youtube-to-bookplayer
Download YouTube audio and push to BookPlayer on iPhone via USB. TRIGGERS - youtube audio, bookplayer, download youtube
What this skill does
# youtube-to-bookplayer
Download audio from a YouTube video, tag metadata, and push to BookPlayer on iPhone via USB.
BookPlayer is an iOS audiobook player that resumes playback position — ideal for long-form YouTube content (lectures, audiobooks, podcasts). Files pushed to its `/Documents/` directory are auto-imported on next app launch.
---
> **Self-Evolving Skill**: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
## Task Template
Execute phases 0–5 sequentially. Each phase has a `[Preflight]`, `[Ask]`, `[Execute]`, or `[Verify]` tag indicating its nature. **Do not skip phases.**
---
### Phase 0: Preflight [Preflight]
Check all required tools and device connectivity. **Fail fast** — do not proceed if any check fails.
```bash
# Tool availability
TOOLS_OK=true
for tool in yt-dlp ffmpeg exiftool; do
if command -v "$tool" &>/dev/null; then
echo "$tool: OK ($(command -v "$tool"))"
else
echo "$tool: MISSING"
TOOLS_OK=false
fi
done
# pymobiledevice3 (may only be available via uvx)
if command -v pymobiledevice3 &>/dev/null; then
echo "pymobiledevice3: OK ($(command -v pymobiledevice3))"
else
if uvx --python 3.14 --from pymobiledevice3 pymobiledevice3 --help &>/dev/null 2>&1; then
echo "pymobiledevice3: OK (via uvx)"
else
echo "pymobiledevice3: MISSING"
TOOLS_OK=false
fi
fi
echo "---"
[ "$TOOLS_OK" = true ] && echo "All tools OK" || echo "BLOCKED: Install missing tools (see table below)"
```
**If tools are missing:**
| Tool | Install Command |
| ----------------- | ----------------------------------------------------------------- |
| `yt-dlp` | `brew install yt-dlp` |
| `ffmpeg` | `brew install ffmpeg` |
| `exiftool` | `brew install exiftool` |
| `pymobiledevice3` | `uvx --python 3.14 --from pymobiledevice3 pymobiledevice3 --help` |
**Device check** (only after tools pass):
```bash
# Check for connected iOS device
pymobiledevice3 usbmux list 2>/dev/null || uvx --python 3.14 --from pymobiledevice3 pymobiledevice3 usbmux list
# Check BookPlayer is installed
pymobiledevice3 apps list --no-color 2>/dev/null | grep -i "audiobookplayer\|bookplayer" || \
uvx --python 3.14 --from pymobiledevice3 pymobiledevice3 apps list --no-color 2>/dev/null | grep -i "audiobookplayer\|bookplayer"
```
If no device found: ask user to connect iPhone via USB, unlock it, and tap "Trust This Computer".
If BookPlayer not found: ask user to install BookPlayer from the App Store.
---
### Phase 1: Accept URL & Confirm [Ask]
**If `$ARGUMENTS[0]` is provided**, use it as the YouTube URL. Otherwise, use AskUserQuestion to ask for the URL.
**Preview metadata before proceeding:**
```bash
yt-dlp --dump-json --no-download "$URL" 2>/dev/null | python3 -c "
import json, sys
d = json.load(sys.stdin)
hrs, rem = divmod(int(d.get('duration', 0)), 3600)
mins, secs = divmod(rem, 60)
print(f\"Title: {d.get('title', 'Unknown')}\")
print(f\"Channel: {d.get('channel', 'Unknown')}\")
print(f\"Duration: {hrs}h {mins}m {secs}s\")
print(f\"Upload: {d.get('upload_date', 'Unknown')}\")
"
```
Use AskUserQuestion to confirm:
- Title, channel, duration look correct
- Whether to customize the metadata (title/artist/album) or use defaults from yt-dlp
---
### Phase 2: Download Audio [Execute]
```bash
WORK_DIR=$(mktemp -d)
echo "Working directory: $WORK_DIR"
yt-dlp -x --audio-format m4a --audio-quality 0 --no-playlist \
-o "$WORK_DIR/%(title).100B.%(ext)s" \
"$URL"
# Show result
ls -lh "$WORK_DIR"/*.m4a
```
**Notes:**
- `--audio-quality 0` = best available quality
- `%(title).100B` truncates filename to 100 bytes (prevents filesystem issues)
- `--no-playlist` ensures single video download even from playlist URLs
- ffmpeg is auto-invoked by yt-dlp for M4A conversion
---
### Phase 3: Tag Metadata [Execute]
Extract metadata from yt-dlp JSON and apply to the M4A file:
```bash
# Get the downloaded file path
M4A_FILE=$(ls "$WORK_DIR"/*.m4a | head -1)
# Apply metadata (use values confirmed in Phase 1, or yt-dlp defaults)
exiftool -overwrite_original \
-Title="$TITLE" \
-Artist="$ARTIST" \
-Album="YouTube Audio" \
"$M4A_FILE"
# Verify tags
exiftool -Title -Artist -Album "$M4A_FILE"
```
**Variables** (from Phase 1 confirmation):
- `$TITLE` — Video title (or user-customized)
- `$ARTIST` — Channel name (or user-customized)
- Album defaults to "YouTube Audio" unless user specifies otherwise
---
### Phase 4: Push to BookPlayer [Execute]
> **CRITICAL**: Use the Python API with `documents_only=True`. The CLI `pymobiledevice3 apps push` uses VendContainer mode and **will not work** with BookPlayer.
