pp-youtube
Search YouTube in bulk, grab transcripts, get embed snippets, fetch top comments, list a channel's recent uploads — for the photo-keywords-to-blog-post workflow. Trigger phrases: `search youtube for`, `find youtube videos about`, `get youtube transcript`, `find videos like`, `youtube embed for`, `top comments on`, `recent uploads from`, `latest videos from @`, `use youtube-pp`, `run youtube-pp`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/media-and-entertainment/youtube/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
# YouTube — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `youtube-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first:
1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows:
```bash
npx -y @mvanhorn/printing-press-library install youtube --cli-only
```
2. Verify: `youtube-pp-cli --version`
3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill.
If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.3 or newer):
```bash
go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/youtube/cmd/youtube-pp-cli@latest
```
If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds.
## When to Use This CLI
Use this CLI when you have search terms (from photo tags, image labels, or notes) and want relevant YouTube videos back — with transcripts to verify relevance and embed snippets to drop into a blog draft. It's read-only and local; not a webapp backend, not a write tool.
## When Not to Use This CLI
Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
### Blog-post composition
- **`youtube search-bulk`** — Take a list of search terms from stdin or args, return top-N YouTube videos per term in one JSON document with titles, channels, embed URLs, and thumbnails.
_When you have N search terms from an upstream pipeline (image labels, photo tags, scraped keywords), reach for this instead of looping single searches._
```bash
youtube-pp-cli youtube search-bulk "sourdough scoring" "latte art" --top 3
```
- **`youtube videos-transcript`** — Fetch the spoken-content transcript of a YouTube video using the timedtext endpoint. Works for auto-generated and manual captions on any public video. Caches into the local store.
_Read the transcript before deciding whether a candidate video actually fits the topic of the blog post or photo._
```bash
youtube-pp-cli youtube videos-transcript dQw4w9WgXcQ --lang en --json
```
- **`youtube videos-embed`** — Print embed HTML, iframe, or markdown-style embed for a video ID. Direct copy-paste into a blog draft.
_Once you've picked a video for the blog, get the embed snippet without remembering the exact iframe URL pattern._
```bash
youtube-pp-cli youtube videos-embed dQw4w9WgXcQ --format markdown
```
### Reachability mitigation
- **`youtube videos-related`** — Find videos related to a target video using topicDetails + same-channel + tag overlap from the local store. Best-effort replacement for the deprecated relatedToVideoId parameter.
_When one candidate video is on-topic but you want more like it, this is the working stand-in for the deprecated parameter._
```bash
youtube-pp-cli youtube videos-related dQw4w9WgXcQ --limit 10 --json
```
### Audience signal
- **`youtube videos-comments`** — Fetch top comments on a video, ranked locally by likeCount. Pulls up to 5 pages from commentThreads.list and sorts so most-liked floats regardless of API order.
_Use to gauge whether a video is actually well-received before embedding, or to surface viewer-supplied context the description doesn't mention._
```bash
youtube-pp-cli youtube videos-comments dQw4w9WgXcQ --top 10
```
### Channel discovery
- **`youtube channel-uploads`** — List a channel's most recent uploads in one call. Resolves @handle or channelId, walks the auto-generated uploads playlist, returns video IDs + titles + publish times.
_Replaces the manual two-step lookup. Pairs naturally with --for-handle workflows._
```bash
youtube-pp-cli youtube channel-uploads @veritasium --top 10
```
## Command Reference
**youtube** — Manage youtube
- `youtube-pp-cli youtube channels-list` — Retrieves a list of resources, possibly filtered. Now supports `--for-handle @handle` for modern channel resolution.
- `youtube-pp-cli youtube comment-threads-list` — Retrieves top-level comment threads, filterable by video, channel, or thread id.
- `youtube-pp-cli youtube playlist-items-list` — Retrieves a list of resources, possibly filtered.
- `youtube-pp-cli youtube playlists-list` — Retrieves a list of resources, possibly filtered.
- `youtube-pp-cli youtube search-list` — Retrieves a list of search resources
- `youtube-pp-cli youtube videos-list` — Retrieves a list of resources, possibly filtered.
### Finding the right command
When you know what you want to do but not which command does it, ask the CLI directly:
```bash
youtube-pp-cli which "<capability in your own words>"
```
`which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match — fall back to `--help` or use a narrower query.
## Recipes
> **Sample use case:** [justinwfu/pictovideo](https://github.com/justinwfu/pictovideo) puts the recipes below into a real photo-keywords → candidate-video → embedded blog draft pipeline. Look there if you want to see the commands wired end-to-end before composing your own flow.
### Photo keywords to candidate videos
```bash
cat photo-keywords.txt | youtube-pp-cli youtube search-bulk --stdin --top 5 --json --select "results[].videoId,results[].title,results[].channelTitle,results[].embedUrl"
```
Reads keywords (one per line), searches each, returns webapp-ready embed-URL JSON. Use --select with dotted paths to keep the output tight.
### Verify a candidate via transcript
```bash
youtube-pp-cli youtube videos-transcript dQw4w9WgXcQ --lang en --json --select "text" | head -c 2000
```
Pull the first 2KB of the transcript to confirm the video is actually about the topic before adding it to the blog.
### Get a markdown embed for the draft
```bash
youtube-pp-cli youtube videos-embed dQw4w9WgXcQ --format markdown
```
Drops a ready-to-paste markdown video reference into your editor buffer.
### Find more candidates like a picked one
```bash
youtube-pp-cli youtube videos-related dQw4w9WgXcQ --limit 5 --json --select "results[].videoId,results[].title"
```
Heuristic-based replacement for the deprecated relatedToVideoId. Uses topic + channel + tag overlap from synced local data.
### Bulk-research pipeline
```bash
cat photo-keywords.txt | youtube-pp-cli youtube search-bulk --stdin --top 3 --json | jq '.results[].videoId' | xargs -I {} youtube-pp-cli youtube videos-transcript {} --json
```
End-to-end: keywords in, transcripts out, ready for a quality filter before blog composition.
## Auth Setup
API-key only — set `YOUTUBE_API_KEY` and you're done. Read-only public-data operations only (10,000 quota units/day default). Write operations are not configured; this CLI is for discovery and research, not channel management.
Run `youtube-pp-cli doctor` to verify setup.
## Agent Mode
Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color --yes`.
- **Pipeable** — JSON on stdout, errors on stderr
- **Filterable** — `--sRelated in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.