Run any Skill in Manus with one click

youtube-transcript-to-disk

Stars0

Forks0

UpdatedApril 2, 2026 at 00:08

Fetches a YouTube transcript via TranscriptAPI, writes `.txt` and `.json` under `data/transcripts/youtube/`, and never assumes a default video. Use when the user wants a YouTube transcript saved to disk, TranscriptAPI transcript export, or to avoid losing transcript output in the terminal. Requires an explicit URL or video id every time.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

shiftshapr

shiftshapr/agent-lab

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	youtube-transcript-to-disk
description	Fetches a YouTube transcript via TranscriptAPI, writes `.txt` and `.json` under `data/transcripts/youtube/`, and never assumes a default video. Use when the user wants a YouTube transcript saved to disk, TranscriptAPI transcript export, or to avoid losing transcript output in the terminal. Requires an explicit URL or video id every time.

YouTube transcript → disk (TranscriptAPI)

Rules (non-negotiable)

Never pick a default YouTube video. Do not run the fetch script without the user (or message) supplying a specific watch / youtu.be URL or 11-character video id. If the target is missing, stop and ask for it — do not invent or reuse an example id.
Each successful run charges TranscriptAPI. Do not re-fetch the same video unless the user explicitly asks (e.g. refresh, captions updated). If data/transcripts/youtube/<video_id>.txt already exists, mention it and confirm before calling the API again.
Prefer --quiet so the full transcript is not dumped to stdout; output paths are printed on stderr. Use non-quiet only if the user wants to see the text in the terminal.

Prerequisites

Working directory: agent-lab repo root (workspace/agent-lab).
Credentials in agent-lab/.env: TRANSCRIPT_API_KEY or API_KEY (TranscriptAPI bearer token). The script loads .env automatically.

Command

cd /path/to/agent-lab
node scripts/fetch-transcriptapi-transcript.mjs --quiet "<YOUTUBE_URL_OR_11_CHAR_ID>"

Examples (user-supplied targets only):

node scripts/fetch-transcriptapi-transcript.mjs --quiet "https://www.youtube.com/watch?v=VIDEO_ID"
node scripts/fetch-transcriptapi-transcript.mjs --quiet "https://youtu.be/VIDEO_ID"
node scripts/fetch-transcriptapi-transcript.mjs --quiet VIDEO_ID

Outputs (always written on success)

File	Contents
`data/transcripts/youtube/<video_id>.txt`	Lines `[HH:MM:SS] text`
`data/transcripts/youtube/<video_id>.json`	Raw `transcript` array + `video_url`, `fetched_at`, `line_count`

Paths are under the agent-lab repo; data/transcripts/youtube/ is intended to be commit-friendly (unlike logs/).

Errors

HTTP 404 — API has no transcript for that video (often captions unavailable).
HTTP 408 — Transient; safe to retry with the same URL after a short wait (still one credit per successful attempt; do not spam retries).

Bride pipeline uses Python projects/monuments/bride_of_charlie/scripts/fetch_transcripts.py (TranscriptAPI or youtube-transcript-api). This skill is for explicit TranscriptAPI + guaranteed disk writes via scripts/fetch-transcriptapi-transcript.mjs.

More from this repository

same repository

boc-narrative-layers

shiftshapr/agent-lab

Generate multi-lens narratives for Bride of Charlie from structured data (episodes, claims, graph, social threads); support claim-constraint relaxation for alternate tellings; align book-app chat with meta-layer sources. Use when authoring BOC stories, book-app copy, or enabling others to narrate from the same evidence base.

2026-04-020

discord-community-management

shiftshapr/agent-lab

Plans and operates Discord for Pacha (family-safe, slate/community) and Meta-Layer (governance, DPs, gov hub handoffs): channel maps, mod norms, escalation, announcements, and what belongs in Discord vs GitHub. Use when the user mentions Discord, server setup, moderation, Pacha Discord, meta-layer Discord, community rules, or bot/workflow hooks for servers.

