Uploads promo videos and content to Cloudflare R2 or AWS S3. Use when the user wants to host promo content for social media or distribution.
npx skills add https://github.com/bitwize-music-studio/claude-ai-music-skills --skill cloud-uploader
Upload promo videos and other album content to cloud storage (Cloudflare R2 or AWS S3).
After generating promo videos with /bitwize-music:promo-director, upload them to cloud storage for:
Generate → Master → Promo Videos → **[Cloud Upload]** → Release
Optional step after promo-director, before release-director.
Cloud credentials must be configured in ~/.bitwize-music/config.yaml:
cloud:
enabled: true
provider: "r2" # or "s3"
# For Cloudflare R2
r2:
account_id: "your-account-id"
access_key_id: "your-access-key"
secret_access_key: "your-secret-key"
bucket: "promo-videos"
# For AWS S3
s3:
region: "us-west-2"
access_key_id: "your-access-key"
secret_access_key: "your-secret-key"
bucket: "promo-videos"
See ${CLAUDE_PLUGIN_ROOT}/reference/cloud/setup-guide.md for detailed setup instructions.
/bitwize-music:promo-director first){audio_root}/artists/{artist}/albums/{genre}/{album}/promo_videos/{audio_root}/artists/{artist}/albums/{genre}/{album}/album_sampler.mp4# If using the shared venv (recommended)
~/.bitwize-music/venv/bin/pip install -r ${CLAUDE_PLUGIN_ROOT}/requirements.txt
# Or install separately
pip install boto3
The upload script uses ~/.bitwize-music/venv if available, otherwise falls back to system Python.
Check config:
cat ~/.bitwize-music/config.yaml | grep -A 20 "cloud:"
Verify:
cloud.enabled: trueCheck promo videos exist:
ls {audio_root}/artists/{artist}/albums/{genre}/{album}/promo_videos/
ls {audio_root}/artists/{artist}/albums/{genre}/{album}/album_sampler.mp4
If missing:
Error: Promo videos not found.
Generate with: /bitwize-music:promo-director {album}
Call get_python_command() first to get the venv Python path and plugin root. Use these for all bash invocations below.
PYTHON="{python from get_python_command}"
PLUGIN_DIR="{plugin_root from get_python_command}"
Preview first:
$PYTHON "$PLUGIN_DIR/tools/cloud/upload_to_cloud.py" {album} --dry-run
Output shows:
Upload all (promos + sampler):
$PYTHON "$PLUGIN_DIR/tools/cloud/upload_to_cloud.py" {album}
Upload only track promos:
$PYTHON "$PLUGIN_DIR/tools/cloud/upload_to_cloud.py" {album} --type promos
Upload only album sampler:
$PYTHON "$PLUGIN_DIR/tools/cloud/upload_to_cloud.py" {album} --type sampler
Upload with public access:
$PYTHON "$PLUGIN_DIR/tools/cloud/upload_to_cloud.py" {album} --public
For R2:
{artist}/{album}/For S3:
aws s3 ls s3://{bucket}/{artist}/{album}/## Cloud Upload Complete
**Provider:** R2 (or S3)
**Bucket:** {bucket}
**Album:** {album}
**Uploaded Files:**
- {artist}/{album}/promos/01-track_promo.mp4
- {artist}/{album}/promos/02-track_promo.mp4
- ...
- {artist}/{album}/promos/album_sampler.mp4
**Total:** 11 files, 125.4 MB
**Next Steps:**
1. Verify files in cloud dashboard
2. If public: Test URLs work
3. Continue to release: /bitwize-music:release-director {album}
IMPORTANT: Cloud paths are FLAT - no genre folder.
The cloud path structure is different from the local content structure:
| Location | Path Structure |
|----------|----------------|
| Local content | {content_root}/artists/{artist}/albums/{genre}/{album}/ |
| Local audio | {audio_root}/artists/{artist}/albums/{genre}/{album}/ |
| Cloud | {artist}/{album}/ (no genre!) |
Files are organized in the bucket as:
{bucket}/
└── {artist}/
└── {album}/
└── promos/
├── 01-track_promo.mp4
├── 02-track_promo.mp4
├── ...
└── album_sampler.mp4
Example for album "my-album" by "bitwize" in rock genre:
~/music/artists/bitwize/albums/rock/my-album/bitwize/my-album/promos/ (NOT bitwize/albums/rock/my-album/)| Option | Description |
|--------|-------------|
| --type promos | Upload only track promo videos |
| --type sampler | Upload only album sampler |
| --type all | Upload both (default) |
| --dry-run | Preview without uploading |
| --public | Set files as public-read |
| --audio-root PATH | Override audio_root from config |
Basic upload:
/bitwize-music:cloud-uploader my-album
Preview only:
/bitwize-music:cloud-uploader my-album --dry-run
Upload promos only:
/bitwize-music:cloud-uploader my-album --type promos
Upload with public access:
/bitwize-music:cloud-uploader my-album --public
"Cloud uploads not enabled"
cloud.enabled: true to config${CLAUDE_PLUGIN_ROOT}/reference/cloud/setup-guide.md"Credentials not configured"
"Album not found"
{audio_root}/artists/{artist}/albums/{genre}/{album}/"No files found to upload"
/bitwize-music:promo-director {album}"Access Denied"
"Bucket not found"
--public flag only for files intended for public accesspromo-director:
After promo generation:
Promo videos generated successfully.
**Optional:** Upload to cloud storage: /bitwize-music:cloud-uploader {album}
release-director:
After cloud upload:
Cloud upload complete.
Ready for release workflow: /bitwize-music:release-director {album}
${CLAUDE_PLUGIN_ROOT}/reference/cloud/setup-guide.md - Detailed setup instructions${CLAUDE_PLUGIN_ROOT}/skills/promo-director/SKILL.md - Generate promo videos${CLAUDE_PLUGIN_ROOT}/skills/release-director/SKILL.md - Release workflowSonnet 4.5 - This skill runs scripts and coordinates workflow. No creative output from LLM.
Analyze text and images for harmful content with customizable blocklists.
Azure AI Content Understanding SDK for Python. Use for multimodal content extraction from documents, images, audio, and video.
Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants.
Azure AI Voice Live SDK for .NET. Build real-time voice AI applications with bidirectional WebSocket communication.
Build real-time voice AI applications with bidirectional WebSocket communication.
Azure Speech to Text REST API for short audio (Python). Use for simple speech recognition of audio files up to 60 seconds without the Speech SDK.
Expert at handling file uploads and cloud storage. Covers S3, Cloudflare R2, presigned URLs, multipart uploads, and image optimization. Knows how to handle large files without blocking.
Expert Mermaid diagram creation, validation, and rendering with dual-engine output (SVG/PNG/ASCII). Supports all 20+ diagram types including C4 architecture, AWS architecture-beta with service icons, flowcharts, sequence, ERD, state, class, mindmap, timeline, git graph, sankey, and more. Features code-to-diagram analysis, batch rendering, 15+ themes, and syntax validation. Use when users ask to create diagrams, visualize architecture, render mermaid files, generate ASCII diagrams, document system flows, model databases, draw AWS infrastructure, analyze code structure, or anything involving "mermaid", "diagram", "flowchart", "architecture diagram", "sequence diagram", "ERD", "C4", "ASCII diagram". Do NOT use for non-Mermaid image generation, data plotting with chart libraries, or general documentation writing.
Take bitwize-music-studio/cloud-uploader from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.