Youtube Angle Ideation logo

Youtube Angle Ideation

Community
matyasstoch
youtube-angle-ideation

Use when David has raw material (podcast transcript, interview, research notes, finished recording) and needs to find the angle/framing for a YouTube video. Funnels from many angles → one-sentence framings → chosen direction before any outline work begins.

Overview

Publishermatyasstoch
Repositorydavid-skills
Skill nameyoutube-angle-ideation
Stars
61
Forks
11
Bundled files
Instructions only
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 matyasstoch on GitHub. Read the source before you install it.

Installation

Install the Youtube Angle Ideation 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/matyasstoch/david-skills/tree/main/skills/creative/youtube-angle-ideation
  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/matyasstoch/david-skills.git /tmp/david-skills
mkdir -p .claude/skills
cp -r /tmp/david-skills/skills/creative/youtube-angle-ideation .claude/skills/youtube-angle-ideation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Youtube Angle Ideation 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 Youtube Angle Ideation 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 Youtube Angle Ideation 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.

YouTube Angle Ideation

David's pre-production funnel for turning raw material (a recorded podcast, an interview transcript, a research dump) into ONE chosen video angle. Run this BEFORE drafting an outline, intro, or thumbnail.

When to Use

  • David has finished recording a podcast/interview and asks "what's this video about?"
  • David shares a transcript and asks for angles, framings, hooks, or "what should we make this?"
  • David is about to write an intro or outline but hasn't locked the angle yet
  • Any pre-production task where the topic is fuzzy

If the angle is already locked, skip this skill and go to youtube-presentation (deck) or intro drafting.

The Funnel (3 stages)

David's proven sequence — DO NOT skip steps or merge them. Each stage narrows.

Stage 1: Read the material

Read the full transcript/source. Form an honest read of what the episode actually IS vs. what it could be framed as. Note tension, surprises, the strongest 2-3 sound bites, the genuine through-line.

Stage 2: 7 angles (broad)

List ~7 distinct angles the video COULD be. Each angle = a different lens. Rank by punch. Mix tactical, mindset, contrarian, meta. One-liner each, no fluff. Add a bonus 8th if there's a strong outlier.

Format:

1. **Angle Name** — one-sentence description of the lens.
2. ...

Stage 3: 10 one-sentence framings

Once David reacts (or just asks for it), give 10 different single-sentence descriptions of "what this video is about." Each sentence must stand alone as a pitch. Vary the emphasis — some lead with the person, some with the result, some with the contrarian take, some with the practical promise.

Keep each under ~20 words. No two should feel like rewrites of each other.

Stage 4 (David picks)

David picks. Only then move to intro/outline/deck.

Critical Rules

  • NEVER say "script." Use "pre-production" or "outline." Banned word.
  • Don't draft the intro until the angle is locked. Even if asked indirectly. Confirm the angle first.
  • Don't combine stages. If David asks for 7 angles, give 7 angles — not 7 angles + the intro + a thumbnail idea. Single-faceted output.
  • Ask broad discovery questions about the DOMAIN, not confirmation of what's written. When narrowing, ask things like "who's the target viewer?" and "what's the hook angle?" — one question at a time, never combined.
  • Honest read first. If the episode is "Mickey explaining his workflow with David as host," say that. Don't pretend it's a David-led manifesto. The angle has to match the actual material.

Pitfalls

  • Giving framings that are all minor rewrites of each other (e.g. all start with "How to..."). Force variety in sentence structure and emphasis.
  • Jumping to intro/outline before David picks. Wait.
  • Treating this like a one-shot brainstorm. It's a funnel — each stage builds on David's reaction to the previous one.
  • Asking multi-part questions ("who's the audience AND what's the hook?"). Split into separate turns.

Related

  • youtube-presentation — after angle is locked, build the slide deck
  • youtube-content — for transcript extraction (yt-dlp / youtube-transcript-api)
  • ns-module-preproduction — different workflow, for NS course modules only

Frequently asked questions

What does the Youtube Angle Ideation AI skill do?

Use when David has raw material (podcast transcript, interview, research notes, finished recording) and needs to find the angle/framing for a YouTube video. Funnels from many angles → one-sentence framings → chosen direction before any outline work begins.

Why use Youtube Angle Ideation on TypingMind?

Because you install it once and use it with any model. Youtube Angle Ideation 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 Youtube Angle Ideation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/matyasstoch/david-skills/tree/main/skills/creative/youtube-angle-ideation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Youtube Angle Ideation?

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 Youtube Angle Ideation?

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

Is the Youtube Angle Ideation AI skill free?

It is published on GitHub by matyasstoch. Check the repository for licensing terms. 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 👇