youtube-transcribe
Skill1 starsChanged 5 months agoMITView on GitHub
Use this skill when the user provides a YouTube URL and wants its spoken content extracted as text. The trigger pattern is: a youtube.com or youtu.be link paired with any intent to capture what is said — whether phrased as transcribe, get transcript, get captions, convert to text, write up, read, or go through. The URL plus content-extraction intent is the signal. Skip for YouTube API questions, metadata lookups (views, likes, description), or general coding tasks.
- Installs packages
9 other projects use a version of this.
Adopted by
Most recently taken up by
- g-shevchenko/utility-skillstheir own version, first seen Oct 20, 2026
- matthull/my-skillstheir own version, first seen Oct 20, 2026
- chenwei791129/agent-skillstheir own version, first seen Oct 19, 2026
- marks97/youtube-transcribetheir own version, first seen Oct 8, 2026
- chubbyguan/chubbyskillstheir own version, first seen Jun 30, 2026
- tunnckoCore/skillstheir own version, first seen May 31, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- chubbyguan/chubbyskills★ 1.3ksame name
- kennyzir/7deer_skills★ 321same name
- laxmimerit/Claude-Skills★ 6same name
- magnusrodseth/dotfiles★ 3same name
- tunnckoCore/skills★ 2same name
- chenwei791129/agent-skills★ 0same name
- g-shevchenko/utility-skills★ 0same name
- marks97/youtube-transcribe★ 0same name
- matthull/my-skills★ 0same 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 repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- custom-standardsSkill
- agent-code-to-confirmSkill
- agent-to-confirmSkill
- claude-guideline-creationSkill
- skill-creatorSkill
- youtube-to-guidelineSkill
- fastapi-standardsSkill
- general-standardsSkill
- go-standardsSkill
- java-standardsSkill
- nextjs-standardsSkill
- nodejs-standardsSkill
- python-standardsSkill
- react-standardsSkill
- reviewing-codebasesSkill
- rust-standardsSkill
- skill-toggleSkill
- typescript-standardsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 12 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Check the library is installed, installing it if not:
- Distinctive: line 37
Run the bundled script — it fetches every segment, groups them into paragraphs, cleans HTML entities, and applies known ASR corrections …
- Distinctive: line 56
If no transcript can be retrieved at all, report the error and stop — do not fabricate content.
- Distinctive: line 67
Overview: Write 2–3 sentences — who's speaking, what the video covers, the main takeaway.
- Very specific: line 86
Before presenting the final output, apply the agent-to-confirm self-audit:
- Distinctive: line 96
If any of these checks fail, fix the issue before proceeding.
- Distinctive: line 146
If the video has no transcript available, say so clearly and suggest the user check if captions are enabled on the video.
- Distinctive: line 163
Do not compress or summarize content into bullet points — the document sections must contain the full spoken content, just better organized
- Distinctive: line 164
Do not invent section titles that don't reflect actual topic shifts in the speech
- Distinctive: line 165
Do not skip segments because they seem repetitive or filler ("um", "uh", "you know") — clean them naturally into readable prose but do not …
- Distinctive: line 166
Do not add timestamps that weren't in the source data
- Very specific: line 167
Do not fabricate content to fill apparent gaps — mark them as [UNCLEAR] instead
- Distinctive: line 168
Do not claim the transcript is complete if you only fetched a partial response
- Distinctive: line 169
Do not place corrections inline in the document body — they all go at the end in the Corrections Applied section
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
What this skill does
Fetches a YouTube video's captions/transcript and delivers it as clean, structured text that faithfully represents everything spoken — no paraphrasing, no gaps. Where the raw transcript has obvious errors, idioms, or ambiguities, it attempts corrections at 95% confidence and flags anything it cannot confidently fix. It also invokes the agent-to-confirm skill as a final hallucination check before presenting the result.
Step 1 — Extract the video ID
YouTube URLs come in several forms. Parse the video ID from whichever is given:
| URL pattern | Video ID location |
youtube.com/watch?v=VIDEO_ID | v query param |
youtu.be/VIDEO_ID | path segment |
youtube.com/shorts/VIDEO_ID | path after /shorts/ |
youtube.com/embed/VIDEO_ID | path after /embed/ |
youtube.com/live/VIDEO_ID | path after /live/ |
Strip any extra params (&t=30s, ?si=..., etc.) — only the 11-character video ID matters.
Step 2 — Fetch the transcript
Check the library is installed, installing it if not:
pip show youtube-transcript-api || pip install youtube-transcript-apiRun the bundled script — it fetches every segment, groups them into paragraphs, cleans HTML entities, and applies known ASR corrections (e.g. "Cloud Code" → "Claude Code") in one pass:
python ~/.claude/skills/youtube-transcribe/scripts/fetch_transcript.py <VIDEO_ID> <VIDEO_ID>_transcript.mdNote the TOTAL_SEGMENTS=<N> printed at the end — you'll need it for the Step 4 completeness
check. The output file has placeholders for video title, Overview, and section headings —
that's deliberate; the script can fetch and clean text, but judging where a topic shift
happens or what a video is "about" needs the kind of reading comprehension only you can apply.
Step 3 covers filling those in.
