Diverse Island Ga logo

Diverse Island Ga

Organization
Optima-CityU
diverse-island-ga

Diverse Island Genetic Algorithm skill. USE WHEN the user explicitly requests Diverse Island GA / diversity-oriented island GA, or wants specialized island roles with adaptive migration and novelty preservation instead of a uniform island GA.

Overview

PublisherOptima-CityU
RepositoryLLM4AD_Next
Skill namediverse-island-ga
Stars
596
Forks
41
Bundled files
1
LicenseBSD-3-Clause
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.

  • 1 bundled files

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

  • Open source

    Published by Optima-CityU on GitHub. Read the source before you install it.

Installation

Install the Diverse Island Ga 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/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/diverse-island-ga
  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/Optima-CityU/LLM4AD_Next.git /tmp/LLM4AD_Next
mkdir -p .claude/skills
cp -r /tmp/LLM4AD_Next/skills/algo-design/diverse-island-ga .claude/skills/diverse-island-ga
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Diverse Island Ga 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 Diverse Island Ga 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 Diverse Island Ga 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.

Diverse Island GA Skill

Reference: LLM4AD_Next specialized island model. Extends IslandGA with specialized island roles (a continuous exploitation↔exploration spectrum), adaptive stagnation-aware migration, and novelty preservation.

1. Method Essence

Diverse IslandGA builds on the classic island model but removes the assumption that all islands are identical. Instead, it assigns each island a continuous strategy position along the exploration↔exploitation spectrum, and coordinates them through adaptive migration that fires only when an island stagnates. This keeps the population diverse and avoids the premature spread of a local optimum.

Core mechanisms:

ConceptRole
Island strategy spectrumisland_strategy_strength controls how much islands differ (experience-reuse → novelty exploration)
Adaptive migrationadaptive_migration receives migrants only after an island stagnates
Stagnation thresholdmigration_stagnation_threshold consecutive non-improving generations before migration is allowed
Novelty survivornovelty_survivor_ratio reserves non-elite survivor slots for code-dissimilar individuals
Exploration restartexploration_restart_ratio share of candidates built from scratch on the most exploratory island
Short-run guardshort_task_max_migrations caps migration events on short runs

2. Recommended Parameters

See params.yaml in this directory for the recommended parameter configuration.

Note: This variant ships with a smaller out-of-box workload (max_generations=10, island_population_size=5) than the plain IslandGA, so it is safe to run without heavy tuning.

What Happens During Evolution

  1. Initialize num_islands islands, each at a distinct point on the strategy spectrum
  2. Each island evolves with its own exploration/exploitation bias and memory policy
  3. Every generation, elites are reevaluated at higher fidelity (elite_reevaluation_count)
  4. Migration is adaptive: an island may receive migrants only after migration_stagnation_threshold non-improving generations
  5. Novel survivors (low code similarity) are retained to preserve diversity
  6. On short runs, migration is capped by short_task_max_migrations

Common Pitfalls

  • Uniform islands (strength too low) → little diversity benefit; raise island_strategy_strength
  • Migration too aggressive → premature convergence; rely on adaptive stagnation gating
  • Exploration island flooding → tune exploration_restart_ratio and novelty ratio
  • Short runs over-migrating → keep short_task_max_migrations low (default 1)

4. Acceptance Criteria

  • Islands occupy distinct points on the exploration↔exploitation spectrum
  • Migration triggers only after stagnation (adaptive, not periodic-only)
  • Novelty survivors maintain inter-island diversity
  • Short runs respect the migration cap
  • Final best beats a uniform IslandGA baseline on the same problem

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 Diverse Island Ga AI skill do?

Diverse Island Genetic Algorithm skill. USE WHEN the user explicitly requests Diverse Island GA / diversity-oriented island GA, or wants specialized island roles with adaptive migration and novelty preservation instead of a uniform island GA.

Why use Diverse Island Ga on TypingMind?

Because you install it once and use it with any model. Diverse Island Ga 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 Diverse Island Ga in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/diverse-island-ga. 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 Diverse Island Ga?

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 Diverse Island Ga?

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

Is the Diverse Island Ga AI skill free?

Yes. It is published on GitHub by Optima-CityU under the BSD-3-Clause 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 👇