agentleFS
sant1jmnzsant1jmnz/claude-code-kit/skills/youtube-scriptwriting/SKILL.md

youtube-scriptwriting

Skill2 starsChanged 3 days agoMITView on GitHub

Transform raw ideas and brain dumps into polished YouTube scripts through a structured checkpoint workflow. Use when the user wants to write a YouTube script, improve video retention, craft hooks, structure educational or entertainment content, or turn source material (transcripts, notes, research) into a compelling video script. Guides through research, hook writing, story structure, body content, and editing phases.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. joaoguirunas/team-os★ 6same name

    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 repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    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
  1. Distinctive:

    All great scripts operate on one principle: Reality must beat expectations.

    line 12
  2. Distinctive:

    When reality > expectations → satisfaction, engagement, shares

    line 16
  3. Distinctive:

    When reality < expectations → disappointment, drop-off, bounce

    line 17
  4. Distinctive:

    Every decision in scriptwriting serves this gap.

    line 19
  5. Distinctive:

    Create a bullet outline BEFORE writing.

    line 75
  6. Distinctive:

    Rehooks: Every 30-60 seconds, reagitate the promise ("But here's where it gets interesting...")

    line 85
  7. Distinctive:

    Second-best first: Put your second-best point first, best point second (creates ascending pattern)

    line 87
  8. Distinctive:

    Run three audits on your draft.

    line 91
  9. Distinctive:

    Read each line: Is this necessary or a tangent?

    line 94
  10. Distinctive:

    Delete anything that breaks the through-line

    line 95
  11. Distinctive:

    Test: Can viewer follow beginning to end without getting lost?

    line 96

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

YouTube Script Writing

Transform disorganized ideas into retention-optimized scripts through a checkpoint-based workflow.

Core Psychology

All great scripts operate on one principle: Reality must beat expectations.

  • Viewer expectations = what they think will happen based on title/thumbnail
  • Reality = what you actually deliver in the video
  • When reality > expectations → satisfaction, engagement, shares
  • When reality < expectations → disappointment, drop-off, bounce

Every decision in scriptwriting serves this gap.

The Workflow

Work through these checkpoints in order. Each builds on the previous.

Checkpoint 1: Define the Foundation

Before writing anything:

  1. Target audience: Who specifically is watching? What do they already know?
  2. Desired emotion: Pick ONE primary emotion to transfer:
    • Awe/inspiration
    • Amusement/humor
    • Excitement/joy
    • Anger/outrage
    • Surprise/shock/curiosity
    • Sadness/empathy
  3. Core promise: One sentence describing what viewer gets from watching

Checkpoint 2: Research & Mine for Shock

Find the facts that will beat expectations. See references/research.md.

Shock Score Method: Rate each fact 1-100 based on "How many viewers would NOT know this?"

  • 80+ = Gold (most viewers surprised)
  • 50-79 = Good supporting points
  • Below 50 = Skip unless essential context

Collect 5-10 high-shock facts before proceeding.

Checkpoint 3: Write the Hook

The hook confirms the click and opens a curiosity loop. See references/hooks.md for the 9 proven formats.

Quick Formula (works for any niche):

  • Target: Who is this for?
  • Transformation: What will they gain?
  • Stakes: What happens if they don't watch?

Hook Commandments (verify all 4):

  1. Alignment: Visual, spoken, and text hooks match
  2. Speed: Value promised in first 3 seconds
  3. Clarity: Topic is unmistakable
  4. Curiosity: Opens a question they must answer

Checkpoint 4: Choose Story Structure & Outline

Pick ONE structure that fits your content. See references/structures.md for all 7 formats.

Most Common Structures:

  • Tutorial: Step-by-step process → Hook → Steps → Outro
  • Listicle: Ordered items → Hook → List → Outro
  • Problem-Solver: Pain → Solution → Hook → Problem → Solution → Outro
  • Case Study: How X achieved Y → Hook → Framework → Outro

Create a bullet outline BEFORE writing. Sequence your shock facts logically.

Checkpoint 5: Write the Body

For each section, use the Value Loop:

  1. Context: What is it? (Simple, clear)
  2. Application: How to use it? (Examples)
  3. Framing: Why does it matter? (Connect to bigger picture)

Retention Techniques (see references/retention.md):

  • Rehooks: Every 30-60 seconds, reagitate the promise ("But here's where it gets interesting...")
  • Setups & Payoffs: Tease information, delay reveal, then deliver
  • Second-best first: Put your second-best point first, best point second (creates ascending pattern)

Checkpoint 6: Edit for Quality

Run three audits on your draft. See references/editing.md.

1. Story Flow Audit

  • Read each line: Is this necessary or a tangent?
  • Delete anything that breaks the through-line
  • Test: Can viewer follow beginning to end without getting lost?

2. Comprehension Audit

  • Target 6th grade vocabulary
  • Shorter sentences (staccato, not run-on)
  • Active voice ("The dog jumped" not "The jumping was done by the dog")
  • Restate complex ideas twice, second time simpler

3. Speed-to-Value Audit

  • Is value signaled in first 3 seconds?
  • Rehooks every 30-60 seconds?
  • Outro summarizes or extends value?

Checkpoint 7: Outro & CTA

Binge Loop Formula (last 15-30 seconds):

  1. Link back to video content naturally
  2. Introduce a NEW problem/question
  3. Promise to solve it in another video or resource

Quick Reference: Script Template

HOOK (0-15 seconds)
- Confirm the click
- Open curiosity loop
- Establish credibility (optional)

BODY SECTION 1 (Rehook → Content → Payoff)
[Second-best point]

BODY SECTION 2 (Rehook → Content → Payoff)
[Best point]

BODY SECTION 3+ (Rehook → Content → Payoff)
[Remaining points in descending order]

OUTRO (Last 15-30 seconds)
- Summarize value delivered
- Binge loop to next video/resource

When to Use Each Reference

  • Starting from scratch with no topic? → references/research.md
  • Stuck on how to start the video? → references/hooks.md
  • Don't know how to organize points? → references/structures.md
  • Retention dropping mid-video? → references/retention.md
  • Script feels clunky or confusing? → references/editing.md

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.