. **Context:** Topic: [SPECIFIC]. Audience: [WHO]. Goal: [reach / sub conversio…
TikTok Script (Creator-style 30s)
**Role:** TikTok creator + strategist. **Context:** Niche: [WHAT]. Audience: [DEMO]. Style: [educational / story / reaction / demo]. **Task:…
Instagram Reels Script (60s)
**Role:** IG Reels creator. **Context:** Niche: [WHAT]. Audience: [WHO]. Format: [educational / B-roll narration / lifestyle]. **Task:** 60s…