2026-04-020

dp-meta-layer-draft

shiftshapr/agent-lab

Drafts Desirable Property text and inscription-ready variants from app.themetalayer.org DP sources, applying the full meta-layer lens. Saves outputs to the agent-lab Draft Editor via save_draft when available. Produces article-first or video-first companion assets and CTAs for comments and supporting/opposing artifacts. Use when working on DP drafts, on-chain inscription text, gov hub copy, meta-layer properties, Draft Editor, or "draft DPn / desirable property / inscription."

2026-04-020

google-drive-document-ingestion

shiftshapr/agent-lab

Ingest documents from Google Drive into the meta-layer knowledge graph. Converts Word docs, PDFs, and Google Docs to structured knowledge, extracts concepts, and adds to Neo4j. Use when the user wants to process Drive documents, mentions "ingest from Drive", "add Drive docs to graph", or needs to organize Google Drive content into their knowledge base.

2026-04-020

google-drive-knowledge-organizer

shiftshapr/agent-lab

Organize Google Drive documents using meta-layer concepts and knowledge graph relationships. Auto-categorizes documents, creates folder structures, generates knowledge maps, and maintains semantic organization. Use when user wants to "organize Drive by concepts", "restructure Drive folders", "categorize documents", or "create knowledge-based Drive organization".

2026-04-020

google-drive-watcher

shiftshapr/agent-lab

Monitor Google Drive folders for new or updated documents and automatically trigger ingestion workflows. Sets up webhooks and polling to detect changes. Use when user wants to "watch Drive for changes", "auto-ingest new documents", "monitor Drive folder", or set up automated document processing.

2026-04-020

name	youtube-transcript-to-disk
description	Fetches a YouTube transcript via TranscriptAPI, writes `.txt` and `.json` under `data/transcripts/youtube/`, and never assumes a default video. Use when the user wants a YouTube transcript saved to disk, TranscriptAPI transcript export, or to avoid losing transcript output in the terminal. Requires an explicit URL or video id every time.

YouTube transcript → disk (TranscriptAPI)

Rules (non-negotiable)

Never pick a default YouTube video. Do not run the fetch script without the user (or message) supplying a specific watch / youtu.be URL or 11-character video id. If the target is missing, stop and ask for it — do not invent or reuse an example id.
Each successful run charges TranscriptAPI. Do not re-fetch the same video unless the user explicitly asks (e.g. refresh, captions updated). If data/transcripts/youtube/<video_id>.txt already exists, mention it and confirm before calling the API again.
Prefer --quiet so the full transcript is not dumped to stdout; output paths are printed on stderr. Use non-quiet only if the user wants to see the text in the terminal.

Prerequisites

Working directory: agent-lab repo root (workspace/agent-lab).
Credentials in agent-lab/.env: TRANSCRIPT_API_KEY or API_KEY (TranscriptAPI bearer token). The script loads .env automatically.

Command

cd /path/to/agent-lab
node scripts/fetch-transcriptapi-transcript.mjs --quiet "<YOUTUBE_URL_OR_11_CHAR_ID>"

Examples (user-supplied targets only):

node scripts/fetch-transcriptapi-transcript.mjs --quiet "https://www.youtube.com/watch?v=VIDEO_ID"
node scripts/fetch-transcriptapi-transcript.mjs --quiet "https://youtu.be/VIDEO_ID"
node scripts/fetch-transcriptapi-transcript.mjs --quiet VIDEO_ID

Outputs (always written on success)

File	Contents
`data/transcripts/youtube/<video_id>.txt`	Lines `[HH:MM:SS] text`
`data/transcripts/youtube/<video_id>.json`	Raw `transcript` array + `video_url`, `fetched_at`, `line_count`

Paths are under the agent-lab repo; data/transcripts/youtube/ is intended to be commit-friendly (unlike logs/).

Errors

HTTP 404 — API has no transcript for that video (often captions unavailable).
HTTP 408 — Transient; safe to retry with the same URL after a short wait (still one credit per successful attempt; do not spam retries).

Bride pipeline uses Python projects/monuments/bride_of_charlie/scripts/fetch_transcripts.py (TranscriptAPI or youtube-transcript-api). This skill is for explicit TranscriptAPI + guaranteed disk writes via scripts/fetch-transcriptapi-transcript.mjs.