youtube-tools/SKILL.md
Fetch transcripts and create structured watching guides / summaries for YouTube videos. Use when the user asks to (1) get, fetch, extract, or download a transcript or captions from a YouTube video URL, or (2) summarize, create a watching guide, or produce a structured summary of a YouTube video. Trigger on youtube.com/watch, youtu.be, or youtube.com/shorts links.
npx skillsauth add ceshine/ceshine-agent-skills youtube-toolsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Fetch YouTube video transcripts and produce structured watching guides via the defuddle CLI (npx defuddle from the npm registry).
npx defuddle parse <youtube-url> --markdown
Always use --markdown to get the transcript in readable Markdown format.
--lang <code> — request a specific language (BCP 47, e.g. en, ja, zh).-o <file> — write output to a file instead of stdout.A watching guide is a structured summary that breaks a video into segments with summaries and highlighted quotes. Use this workflow when the user asks to summarize a video or create a watching guide.
npx defuddle parse <url> --markdown.watching-guide.md, or as the user specifies).Convert transcript timestamps (MM:SS or HH:MM:SS) to YouTube deep links:
https://www.youtube.com/watch?v=VIDEO_ID&t=TOTAL_SECONDSs
Example: 0:09:57 → &t=597s (9×60 + 57 = 597).
# Watching guide — [Video Title]
*[Brief description, e.g. "Host interviews Guest"] · ~[duration] · [video link]*
---
### `00:00 – 02:00` [Segment Title]
[► 0:00](<video-link>&t=0s)
[2–4 sentence summary of this segment.]
**Highlights**
> *"Verbatim quote from the transcript."*
> [0:01:30](<video-link>&t=90s)
> *"Another notable quote."*
> [0:01:55](<video-link>&t=115s)
---
### `02:00 – 10:30` [Next Segment Title]
[► 2:00](<video-link>&t=120s)
[Summary paragraph.]
**Highlights**
> *"Key quote."*
> [0:05:12](<video-link>&t=312s)
tools
Run Google searches and fetch JS-rendered web pages as Markdown via `google-search-cli`, a Patchright-based CLI invoked through `uvx` from its GitHub repo (no local install needed). Use when the agent needs (1) fresh Google search results from a query, (2) the Markdown of a URL that plain HTTP fetch (curl/WebFetch) cannot render because it requires JavaScript or evades bots, or (3) inspection of the raw HTML of a Google results page. Trigger phrases include "google for ...", "search the web for ...", "fetch this page as markdown", "this page needs JS to render". Do not use for static doc URLs that WebFetch handles cleanly, or when Chromium cannot be installed on the machine.
tools
Always use this skill at the beginning of a session. It establishes how to find and use skills, and requires relevant Skill tool invocation before ANY response including clarifying questions
tools
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations.
development
Retrieve the Markdown version of a public web page from a URL using the agent's built-in URL fetch capability and markdown.new. Use when a user asks for page content in Markdown, cleaner extracted page content for LLM use, or URL-to-Markdown conversion.