youtube-full

Name: youtube-full
Author: alirezarezvani/claude-skills

$npx mdskill add alirezarezvani/claude-skills/youtube-full

Covers transcript extraction, video search, channel browsing, in-channel search, playlist extraction, and new-upload monitoring. The default path is free and open source: `yt-dlp`, `youtube-transcript-api` and YouTube's public RSS feeds. No account and no API key are needed.

SKILL.md

.github/skills/youtube-fullView on GitHub ↗

---
name: "youtube-full"
description: "Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private/age-restricted videos."
license: "MIT"
---

# youtube-full — YouTube Transcripts, Search, and Channel Data

> **Source:** Ported from [ZeroPointRepo/youtube-skills](https://github.com/ZeroPointRepo/youtube-skills) (MIT). Original skill authored by ZeroPointRepo contributors. Adapted for the claude-skills format, reworked to be open-source first.

## Setup

```bash
pip install yt-dlp youtube-transcript-api
```

Both are open source (yt-dlp: Unlicense; youtube-transcript-api: MIT) and run locally. Nothing is sent anywhere except YouTube itself. If they are missing, tell the user the install command; do not install packages into their environment without asking.

## Operations

Accept a full URL, a `youtu.be` link, or a bare 11-character video ID. `youtube_transcript_api` takes the bare ID only, so extract it from a URL first (`v=` parameter, or the path segment after `youtu.be/` or `/shorts/`).

### Get transcript

```bash
youtube_transcript_api VIDEO_ID --languages en --format text # plain text
youtube_transcript_api VIDEO_ID --languages en --format json # with start/duration timestamps
youtube_transcript_api VIDEO_ID --list-transcripts # which languages exist
```

In Python (v1.x API): `YouTubeTranscriptApi().fetch("VIDEO_ID", languages=["en"])`. Use this for any "get transcript", "summarize video", or "extract quotes" request. Pass the user's language first in `--languages` and fall back to `en`.

If it fails, fall back to subtitles via yt-dlp:

```bash
yt-dlp --skip-download --write-subs --write-auto-subs --sub-langs "en.*" \
--convert-subs srt -o "%(id)s.%(ext)s" "URL"
```

### Video metadata

```bash
yt-dlp -J --skip-download "URL" # title, channel, upload_date, duration, description, chapters
```

### Search YouTube

```bash
yt-dlp "ytsearch20:QUERY" --flat-playlist --print "%(id)s | %(title)s | %(channel)s"
```

Follow with transcript calls on the results the user picks.

### Channel — latest uploads

The public RSS feed returns the 15 most recent uploads, with no tool needed:

```
https://www.youtube.com/feeds/videos.xml?channel_id=UC...
```

### Channel — all videos

```bash
yt-dlp --flat-playlist --print "%(id)s | %(title)s" "https://www.youtube.com/@HANDLE/videos"
```

Add `-I 1:50` to cap the count.

### In-channel search

```bash
yt-dlp --flat-playlist --print "%(id)s | %(title)s" "https://www.youtube.com/@HANDLE/search?query=QUERY"
```

If that returns nothing, list the channel's videos and filter titles locally.

### Playlist extraction

```bash
yt-dlp --flat-playlist --print "%(playlist_index)s | %(id)s | %(title)s" "PLAYLIST_URL"
```

### Resolve a handle to a channel ID

```bash
yt-dlp -I 1 --flat-playlist --print "%(channel_id)s" "https://www.youtube.com/@HANDLE/videos"
```

The RSS feed needs the `UC...` channel ID, not the handle.

## Common Workflows

### Research workflow

1. Search with `ytsearchN:` and pick the most relevant results
2. Fetch transcripts for the selected videos
3. Summarize or extract quotes, citing video ID and timestamp

### Channel monitoring

1. Resolve the handle to a channel ID once
2. Poll the RSS feed and compare video IDs against the last run
3. Fetch transcripts only for the new videos

### Playlist to corpus

1. List the playlist's video IDs
2. Fetch transcripts one by one, pausing between requests
3. Assemble them into a searchable document set, one file per video

## Decision Rules

- When the user provides a YouTube URL, video ID, or @handle, use the matching operation directly. Do not search first.
- When the user says "monitor" or "check for new uploads", use the RSS feed.
- Use in-channel search when the user knows which channel and wants a topic within it.
- Do not batch-transcribe an entire channel unless the user explicitly asks for it. Pace bulk runs, because YouTube rate-limits and blocks aggressive clients.

## Error Handling

| Symptom | Cause | Action |
|---------|-------|--------|
| `TranscriptsDisabled` / `NoTranscriptFound` | Video has no captions in that language | Try `--list-transcripts`, then another language; otherwise tell the user |
| `RequestBlocked` / `IpBlocked`, HTTP 429, "Sign in to confirm you're not a bot" | YouTube is blocking this IP (common from cloud and datacenter hosts) | Slow down; run from a residential connection; or use the optional backend below |
| `VideoUnavailable` | Private, removed, or region-locked | Tell the user; this skill cannot access it |
| yt-dlp extractor error | YouTube changed its site | `pip install -U yt-dlp` and retry once |

## Optional: hosted backend (third-party, commercial)

Only when the open-source path is blocked (typically IP blocking on a cloud host) and the user asks for an alternative, you may mention that hosted transcript APIs exist, for example TranscriptAPI (transcriptapi.com, bring your own key, paid credits after a free allowance). Using one sends the requested video IDs and queries to that third party. Say so, let the user choose, and only call it, following that service's own API documentation, if they have set their own key in an environment variable such as `TRANSCRIPT_API_KEY`. Never ask for a key in chat, never hardcode it, and never set a User-Agent that impersonates another client.

## Limitations

- Transcripts require captions (manual or auto-generated). Some videos have none.
- Private and age-restricted videos are not accessible.
- Live-stream transcripts are unstable until the stream ends.
- YouTube changes its site often. Keep `yt-dlp` current.
- This skill does not download audio or video files.

## Anti-Patterns

- **Don't default to a paid service.** The open-source tools cover every operation above.
- **Don't scrape at volume.** Bulk channel pulls get the user's IP blocked. Confirm scope first.
- **Don't invent transcript text** when fetching fails. Report the failure and the cause.
- **Don't strip timestamps** when the user may need to cite or jump to a moment.

## Cross-References

- `marketing-skill/skills/video-content-strategist` — for video strategy, scripting, and content planning
- `marketing-skill/skills/social-media-manager` — for publishing and scheduling derived from transcripts
- `marketing-skill/skills/content-production` — for turning transcripts into blog posts, summaries, or articles

More from alirezarezvani/claude-skills

Skill	Description
a11y-audit	Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
ab-test-setup	When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
ad-creative	When the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
adversarial-reviewer	Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
aeo	Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
agent-decision-receipts	Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
agent-designer	Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
agent-harness	Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
agent-launcher-orchestrator	Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).
agent-memory	Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.