taskchad-os: Skill for Claude Code

.claude/skills/yt-livestream/SKILL.md

yt-livestream is a skill for Claude Code from TheSmokeDev/taskchad-os. It costs 70 tokens per session (2,101 once invoked), scanned A, original, MIT.

A transcript analysis guide that finds self-contained video segments in a YouTube livestream and marks their timestamps.

In plain words
What is it for?
Use it to find ideas for longer videos and Shorts from teaching, demonstrations, reactions, or other notable moments.
Why use it?
It helps locate useful moments in a long livestream without treating the entire recording as one piece of content.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is TheSmokeDev/taskchad-os's own configuration. It tells Claude Code how to work on taskchad-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything taskchad-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TheSmokeDev/taskchad-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TheSmokeDev/taskchad-os/master/.claude/skills/yt-livestream/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/TheSmokeDev/taskchad-os

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for yt-livestream

README.md
[![agentmods](https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/yt-livestream/github.svg)](https://agentmods.dev/skills/thesmokedev/taskchad-os/yt-livestream)
Your own site
<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/yt-livestream"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/yt-livestream/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for yt-livestream

Your own site · 80×15
<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/yt-livestream"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/yt-livestream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,101 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.02101
Opus 5 $0.00035 $0.01051
Sonnet 5 $0.00014 $0.00420
Haiku 4.5 $0.00007 $0.00210

Measured 7d ago against content hash d031637e9efa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

yt-livestream 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 7d 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.

.claude/skills/yt-livestream/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Livestream Content Extractor

Extract repurposable content segments from YouTube livestream transcripts. Identify long-form video opportunities and Shorts moments with precise timestamps.

Philosophy

Livestreams are goldmines of content - hours of authentic teaching, demos, reactions, and insights. The challenge is finding the segments that work as standalone pieces. You're looking for:

Clear boundaries - Where a topic starts and ends naturally Standalone value - Segments that make sense without the surrounding context High-density moments - The exciting, insightful, or visually impressive parts

This isn't about summarizing the stream. It's about identifying extractable segments that could become their own content pieces.

Defaults

Setting Default Notes
Long-form videos 3 Configurable via user request
Shorts 6 Configurable via user request
Output Content-Ideation/Livestream/YYYY-MM-DD/ Single markdown file

If the user specifies different counts (e.g., "give me 5 video ideas and 10 shorts"), use their numbers.

Workflow

1. Read the Transcript

Read the full transcript file the user provides. Livestreams are typically 2-4 hours long, so the transcript will be substantial.

As you read, mentally note:

  • Topic shifts (when the conversation moves to something new)
  • Energy peaks (excitement, emphasis, "this is important" moments)
  • Demo segments (showing something working, building something)
  • Explanatory chunks (clear teaching moments)
  • Hot takes or opinions (strong viewpoints that stand alone)
  • Results/reveals (impressive outcomes, "and here's what we get")

2. Identify Long-Form Video Segments

Target length: 5-30 minutes of content (typically 10-20 minutes works best)

Look for segments with clear topical boundaries - a natural start and end where the content is self-contained.

What makes a good long-form segment:

Type What to Look For
Tutorial/Build Step-by-step walkthrough with setup, implementation, and result
Deep Dive Extended exploration of a single topic, tool, or concept
New Tech Discussion Introduction and breakdown of a new framework, tool, or approach
Problem → Solution Debugging session, architectural decision, or challenge overcome
Comparison/Analysis Evaluating options, trade-offs, or approaches
Q&A Segment Answering viewer questions with substantial depth

Read the full file on GitHub · 239 lines

Changes

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.

  1. 7d ago First seen · 239 lines · 70 tokens per session scan A d031637e9efa

Subscribe to this mod's changes

yt-livestream is a skill published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 2,101 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories