agentleFS
ilovefinikiilovefiniki/agent-skills/skills/youtube-action-planner/SKILL.md

youtube-action-planner

Skill0 starsChanged 49 days agoMITView on GitHub

Autonomous deep topic researcher and action plan generator from YouTube video corpora. Selects top fresh videos on a topic, extracts multi-video transcripts simultaneously, and synthesizes an executive implementation plan in Markdown.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When given a topic (e.g. "building autonomous AI agents 2026"):

    line 15
  2. Distinctive:

    Run the batch transcript extractor passing all video URLs:

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

YouTube Action Planner & Topic Researcher

Researches top fresh videos on any technical or business topic, extracts full transcripts in batch, synthesizes multi-expert insights, and compiles an actionable step-by-step implementation plan.


🚀 Workflow

Step 1: Discover High-Authority Videos

When given a topic (e.g. "building autonomous AI agents 2026"):

  • Identify 5 to 10 top-ranking, fresh, high-authority YouTube video URLs.

Step 2: Batch Extract Transcripts

Run the batch transcript extractor passing all video URLs:

python3 scripts/get_transcript.py <URL_1> <URL_2> <URL_3> ... <URL_10>

Outputs a consolidated JSON mapping each video URL to its full text transcript without downloading video or audio streams.

Step 3: Cross-Expert Synthesis

Synthesize the extracted transcripts across all videos:

  • Identify consensus practices vs divergent viewpoints.
  • Filter out sponsor segments, channel promos, and generic fluff.
  • Extract concrete tools, libraries, architectural decisions, and failure modes.

Step 4: Generate Action Plan Report

Format into a clean, structured implementation document saved to ./plans/YYYY-MM-DD_topic-slug.md:

# 📋 Master Action Plan: [Topic Name]

**Synthesized Sources:** {count} videos analyzed  
**Generated:** YYYY-MM-DD  

## 🎯 Executive Summary
[High-level synthesis of current state of the art and key takeaways across all reviewed sources]

## 🛠️ Synthesized Multi-Step Action Plan
- [ ] **Phase 1: Foundation & Setup**
  - Concrete step 1 with rationale from video citations
  - Concrete step 2
- [ ] **Phase 2: Execution & Implementation**
  - Concrete step 3
- [ ] **Phase 3: Hardening & Testing**
  - Concrete step 4

## 💎 Golden Nuggets & Non-Obvious Insights
- Crucial architecture tip from [Creator/Channel] (URL)
- Common pitfall warned by [Creator/Channel] (URL)

## 🔗 Analyzed Sources & Citations
1. [Video Title 1](URL) — Key contribution
2. [Video Title 2](URL) — Key contribution

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.