Godot Genre Rhythm logo

Godot Genre Rhythm

Community
thedivergentai
godot-genre-rhythm

Expert blueprint for rhythm games including audio synchronization (BPM conductor, latency compensation with AudioServer.get_time_since_last_mix), note highways (scroll speed, timing windows), judgment systems (Perfect/Great/Good/Bad/Miss), scoring with combo multipliers, input processing (lane-based, hold note detection), and chart/beatmap loading. Based on DDR/osu!/Beat Saber research. Trigger keywords: rhythm_game, audio_sync, timing_judgment, note_highway, combo_system, BPM_conductor, latency_compensation.

Overview

Publisherthedivergentai
RepositoryGD-Agentic-Skills
Skill namegodot-genre-rhythm
Stars
727
Forks
43
Bundled files
14
LicenseLGPL-3.0
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.

  • 14 bundled files

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

  • Open source

    Published by thedivergentai on GitHub. Read the source before you install it.

Installation

Install the Godot Genre Rhythm 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.
  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/thedivergentai/GD-Agentic-Skills.git /tmp/GD-Agentic-Skills
mkdir -p .claude/skills
cp -r /tmp/GD-Agentic-Skills/skills/godot-genre-rhythm .claude/skills/godot-genre-rhythm
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Godot Genre Rhythm 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 Godot Genre Rhythm 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 Godot Genre Rhythm 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.

NEVER Do (Expert Anti-Patterns)

Audio Sync & Logic

  • NEVER use Time.get_ticks_msec() / Time.get_ticks_usec() as the song clock; strictly use AudioStreamPlayer.get_playback_position() + AudioServer.get_time_since_last_mix() - AudioServer.get_output_latency() (see rhythm_conductor.gd).
  • NEVER process song logic in _process(); strictly use _physics_process() or a conductor loop to ensure deterministic timing regardless of render frames.
  • NEVER use _process() to capture hit inputs; strictly use _input(event) to record the exact timestamp of the button press event.
  • NEVER scale engine time_scale for song speed; strictly use AudioStreamPlayer.pitch_scale to adjust speed and avoid globally breaking physics logic.
  • NEVER neglect Audio Latency calibration; strictly provide a tool for players to adjust for hardware/Bluetooth delays (~30-100ms) to prevent "unplayable" sync issues.
  • NEVER use _process delta as the song clock; strictly read the conductor's get_song_time() (playback + mix − output latency).
  • NEVER move thousands of note sprites on the CPU; strictly use a Shader-Based Highway (UV scrolling) to offload track movement to the GPU.
  • NEVER use yield or await for beat timing; strictly use a sample-accurate Delta Accumulator tied to the audio clock.
  • NEVER assume a constant BPM; strictly build your conductor to handle a Tempo Map for complex track changes.

Feedback & Performance

  • NEVER judge inputs based on world position (pixels); strictly judge against the Song's Elapsed Time (ms) to ensure consistency across resolutions.
  • NEVER play hit sounds with static pitch; strictly add ±5% Random Pitch Variation to hit sounds to avoid the "machine gun" effect.
  • NEVER use tight timing windows (e.g., <25ms) for all players; strictly use Wider Windows for Beginners to prevent immediate frustration.
  • NEVER instantiate note nodes every beat; strictly use Object Pooling to recycle note instances and prevent GC spikes during dense tracks.
  • NEVER use standard Area2D signals for rhythmic hits; strictly Poll Inputs in the conductor loop to compare against target timestamps.
  • NEVER calculate FFT for visualization on the main thread; strictly use AudioEffectSpectrumAnalyzerInstance for optimized engine-side analysis.
  • NEVER allow note spamming/mashing; strictly penalize misses or break combos to maintain the game's integrity.
  • NEVER use load() dynamically during gameplay; strictly use ResourceLoader.load_threaded_request() to avoid thread stalling.
  • NEVER forget to pause the conductor/ highway; strictly sync with the audio player's pause state to prevent notes from scrolling while the music is stopped.

