YouTube Transcript skill
Retrieve available captions, then optionally transcribe audio when subtitles are absent.
Community · michalparkola| Author | michalparkola |
|---|---|
| Licence | MIT |
| Source | michalparkola/tapestry-skills · SKILL.md on GitHub |
| Works in | Claude Code · Codex, Gemini CLI, Cursor, Copilot |
| Read from the source on |
The youtube-transcript skill retrieves captions with yt-dlp.
It prefers manual subtitles, then automatic captions; Whisper is an optional last resort.
From the skill's SKILL.md: # YouTube Transcript Downloader
What it does
- Lists subtitles, retrieves a track and optionally cleans VTT.
What you get
- Subtitle files or deduplicated plain text.
When to use it
- Read or quote available video speech.
When not to use it
- Assuming every video has accessible captions.
What it needs
- Network access and yt-dlp; optional Whisper, FFmpeg and model storage for transcription.
Files in the skill
| File or folder | What it is for |
|---|---|
SKILL.md | Subtitle selection, fallback transcription and cleanup steps. |
Licence as found in the repository on 2026-11-16: MIT.
Example prompts
Type one of these after installing; naming the skill makes sure it is used.
- Get this video’s English captions.
- Turn this VTT into readable text.
- List subtitle languages before downloading.
How to install youtube-transcript
Prepare the workflow
Install yt-dlp separately. The fallback asks before downloading audio or models. Keep subtitle timing when you need citations.
yt-dlp --list-subs "YOUTUBE_URL"A skill is a folder with a SKILL.md file. You install it once; the agent reads its short description at the start of each session and loads the full instructions only when a request matches. Pick the place you use:
Claude Code: copy the folder into your skills folder
Put the skill's folder in ~/.claude/skills/ to use it in every project on this computer, or in .claude/skills/ inside a repository to share it with everyone who works there (commit it).
git clone --depth 1 https://github.com/michalparkola/tapestry-skills.git
mkdir -p ~/.claude/skills
cp -R tapestry-skills/youtube-transcript ~/.claude/skills/Claude Code notices new or changed skills in these folders during the session. If the skills folder did not exist when the session started, run /reload-skills once. Then type /youtube-transcript or just describe the task.
On Windows, run the commands in Git Bash or WSL, or copy the folder into the same place with File Explorer.
Codex, Gemini CLI, Cursor and GitHub Copilot
These agents read the same SKILL.md folders. The one folder all four accept inside a project is .agents/skills/, so this copies the skill there:
git clone --depth 1 https://github.com/michalparkola/tapestry-skills.git
mkdir -p .agents/skills
cp -R tapestry-skills/youtube-transcript .agents/skills/| Agent | Project folder | Your user folder | Notes |
|---|---|---|---|
| OpenAI Codex | .agents/skills/ | ~/.agents/skills/ | Type $ or run /skills to pick a skill; Codex also chooses one when your task matches. |
| Gemini CLI | .agents/skills/.gemini/skills/ | ~/.agents/skills/~/.gemini/skills/ | Or install from Git with gemini skills install <git URL> --path <folder> --consent. Google replaced Gemini CLI with Antigravity CLI for free-tier and Google One users on 18 June 2026; Antigravity uses .agents/skills/ in a project and ~/.gemini/config/skills/ for you. |
| Cursor | .agents/skills/.cursor/skills/ | ~/.agents/skills/~/.cursor/skills/ | Type / in Agent chat to pick a skill. Cursor also reads Claude Code's .claude/skills/ folders. |
| GitHub Copilot | .github/skills/.agents/skills/.claude/skills/ | ~/.copilot/skills/~/.agents/skills/ | Works in Copilot CLI, the cloud agent, and agent mode in VS Code, Visual Studio and JetBrains (IDE support depends on the version). Or run gh skill install OWNER/REPOSITORY SKILL (public preview, GitHub CLI 2.90.0 or later). |
Sources for these steps
Checked against each vendor's documentation on 2026-11-14:
Inspect available tracks
Listing subtitles first avoids guessing language codes and distinguishes human captions from automatic transcripts.
Budget for fallback work
Speech transcription needs audio, disk space and a model. It is a separate step with additional download and compute costs.
Questions about youtube-transcript
Does it download the video first?
Caption retrieval can skip the video download.
What if captions are missing?
It can propose local Whisper transcription.
Is automatic text always accurate?
No. Review names, numbers and quotations.
Can private videos fail?
Yes. Access, region and authentication restrictions still apply.
More AI skills
Related skills
Claude Real Video skill
Community · HUANGCHIHHUNGLeoExtract scene-aware frames and speech for evidence-based video discussion.Remotion FFmpeg skill
Community · kajisho5Add measured motion graphics, captions and jump cuts to real footage.Article Extractor skill
Community · michalparkolaExtract an accessible web article into a clean local text file with a reviewed preview.Video Prompting skill
Community · Square Zero LabsDraft model-specific video prompts and consistent-character reference sheets.Motion Film skill
Community · arhenCoordinate branded motion films with a shared clock, design system and delivery checks.Papercut Explainer skill
Community · 0xS4N4TGPlan and build vertical paper-cut explainers through staged, resumable production.