Promo Director logo

Promo Director

Organization
bitwize-music-studio
promo-director

Generates 15-second vertical promo videos for social media from mastered audio. Use after mastering is complete and before release, when the user wants social media content.

Overview

Publisherbitwize-music-studio
Repositoryclaude-ai-music-skills
Skill namepromo-director
Stars
546
Forks
130
Bundled files
2
LicenseCC0-1.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by bitwize-music-studio on GitHub. Read the source before you install it.

Installation

Install the Promo Director AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/promo-director
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bitwize-music-studio/claude-ai-music-skills.git /tmp/claude-ai-music-skills
mkdir -p .claude/skills
cp -r /tmp/claude-ai-music-skills/skills/promo-director .claude/skills/promo-director
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Promo Director in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Promo Director on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Promo Director is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Promo Director Skill

Generate professional promo videos for social media from mastered audio. Creates 15-second vertical videos (9:16, 1080x1920) optimized for Instagram Reels, Twitter, and TikTok.

Purpose

After mastering audio, generate promotional videos that combine:

  • Album artwork
  • Audio waveform visualization (9 styles available)
  • Track title + artist name
  • Automatic color scheme extracted from artwork
  • Intelligent segment selection (finds the most energetic 15 seconds)

When to Use

  • After mastering complete, before release
  • User says "generate promo videos" or "create promo videos for [album]"
  • When album has mastered audio + artwork ready

Position in Workflow

Generate → Master → **[Promo Videos]** → Release

Optional step between mastering-engineer and release-director.

Workflow

1. Setup Verification

Check ffmpeg:

bash
ffmpeg -filters | grep showwaves

Required filters: showwaves, showfreqs, drawtext, gblur

If missing:

Error: ffmpeg not found or missing required filters

Install ffmpeg:
  macOS: brew install ffmpeg
  Linux: apt install ffmpeg

After installing, run this command again.

Check Python dependencies:

Call get_python_command() to verify the venv exists. If venv_exists is false, show the warning and suggest /bitwize-music:setup.

2. Album Detection

Resolve audio path via MCP:

Call resolve_path("audio", album_slug) — returns the full audio directory path including artist folder.

Example result: ~/bitwize-music/audio/artists/bitwize/albums/electronic/sample-album/

Verify contents:

  • ✓ Mastered audio files (.wav, .mp3, .flac, .m4a)
  • ✓ Album artwork (album.png or album.jpg)

If artwork missing:

Error: No album artwork found in {audio_root}/artists/{artist}/albums/{genre}/{album}/

Expected: album.png or album.jpg

Options:
  1. Use /bitwize-music:import-art to place artwork
  2. Specify path manually: --artwork /path/to/art.png

Which option?

3. User Preferences

Check config defaults first:

Read promotion section from ~/.bitwize-music/config.yaml for defaults:

  • promotion.default_style - Default visualization style
  • promotion.duration - Default clip duration
  • promotion.include_sampler - Whether to generate album sampler by default
  • promotion.sampler_clip_duration - Seconds per track in sampler

If config section doesn't exist, use built-in defaults (pulse, 15s, sampler enabled, 12s clips).

Ask: What to generate?

Options (default from config or "both"):

  1. Individual track promos (15s each) + Album sampler (all tracks)
  2. Individual track promos only
  3. Album sampler only

Ask: Visualization style?

Default from promotion.default_style or pulse if not set.

StyleBest ForDescription
pulseElectronic, hip-hopOscilloscope/EKG style with heavy glow (default)
barsPop, rockFast reactive spectrum bars
lineAcoustic, folkClassic clean waveform
mirrorAmbient, chillMirrored waveform with symmetry
mountainsEDM, bass-heavyDual-channel spectrum (looks like mountains)
colorwaveIndie, alternativeClean waveform with subtle glow
neonSynthwave, 80sSharp waveform with punchy neon glow
dualExperimentalTwo separate waveforms (dominant + complementary colors)
circularAbstract, experimentalVectorscope (wild circular patterns)

Default recommendation:

  • Electronic/Hip-Hop → pulse
  • Rock/Pop → bars
  • Folk/Acoustic → line
  • Ambient/Chill → mirror

Ask: Custom duration?

Default: 15 seconds (optimal for Instagram/Twitter)

Options:

  • 15s (recommended, Instagram Reels sweet spot)
  • 30s (longer preview)
  • 60s (full clip, less common)

For sampler:

Default: 12 seconds per track

Calculate total:

Total duration = (tracks * clip_duration) - ((tracks - 1) * crossfade)
Twitter limit: 140 seconds

If over 140s:

WARNING: Expected duration {duration}s exceeds Twitter limit (140s)

Recommendation: Reduce --clip-duration to {140 / tracks}s

4. Generation

Individual track promos:

generate_promo_videos(album_slug, style="pulse", duration=15)

Single track only:

generate_promo_videos(album_slug, style="pulse", track_filename="01-track-name.wav")

Album sampler:

generate_album_sampler(album_slug, clip_duration=12, crossfade=0.5)

Handle errors:

Common issues:

  • ffmpeg filter error → Check ffmpeg install includes filters
  • Font not found → Install dejavu fonts or specify custom font
  • Artwork extraction fails → Use default cyan color scheme
  • librosa unavailable → Fall back to 20% into track for segment selection
  • Audio file corrupt → Skip track, report, continue with others

5. Results Summary

Report generated files:

## Promo Videos Generated

**Location:** {audio_root}/artists/{artist}/albums/{genre}/{album}/

**Individual Track Promos:**
- {audio_root}/artists/{artist}/albums/{genre}/{album}/promo_videos/
- 10 videos generated
- Format: 1080x1920 (9:16), H.264, 15s each
- Style: pulse
- File size: ~10-12 MB per video

**Album Sampler:**
- {audio_root}/artists/{artist}/albums/{genre}/{album}/album_sampler.mp4
- Duration: 114.5s (under Twitter 140s limit ✓)
- Format: 1080x1920 (9:16), H.264
- File size: 45.2 MB

**Next Steps:**
1. Review videos: Open promo_videos/ folder
2. Test on phone: Transfer one video and verify quality
3. Populate social copy: Fill in promo/ templates (twitter.md, instagram.md, etc.)
4. [Optional] Upload to cloud: /bitwize-music:cloud-uploader {album}
5. Ready for release workflow: /bitwize-music:release-director {album}

Technical Reference

See technical-reference.md for:

  • Output specifications (resolution, format, bitrate)
  • Visualization styles (pulse, bars, line, etc.)
  • Platform compatibility (Instagram, Twitter, TikTok)
  • Dependencies (required and optional)
  • Troubleshooting common issues

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Promo Director AI skill do?

Generates 15-second vertical promo videos for social media from mastered audio. Use after mastering is complete and before release, when the user wants social media content.

Why use Promo Director on TypingMind?

Because you install it once and use it with any model. Promo Director is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Promo Director in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/promo-director. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Promo Director?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Promo Director?

As many as you like. As long as a model supports skills, you can use Promo Director with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Promo Director AI skill free?

Yes. It is published on GitHub by bitwize-music-studio under the CC0-1.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