🛠 Expert Components (scripts/)

MANDATORY reads before implementing the matching system:

  1. rhythm_conductor.gd — canonical audio clock
  2. input_judge_logic.gd — time-window judging
  3. note_object_pool.gd — pooled notes (no per-beat instantiate)
  4. latency_calibrator.gd — player hardware offset

Original Expert Patterns

Modular Components

Do NOT load unused lanes: skip audio_spectrum_analyzer.gd unless building reactive viz; skip dynamic_bpm_handler.gd for constant-BPM tracks.


Script map: Baseline MusicConductor samples → rhythm_conductor.gd; JudgmentSysteminput_judge_logic.gd; chart spawn → note_orchestrator.gd + note_object_pool.gd.

Core Loop

  1. Calibrate latency → 2. Conductor clock → 3. Spawn pooled notes → 4. _input judge → 5. Score/combo UI

Decision Trees

Clock (one recipe)

NeedAction
Song positionMANDATORY rhythm_conductor.gd get_song_time()
Visual highwayPosition from song time / beats — never _process delta integration as truth
Hit timestampCapture in _input / _unhandled_input, compare to note target time

Systems

Do not re-inline MusicConductor / NoteHighway / JudgmentSystem / RhythmScoring classes in this skill — load the scripts.

Skill Chain

PhaseSkillsPurpose
1. Audiogodot-audio-systemsStream clock + latency
2. Inputgodot-input-handlingTimestamped hits
3. UIgodot-ui-containersHighway / HUD
4. Perfpooling / shadersDense charts
5. Balancegodot-monte-carlo-balancerWindow difficulty bands

Common Pitfalls

PitfallSolution
Time.get_ticks_* conductorUse playback + mix − latency
Judge in _process_input + song time
Instantiate per notenote_object_pool.gd

MANDATORY for depth beyond decision trees and script catalog: rhythm-systems-deep.md. Do NOT Load on first-pass wiring — use bundled scripts/ first.

Godot-Specific Tips

  1. Audio latency: Calibrate with AudioServer and custom offset
  2. Input polling: Use _input not _process for precise timing
  3. Shaders: UV scrolling for note highways
  4. Particles: Use GPUParticles2D for hit effects

3. Hardware-Synced Latency Calibration

Calculate precise offsets by compensating for OS/Hardware latency.

gdscript

## Reference

> Progressive disclosure: open Official Documentation links only when researching a specific API; load Related Skills when routing to a peer domain — do not preload the whole lattice.

### Official Documentation
- [Sync the gameplay with audio and music](https://docs.godotengine.org/en/stable/tutorials/audio/sync_with_audio.html) — Playback-position helpers (`get_time_since_last_mix`, output latency) that every BPM conductor and judgment window must use.
- [Audio streams](https://docs.godotengine.org/en/stable/tutorials/audio/audio_streams.html) — AudioStreamPlayer roles, pitch_scale for song speed, and how music reaches buses without breaking sync.
- [Audio buses](https://docs.godotengine.org/en/stable/tutorials/audio/audio_buses.html) — Route Music / HitSFX / UI so judgment SFX never fight the track bus.
- [Importing audio samples](https://docs.godotengine.org/en/stable/tutorials/assets_pipeline/importing_audio_samples.html)WAV vs Ogg/MP3 tradeoffs for charts, hit clicks, and calibration tones.
- [AudioServer](https://docs.godotengine.org/en/stable/classes/class_audioserver.html) — Mix/output latency APIs and bus-effect instances used by conductors and spectrum visuals.
- [AudioStreamPlayer](https://docs.godotengine.org/en/stable/classes/class_audiostreamplayer.html) — Non-positional music/hit player API (`get_playback_position`, `pitch_scale`, pause) for the highway clock.
- [AudioEffectSpectrumAnalyzer](https://docs.godotengine.org/en/stable/classes/class_audioeffectspectrumanalyzer.html) — Engine-side FFT effect for reactive highways without main-thread FFT work.
- [Using InputEvent](https://docs.godotengine.org/en/stable/tutorials/inputs/inputevent.html) — `_input` / action press timing for lane hits instead of polling in `_process`.
- [CanvasItem shaders](https://docs.godotengine.org/en/stable/tutorials/shaders/shader_reference/canvas_item_shader.html)UV scroll patterns for GPU note highways that avoid moving thousands of sprites on CPU.
- [Tween](https://docs.godotengine.org/en/stable/classes/class_tween.html) — Judgment splash, receptor pulse, and beat-synced scale pops without frame-tied lerps.
- [Background loading](https://docs.godotengine.org/en/stable/tutorials/io/background_loading.html) — Threaded chart/audio preload so dense tracks never stall the first note.