```bash
M4A_FILE=$(ls "$WORK_DIR"/*.m4a | head -1)
FILENAME=$(basename "$M4A_FILE")
uvx --python 3.14 --from pymobiledevice3 python3 << 'PYEOF'
import sys
from pathlib import Path
from pymobiledevice3.lockdown import create_using_usbmux
from pymobiledevice3.services.house_arrest import HouseArrestService
local_path = sys.argv[1] if len(sys.argv) > 1 else None
if not local_path:
# Find the m4a file from environment
import glob, os
work_dir = os.environ.get("WORK_DIR", "/tmp")
files = glob.glob(os.path.join(work_dir, "*.m4a"))
if not files:
print("ERROR: No .m4a file found in work directory")
sys.exit(1)
local_path = files[0]
file_path = Path(local_path)
filename = file_path.name
file_data = file_path.read_bytes()
size_mb = len(file_data) / (1024 * 1024)
print(f"Pushing: {filename} ({size_mb:.1f} MB)")
lockdown = create_using_usbmux()
service = HouseArrestService(
lockdown=lockdown,
bundle_id="com.tortugapower.audiobookplayer",
documents_only=True # CRITICAL: VendDocuments mode
)
service.set_file_contents(f"/Documents/{filename}", file_data)
print(f"SUCCESS: {filename} pushed to BookPlayer /Documents/")
PYEOF
```
**Anti-pattern — DO NOT USE:**
```bash
# WRONG: This uses VendContainer mode and fails silently on BookPlayer
pymobiledevice3 apps push com.tortugapower.audiobookplayer /path/to/file.m4a
```
---
### Phase 5: Verify [Verify]
List BookPlayer's `/Documents/` directory to confirm the file arrived:
```bash
uvx --python 3.14 --from pymobiledevice3 python3 << 'PYEOF'
from pymobiledevice3.lockdown import create_using_usbmux
from pymobiledevice3.services.house_arrest import HouseArrestService
lockdown = create_using_usbmux()
service = HouseArrestService(
lockdown=lockdown,
bundle_id="com.tortugapower.audiobookplayer",
documents_only=True
)
files = service.listdir("/Documents/")
print("BookPlayer /Documents/ contents:")
for f in sorted(files):
if f.startswith('.'):
continue
try:
info = service.stat(f"/Documents/{f}")
size_mb = info.get('st_size', 0) / (1024 * 1024)
print(f" {f} ({size_mb:.1f} MB)")
except Exception:
print(f" {f}")
PYEOF
```
**Report to user:**
- File name and size in BookPlayer
- Duration (from Phase 1 metadata)
- Remind: open BookPlayer on iPhone to see the new file (force-quit and reopen if it doesn't appear)
**Cleanup:**
```bash
# Remove temp working directory
rm -rf "$WORK_DIR"
echo "Cleaned up: $WORK_DIR"
```
---
## Troubleshooting Quick Reference
| Problem | Quick Fix |
| ---------------------- | ----------------------------------------------------------------- |
| No device found | Unlock iPhone, re-plug USB, tap "Trust" |
| File not in BookPlayer | You used the CLI — must use Python API with `documents_only=True` |
| Wrong metadata shown | Re-run Phase 3 with correct `-Title`/`-Artist` values |
Full troubleshRelated 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.