long-form-youtube

long-form-youtube is a skill for Claude Code, Codex from yaxeen/storytelling-skills. It costs 48 tokens per session (1,664 once invoked), scanned A, original, MIT.

A guide for writing or organising longer YouTube videos, roughly 6–25 minutes, so each section gives viewers a reason to continue to the next one.

In plain words
What is it for?
Use it to outline or write tutorials, essays, reviews, stories, and explainers, or to diagnose where a long-form video loses viewers.
Why use it?
It addresses videos that lose viewers in the middle by connecting the title and thumbnail promise to the script's structure. It helps turn a list of information into a sequence that holds attention.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to outline or write tutorials, essays, reviews, stories, and explainers, or to diagnose where a long-form video loses viewers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yaxeen/storytelling-skills/long-form-youtube
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add yaxeen/storytelling-skills --skill long-form-youtube
Clone the repo
git clone --depth 1 https://github.com/yaxeen/storytelling-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for long-form-youtube

README.md
[![agentmods](https://agentmods.dev/badge/skills/yaxeen/storytelling-skills/long-form-youtube/github.svg)](https://agentmods.dev/skills/yaxeen/storytelling-skills/long-form-youtube)
Your own site
<a href="https://agentmods.dev/skills/yaxeen/storytelling-skills/long-form-youtube"><img src="https://agentmods.dev/badge/skills/yaxeen/storytelling-skills/long-form-youtube/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for long-form-youtube

Your own site · 80×15
<a href="https://agentmods.dev/skills/yaxeen/storytelling-skills/long-form-youtube"><img src="https://agentmods.dev/badge/skills/yaxeen/storytelling-skills/long-form-youtube.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,664 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.01664
Opus 5 $0.00024 $0.00832
Sonnet 5 $0.00010 $0.00333
Haiku 4.5 $0.00005 $0.00166

Measured 12d ago against content hash 7263c517a545, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

long-form-youtube scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/long-form-youtube/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Long-Form YouTube Scripts

  • Short-form wins the first 2 seconds; long-form must win the next 20 minutes.
  • Retention is a chain of open loops: every section opens the next before it closes itself.
  • Built on the six levers — see storytelling-hooks for the full psychology. One-line recap:
    1. Curiosity gap · 2. Emotional mirror · 3. Conflict engine · 4. Relatability · 5. Pattern + surprise · 6. Three-act structure.

When to Use

  • Writing a YouTube video script, tutorial, essay, story, review, or explainer.
  • Planning structure/outline before scripting, or diagnosing a video that "loses people in the middle".
  • Any niche: education, tech, finance, vlog, documentary, business, faith.

Packaging First (Before Any Scripting)

  • Lock the title + thumbnail pair before outlining. The video is written to deliver on the pack, not the other way around — a great script under a weak pack never gets watched. Use titles-and-thumbnails for the pair.
  • Define the target viewer in one sentence: who exactly should click and stay (stage, situation, private worry) — not "everyone interested in X". Every relatability and stakes choice flows from this. The right viewer retained beats the most viewers clicked.
  • Intake before outlining: confirm topic + the user's points, target runtime, audience avatar, goal (subs / sales / session time), and the next video to tease. Always ask for the user's own points if they say they have them — never substitute assumed points for real ones. Everything else may be assumed explicitly if the user can't respond.

Video Skeleton (Quick Reference)

Section Time Job Lever focus
Hook 0:00–0:30 Stop the click-away, make a promise 1, 4, 2
Setup 0:30–1:30 Frame the stakes, preview the payoff 3, 6
Body (chapters) bulk Deliver value as a loop chain all
Sag point ~40–60% Re-hook before attention drops 1, 5
Payoff near end Resolve the opening promise 6
Outro/CTA last 15s One next action 1

Read the full file on GitHub · 121 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 121 lines · 48 tokens per session scan A 7263c517a545

Subscribe to this mod's changes

long-form-youtube is a skill published in the GitHub repository yaxeen/storytelling-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,664 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.