If the script can't run (no Python, no filesystem access, or youtube-transcript-api
itself is unreachable — different failure mode than a missing pip package): fall back to
fetching the YouTube watch page via direct HTTP (not WebFetch, which only renders the static
shell) and parsing the captionTracks JSON out of ytInitialPlayerResponse. The baseUrl
inside it is a signed URL that expires within seconds, so fetch and use it immediately.
If no transcript can be retrieved at all, report the error and stop — do not fabricate content.
Step 3 — Fill in title, overview, and section headings
This is the part automation can't do for you — it requires understanding what was actually said.
- Video title: Infer it from the opening lines of the transcript; speakers almost always state the topic in the first 30 seconds. There's no metadata field for this in the fetched segments.
- Overview: Write 2–3 sentences — who's speaking, what the video covers, the main takeaway. Derive this entirely from the transcript, never from outside knowledge. If you state a count ("covers four steps"), count the actual sections you're about to write and make sure it matches — don't estimate from memory.
- Section headings: A new section starts when the speaker explicitly shifts topic ("Now
let's look at...", "The second point is...", "Moving on to...") or there's a clear thematic
break. Don't invent headings where no real shift exists — a single
## Contentsection is fine for videos with no natural breaks. For short videos (< 5 min), 2–4 sections is normal. - Extra corrections: The script already fixes the ASR mishears it knows about. Scan the
rest of the text for homophones (
their/there/they're), missing punctuation, lowercase proper nouns, or run-on misheard phrases. Apply the same 95% confidence rule: ≥95% confident → fix silently and log it in Corrections Applied; below that → leave the original text, wrap it in[?? original text ??], and log it in Uncertain Flags. If a segment is truly unrecoverable, mark it[INAUDIBLE or UNCLEAR: original text]rather than guessing.
Step 4 — Self-audit with agent-to-confirm
Before presenting the final output, apply the agent-to-confirm self-audit:
Decompose your claims and check:
- Completeness — did every segment from the fetched transcript make it into the document? (Count raw segments fetched vs. total segments declared in the header; they must match the
TOTAL_SEGMENTSfrom Step 2.) - No invented content — every sentence in the output must trace back to a fetched segment. Nothing was paraphrased or added.
- Overview accuracy — if the Overview states a count, count the actual sections in the document you just wrote and confirm the number matches.
- Correction honesty — each correction in the Corrections Applied section has a traceable original and a reason you are ≥ 95% confident.
- Uncertain flags are genuine — items in the Uncertain Flags section are things you truly cannot resolve, not things you got lazy about.
- Closing content present — does the last timestamp in the document land near the video's actual end? Auto-grouping can occasionally drop a trailing partial paragraph — check the tail of the source segments against the tail of the document.
If any of these checks fail, fix the issue before proceeding. If you cannot reach 95% confidence on completeness, tell the user explicitly what portion is confirmed vs. uncertain.
Step 5 — Present the structured document
The goal is a document a reader can actually use — organized, readable, and completely faithful to the source.
Document structure:
# [Video Title]
**URL:** [original URL]
**Language:** [language of the caption track used]
**Caption type:** Manual | Auto-generated
**Total segments:** [N]
---
## Overview
[2–3 sentences per Step 3.]
---
## [Section Title]
[Full spoken content of this section, written as clean continuous prose. Preserve every idea, example, and detail from the transcript. Do not paraphrase or compress. The only changes allowed are corrections already logged, plus natural sentence-boundary punctuation absent from the raw captions.]
[Sparse inline timestamps at section starts — e.g., `[01:24]` — so the reader can jump to the source video.]
---
## [Next Section Title]
[Content...]
---
## Corrections Applied
Changes made with ≥ 95% confidence (original → corrected — reason):
- [00:04] "there going" → "they're going" — homophone correction
- *(none)* if no corrections were made
## Uncertain Flags
Items the transcript preserved verbatim because confidence was below 95%. Look for `[?? ... ??]` markers in the sections above:
- [02:15] "the model [?? lears ??] from data" — possible: "learns", "layers", or mishear; not corrected
- *(none)* if no uncertain itemsIf the video has no transcript available, say so clearly and suggest the user check if captions are enabled on the video.
Error handling
| Situation | Response |
No captionTracks in page source (HTTP fallback) | "No captions found. The video may not have captions enabled, or it may be age-restricted/private." |
baseUrl fetch returns empty or error (HTTP fallback) | Retry once with &fmt=json3 appended; if still fails, report the error |
| Video is very long (> 1 hour) | Warn the user before fetching; the transcript may be large. Fetch it anyway and process completely. |
| Non-English captions only | Transcribe in the source language; note this prominently; do not attempt translation unless the user asked for it |
What NOT to do
- Do not compress or summarize content into bullet points — the document sections must contain the full spoken content, just better organized
- Do not invent section titles that don't reflect actual topic shifts in the speech
- Do not skip segments because they seem repetitive or filler ("um", "uh", "you know") — clean them naturally into readable prose but do not drop the underlying idea
- Do not add timestamps that weren't in the source data
- Do not fabricate content to fill apparent gaps — mark them as
[UNCLEAR]instead - Do not claim the transcript is complete if you only fetched a partial response
- Do not place corrections inline in the document body — they all go at the end in the Corrections Applied section
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.

