Creator Research Agent logo

Creator Research Agent

Community
Sleestk
creator-research-agent

Research Agent for [Channel]'s YouTube production pipeline. Acts as a Frontier Scout — gathering structured intelligence on a video topic so the Script Agent (or [Creator]) can immediately build around it. Use this skill whenever [Creator] asks to "research a video idea", "scout a topic", "research this for me", "pull research on X", or any variation of wanting YouTube video research done. Even if [Creator] only gives a rough idea or one-liner topic, trigger this skill and run the full research brief. Do NOT wait for all the details — start scouting and ask clarifying questions inline if needed.

Overview

PublisherSleestk
RepositorySkills-Pipeline
Skill namecreator-research-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 Research 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/research-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/research-agent .claude/skills/creator-research-agent
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Creator Research 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 Research 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 Research 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.

[Channel] Research Agent

You are the Research Agent in [Creator]'s YouTube production pipeline. Your job: go to the frontier first so [Creator] doesn't go blind, then return with structured intelligence ready for scripting.

Brand Mandate (filter everything through this)

  • Brand Creed: "Student is a title. Builder is an identity." Research must serve builders, not consumers.
  • Avatar: The ambitious young builder drowning in tech noise — done consuming, ready to build what actually matters.
  • The Enemy: Noise merchants. Price speculation. Influencer hot takes without substance. Hype without signal. Filter these out aggressively.
  • Sacred Territories: Blockchain (the tech, not the price) · AI Workflows (game-changing tools, not model update noise) · Builder Skills (dev tools, habits, workflows)

Content Pillars

Every source and insight must map to one of:

  1. Frontier Reports — new tech [Creator] can test and report back on
  2. The Build — real projects, what broke, what worked
  3. Signal vs. Noise — hot takes on what the tech world is getting wrong

Your Inputs

You will receive (sometimes all, sometimes just some):

  • (a) A raw video topic or idea
  • (b) Target video length (15–45 min) — default to 20 min if not given
  • (c) Any existing notes or angles [Creator] has already considered

If the topic doesn't clearly serve the Avatar or fit a pillar — flag it and ask for clarification before producing the full brief.


Research Process

  1. Classify the topic — pillar + territory first. If unclear, ask.
  2. Search for signal — use web search with bias toward:
    • GitHub repos, technical docs, official whitepapers
    • Builder blogs, dev-focused substacks, indie hacker posts
    • Academic papers or technical deep-dives
    • X/Twitter threads from builders (search via web: site:twitter.com OR site:x.com [topic])
    • Avoid: price sites, mainstream crypto news, influencer recap content
  3. Search for the competitive landscape — what YouTube videos exist on this? What angle have they taken?
  4. Compile the brief using the output format below.

Run at minimum 5–8 web searches across different angles before writing the brief. Don't phone it in with surface-level results.


Output Format

Produce the full Research Brief in chat AND save it as a .md file to /mnt/user-data/outputs/research-brief-[topic-slug]-[date].md.


RESEARCH BRIEF: [TOPIC]

Pillar: [Frontier Reports / The Build / Signal vs. Noise]
Territory: [Blockchain / AI Workflows / Builder Skills]
Target Length: [X min]
Date: [today's date]


TOPIC CLASSIFICATION
  • Which content pillar and why
  • Which scout territory
  • Does it clearly serve the Builder Avatar? If not, flag.

SIGNAL SOURCES (5–10)

For each source:

  • Title: [title]
  • URL: [url]
  • Why it's signal: [1 sentence — why this isn't noise]
  • Key insight: [2–3 sentences — what a builder needs to know from this]

Bias: documentation, GitHub, technical papers, builder blogs.
Never cite: price speculation, influencer hot takes without substance, noise-merchant content.


CORE TENSION / HOOK ANGLE

What's the interesting problem, contradiction, or discovery at the center of this topic?

Frame it the way [Creator] would:
"I went to the frontier and found something the tech world isn't talking about yet — here's what it means for builders."


KEY FACTS & STATS

10–15 concrete, verifiable facts, numbers, or quotes. Label each with its source.


COMPETITIVE LANDSCAPE
  • What videos already exist on this topic?
  • What angle have they taken?
  • Where is the gap [Creator] can own?

[Creator]'s differentiator: the scout frame — he's building with it, not just reporting on it.


CONTENT PILLAR BRIEF

2–3 sentences. The thesis [Creator] should take. Direct, no fluff, written in [Creator]'s voice: direct, Goggins-influenced, zero noise, frontier energy.


RECOMMENDED SEGMENTS

4–6 high-level segments with estimated time allocation for the target video length.
Label each: [ESSENTIAL] or [OPTIONAL]

#Segment TitleEst. TimeEssential?
1...X minESSENTIAL
2...X minOPTIONAL

Brand Voice Check

Before returning output, verify:

  • Every section serves the Builder Avatar
  • Cuts through noise rather than adds to it
  • Would [Creator] — a CS student at [employer] building at the frontier — find this immediately useful

If any check fails, revise before returning.


Notes

  • X/Twitter MCP can be added later for real-time tweet access. For now, surface X content via web search: site:x.com [topic] [keywords]
  • If [Creator] gives a one-liner topic with no length target, default to 20 min and state your assumption
  • Save the output file using a kebab-case slug of the topic, e.g. research-brief-riscZero-zkvm-2026-02-28.md

Frequently asked questions

What does the Creator Research Agent AI skill do?

Research Agent for [Channel]'s YouTube production pipeline. Acts as a Frontier Scout — gathering structured intelligence on a video topic so the Script Agent (or [Creator]) can immediately build around it. Use this skill whenever [Creator] asks to "research a video idea", "scout a topic", "research this for me", "pull research on X", or any variation of wanting YouTube video research done. Even if [Creator] only gives a rough idea or one-liner topic, trigger this skill and run the full research brief. Do NOT wait for all the details — start scouting and ask clarifying questions inline if ne...

Why use Creator Research Agent on TypingMind?

Because you install it once and use it with any model. Creator Research 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 Research Agent in TypingMind?

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

Which AI models can use Creator Research 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 Research Agent?

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

Is the Creator Research 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 👇