### Related Skills

#### Prerequisites
- [godot-project-foundations](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-project-foundations/SKILL.md) — Audio latency project settings, bus layout names, and input map lane actions must exist before the conductor runs.
- [godot-audio-systems](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-audio-systems/SKILL.md) — Buses, stream players, spectrum instances, and sync-with-audio helpers this genre skill consumes for BPM clocks.
- [godot-input-handling](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-input-handling/SKILL.md) — Action maps, `_input` vs `_unhandled_input`, and event timestamps for lane press/release and anti-spam.
- [godot-gdscript-mastery](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-gdscript-mastery/SKILL.md) — Typed Resources for NoteData/charts, signals for beat/judgment events, and deterministic timing loops.

#### Complements
- [godot-tweening](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-tweening/SKILL.md) — Judgment labels, receptor flashes, and beat pulses should be Tween-driven, not per-frame scale hacks.
- [godot-shaders-basics](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-shaders-basics/SKILL.md) — Shader highways and spectrum-driven uniforms keep dense charts off the CPU.
- [godot-particles](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-particles/SKILL.md) — Hit sparks and combo flourishes via GPUParticles2D without instantiating VFX every Perfect.
- [godot-ui-containers](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-ui-containers/SKILL.md) — Score/combo HUD, calibration sliders, and lane receptor layout as Control trees.
- [godot-save-load-systems](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-save-load-systems/SKILL.md) — Persist A/V offset, scroll speed, and difficulty windows across sessions.
- [godot-autoload-architecture](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-autoload-architecture/SKILL.md) — Conductor / scoring / pool owners are typically Autoloads with a clear boot order.
- [godot-signal-architecture](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-signal-architecture/SKILL.md) — Beat, judgment, combo-break, and chart-finished signals need owner boundaries so UI never owns the clock.

#### Downstream / consumers
- [godot-performance-optimization](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-performance-optimization/SKILL.md) — Escalate when note pools, highway draw calls, or mix callbacks still hitch after pooling and shader scroll.
- [godot-monte-carlo-balancer](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-monte-carlo-balancer/SKILL.md) — Simulate timing-window width, scroll speed, and miss penalties against clear rates before shipping difficulty tiers.

#### Master
- [godot-master](https://github.com/thedivergentai/gd-agentic-skills/blob/main/skills/godot-master/SKILL.md) — Library router and mirrored module entry; open when discovering which Domain Skill owns a cross-cutting rhythm concern.

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 Godot Genre Rhythm AI skill do?

Expert blueprint for rhythm games including audio synchronization (BPM conductor, latency compensation with AudioServer.get_time_since_last_mix), note highways (scroll speed, timing windows), judgment systems (Perfect/Great/Good/Bad/Miss), scoring with combo multipliers, input processing (lane-based, hold note detection), and chart/beatmap loading. Based on DDR/osu!/Beat Saber research. Trigger keywords: rhythm_game, audio_sync, timing_judgment, note_highway, combo_system, BPM_conductor, latency_compensation.

Why use Godot Genre Rhythm on TypingMind?

Because you install it once and use it with any model. Godot Genre Rhythm 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 Godot Genre Rhythm in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/thedivergentai/GD-Agentic-Skills/tree/main/skills/godot-genre-rhythm. 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 Godot Genre Rhythm?

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 Godot Genre Rhythm?

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

Is the Godot Genre Rhythm AI skill free?

Yes. It is published on GitHub by thedivergentai under the LGPL-3.0 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 👇