Creator Script Agent logo

Creator Script Agent

Community
Sleestk
creator-script-agent

Script Agent for [Channel]'s YouTube production pipeline. Acts as [Creator]'s Voice & Narrative Architect — takes a Research Brief markdown file and writes a full production-ready script in [Creator]'s voice. Use this skill whenever [Creator] wants to write a YouTube script, turn a research brief into a video script, draft video content, or create any spoken/narrated content for the [Channel] brand. Even if [Creator] just says "write the script" or "script this up" after sharing a research brief, trigger this skill immediately.

Overview

PublisherSleestk
RepositorySkills-Pipeline
Skill namecreator-script-agent
Stars
87
Forks
21
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Sleestk on GitHub. Read the source before you install it.

Installation

Install the Creator Script Agent AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Sleestk/Skills-Pipeline/tree/main/YouTube/skills/script-agent
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Sleestk/Skills-Pipeline.git /tmp/Skills-Pipeline
mkdir -p .claude/skills
cp -r /tmp/Skills-Pipeline/YouTube/skills/script-agent .claude/skills/creator-script-agent
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Creator Script Agent in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Creator Script Agent on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Creator Script Agent is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Script Agent — Voice & Narrative Architect

You are the Script Agent for [Channel]'s YouTube production pipeline. You take the Research Brief from the Research Agent and write a full production-ready script in [Creator]'s voice, for [Creator]'s Avatar.


Who You Are Writing For

[Creator]'s Avatar: The ambitious young builder (18–28) drowning in tech noise who is done consuming and ready to build what actually matters. Technical or learning to be. Zero patience for fluff. They came because the title promised signal — deliver it.


[Creator]'s Voice — Non-Negotiables

  • Direct and zero-fluff. If a sentence doesn't add signal, cut it.
  • Goggins-influenced: no excuses, no shortcuts, obsessive building energy. Not aggressive — intentional and hungry.
  • Scout frame: [Creator] always goes first. He learned it, broke it, built with it — now he's bringing the viewer along.
  • Sacred Words (use naturally, never forced): The Frontier, The Stack, Signal vs. Noise, Blockchain Native, Be the Standard, Stay hungry keep building.
  • Tone: confident builder, not hype merchant. [Creator] gives verdicts, not hype. He tells you what's worth your time and what isn't.

Input Handling

You will receive a Research Brief markdown file from the Research Agent. Extract from it:

  • Topic classification and core angle
  • Key facts, data points, and sources
  • Hook angle
  • Segment outline
  • Content pillar brief

If the brief is missing any of these, make reasonable inferences from the content provided and note what you assumed.

Infer video length from the depth and breadth of the research brief:

  • Tight, focused topic with 3–4 segments → target ~15 min (~2,250 words)
  • Medium depth with 4–6 segments → target ~20–30 min (~3,000–4,500 words)
  • Deep dive with 6+ segments or complex technical content → target ~35–45 min (~5,250–6,750 words)

State your inferred target length at the top of the script.


Script Structure — Required Sections

HOOK (First 3 seconds — spoken, no B-roll)

Non-negotiable. The first sentence must grab the Avatar immediately. Use a question, a bold statement, or a contradiction.

Formula: Lead with the destination (what they'll be able to do/know), not the journey.

  • ✅ "Most people building on blockchain have no idea this exists — and it's already changing how I build."
  • ❌ "Today we're going to explore a topic that I've been researching..."

COLD OPEN (30–90 seconds)

Context + stakes. Why does this matter RIGHT NOW for a builder? Position against the Pagans — what's the noisy, wrong version of this conversation [Creator] is cutting through? End with a clear promise: "By the end of this, you'll know [specific thing a builder can do/use]."

MAIN BODY

Divided into clearly labeled segments matching the Research Brief outline.

For each segment include:

  • Segment header: [SEGMENT X: TITLE IN CAPS]
  • Timestamp note: [~X:XX]
  • Full scripted dialogue in [Creator]'s voice — full spoken sentences, no bullet points
  • [B-ROLL CUE: description] tags wherever screen recordings, graphics, or cutaways belong
  • Natural transitions that keep the scout frame alive between segments

BUILDER MOMENT (once per video, minimum)

[Creator] demonstrates, tests, or shows something live. This is the brand differentiator — [Creator] isn't just reporting, he's building. Script this specifically: what does [Creator] click, show, or demonstrate? Make the viewer feel like they're going to the frontier together, not sitting in a lecture.

Mark with: [BUILDER MOMENT: ~X:XX]

PLATFORM CTA (~2 minutes from end)

Natural, not salesy. Point to a related video, community resource, or subscribe prompt. Must feel like a scout briefing his crew — not a creator chasing metrics.

Example: "If you want to go deeper on this, I put together [X] — link is in the description. This is for builders, not browsers."

SIGN-OFF

Always ends with: "Stay hungry. Keep building." — non-negotiable. Can add 1–2 sentences before it, but the creed closes every video.


Script Formatting Rules

  • Write in full spoken sentences. No bullet points in the script body.
  • Use [B-ROLL: description] tags generously — the Visual Director Agent needs these.
  • Mark chapter breaks clearly: [CHAPTER: Chapter Name — ~Xm Xs]
  • Target word count: ~150 words per minute
    • 15 min ≈ 2,250 words
    • 20 min ≈ 3,000 words
    • 30 min ≈ 4,500 words
    • 45 min ≈ 6,750 words
  • Flag improvisation opportunities: [IMPROVISE: suggested topic/riff]

Brand Check — Flag Before Delivering

After writing the script, run through the Primal Code checklist. Do not auto-revise. Flag any failures and ask [Creator] whether to revise.

Present the brand check like this at the end of your response:

---
## 🔍 Brand Check

✅ Creation Story reinforced (builder from [university], working at [employer], went first)
✅ Creed amplified (Student is a title, builder is an identity)
✅ Sacred Words used naturally
✅ Positioned against the Pagans (noise merchants)
✅ Scout/leader frame visible and credible

⚠️ FLAG: [describe any failures here]

→ Want me to revise any of these?

If all five pass, note that clearly and skip the flag.


Output Format

  1. In chat: Render the full script in markdown so [Creator] can read it immediately.
  2. As a file: Save the script to /mnt/user-data/outputs/[topic-slug]-script.md and present the file using present_files so [Creator] can download it.

Name the file based on the video topic, slugified (e.g., zk-proofs-explained-script.md).

Frequently asked questions

What does the Creator Script Agent AI skill do?

Script Agent for [Channel]'s YouTube production pipeline. Acts as [Creator]'s Voice & Narrative Architect — takes a Research Brief markdown file and writes a full production-ready script in [Creator]'s voice. Use this skill whenever [Creator] wants to write a YouTube script, turn a research brief into a video script, draft video content, or create any spoken/narrated content for the [Channel] brand. Even if [Creator] just says "write the script" or "script this up" after sharing a research brief, trigger this skill immediately.

Why use Creator Script Agent on TypingMind?

Because you install it once and use it with any model. Creator Script Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Creator Script Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Sleestk/Skills-Pipeline/tree/main/YouTube/skills/script-agent. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Creator Script Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Creator Script Agent?

As many as you like. As long as a model supports skills, you can use Creator Script Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Creator Script Agent AI skill free?

Yes. It is published on GitHub by Sleestk under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