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.
npx agentmods add skills/cdeistopened/skill-stack/youtube-scriptwritingnpx skills add cdeistopened/skill-stack --skill youtube-scriptwritinggit clone --depth 1 https://github.com/cdeistopened/skill-stackWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00081 | $0.01279 |
| Opus 5 | $0.00041 | $0.00639 |
| Sonnet 5 | $0.00016 | $0.00256 |
| Haiku 4.5 | $0.00008 | $0.00128 |
Grade A, and why
youtube-scriptwriting 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
- Target audience: Who specifically is watching? What do they already know?
- Desired emotion: Pick ONE primary emotion to transfer:
- Awe/inspiration
- Amusement/humor
- Excitement/joy
- Anger/outrage
- Surprise/shock/curiosity
- Sadness/empathy
- 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):
- Alignment: Visual, spoken, and text hooks match
- Speed: Value promised in first 3 seconds
- Clarity: Topic is unmistakable
- Curiosity: Opens a question they must answer
Checkpoint 4: Choose Story Structure & Outline
What ships with it
6 files 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.
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.
- 2d ago First seen · 145 lines · 81 tokens per session scan A 823786c7411a
youtube-scriptwriting is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,279 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…