youtube-to-markdown
Skill11 starsChanged 10 months agoMITView on GitHub
Use when user asks YouTube video extraction, get, fetch, transcripts, subtitles, or captions, or channel browsing. Writes video details and transcription into structured markdown file.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- not-manu/skillstheir own version, first seen Jul 6, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- not-manu/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- chrome-controlSkill
- firefox-controlSkill
- imap-slim-cliSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
If input is a channel URL (contains /@, /channel/, /c/, /user/) or a bare channel ID (starts with UC, 24 chars), but NOT watch?v=: Read and …
- Very specific: line 20
Read and follow ./subskills/channel_browse.md.
- Very specific: line 36
If exists: false: Continue to Step 1.
- Very specific: line 38
If exists: true: Read and follow ./subskills/update_flow.md.
- Very specific: line 81
Use --debug to keep intermediate files.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
YouTube to Markdown
Multiple videos: Process one video at a time, sequentially. Do not run parallel extractions. Do not create your own scripts. Channel subfolder naming: Channel Name (channel_id) — always include the channel ID.
Step -1: Detect input type
If input is a channel URL (contains /@, /channel/, /c/, /user/) or a bare channel ID (starts with UC, 24 chars), but NOT watch?v=:
Read and follow ./subskills/channel_browse.md.
Otherwise: Continue to Step 0.
Step 0: Check if extracted before
python3 ./scripts/run.py check "<YOUTUBE_URL>" "<output_directory>"Output JSON contains video_id. Set BASE_NAME = youtube_{video_id} for all subsequent steps.
Tell the user: "Valitse 'Yes, allow all edits during this session'. Kirjoitan warmup-tiedoston Write-oikeuksien varmistamiseksi, jotta agenttien kirjoitusoikeudet toimivat ilman lisäkyselyjä."
Then Write "# Processing {video_id}\n" to <output_directory>/${BASE_NAME}_warmup.tmp. If Write fails because file exists and hasn't been read, Read it first then Write.
If exists: false: Continue to Step 1.
If exists: true: Read and follow ./subskills/update_flow.md.
Step 1: Choose output
AskUserQuestion:
- question: "What do you want to extract from the video?"
- header: "Output"
- multiSelect: false
- options: A. "Summary + Comments (Recommended)" - Summary cross-analyzed with comments. Timestamped transcript stored for reference. B. "Summary + Comments + Formatted Transcript with Watch Guide" - Option A + cleaned and formatted full transcript with synthesized watch guide → double tokens C. "Summary Only" - Summary of video content. Timestamped transcript stored for reference. D. "Formatted Transcript Only" - Cleaned and formatted full transcript
Step 2: Execute modules
Based on user's choice, read and follow each subskill instruction in ./subskills/{file}.
Concurrency: "|" = run concurrently as parallel foreground agents in one message. Never use run_in_background.
Delegation: Subagents cannot launch sub-subagents. Modules that need parallel Agent calls (transcript_polish.md) must be read and executed by the orchestrator directly — do NOT delegate them to an Agent. Only leaf modules (no internal Agent calls) can be delegated.
- A: transcript_extract.md → (transcript_summarize.md | comment_extract.md) → comment_summarize.md
- B: transcript_extract.md → (transcript_summarize.md | transcript_polish.md | comment_extract.md) → comment_summarize.md
- C: transcript_extract.md → transcript_summarize.md
- D: transcript_extract.md → transcript_polish.md
Bold = orchestrator reads and executes directly (not delegated to Agent).
For option B only, create marker file before running modules:
python3 ./scripts/run.py flag "<output_directory>/${BASE_NAME}_watch_guide_requested.flag"Step 3: Finalize
python3 ./scripts/run.py assemble [flag] "${BASE_NAME}" "<output_directory>"Flags: A=--summary-comments, B=(none), C=--summary-only, D=--transcript-only
Use --debug to keep intermediate files.
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
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.