diverse-island-ga
Diverse Island Genetic Algorithm skill.
Skill by Optima-CityU
Chalk Labs
Need help deploying diverse-island-ga?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/optima-cityu-diverse-island-ga
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, code-generation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/diverse-island-ga
What's inside
- Skill name
diverse-island-ga- Description
- 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.
- License
- BSD-3-Clause
- Instructions
- 49 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- params.yaml
SKILL.md (first lines)
# 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: | Concept | Role | |---|---| | **Island strategy spectrum** | `island_strategy_strength` controls how much islands differ (experience-reuse → novelty exploration) | | **Adaptive migration** | `adaptive_migration` receives migrants only after an island stagnates | | **Stagnation threshold** | `migration_stagnation_threshold` consecutive non-improving generations before migration is allowed | | **Novelty survivor** | `novelty_survivor_ratio` reserves non-elite survivor slots for code-dissimilar individuals | | **Exploration restart** | `exploration_restart_ratio` share of candidates built from scratch on the most exploratory island | | **Short-run guard** | `short_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
From Optima-CityU/LLM4AD_Next, BSD-3-Clause.
More from Optima-CityU/LLM4AD_Next
- 0.818score
proposal-innovation-plan
Optima-CityU
Use when distilling a proposal's innovations and defining milestones, annual plans, contingency points, and expected outcomes.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-literature-evidence
Optima-CityU
Use when researching, organizing, and citing the evidence base for a research proposal after its project foundation is established.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-final-review
Optima-CityU
Use when assembling a completed staged Typst proposal and checking its evidence, logic, citations, structure, and export readiness.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-foundation-layout
Optima-CityU
Use when establishing a research proposal's project foundation, submission constraints, and presentation system before section drafting begins.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
document-knowledge-organizer
Optima-CityU
Organize one or more Markdown source documents into high-fidelity, editable knowledge blocks.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-foundation-feasibility
Optima-CityU
Use when documenting a proposal's research foundation, available conditions, team support, feasibility, and risk controls from author-supplied facts.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-rationale
Optima-CityU
Use when developing a proposal's research purpose, necessity, significance, application value, and practical problem framing from verified evidence.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-objectives
Optima-CityU
Use when defining a proposal's objective hierarchy, research content, work packages, and key scientific or technical problems.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-methods
Optima-CityU
Use when translating established proposal objectives into research methods, a technical route, formal definitions, and an evaluation plan.
SkillAFreshness: A★ 677Claude Code +9 - 0.813score
typst-author
Optima-CityU
Generate idiomatic Typst (.typ) code, edit and troubleshoot Typst documents and projects, and answer Typst syntax/reference questions.
SkillAFreshness: A★ 677Claude Code +9 - 0.813score
llm4ad-task-builder
Optima-CityU
Use when a user wants to build an LLM4AD_Next task package — a runnable directory that lets the LLM4AD platform evolve an algorithm for their problem.
SkillAFreshness: A★ 677Claude Code +9 - 0.813score
reevo
Optima-CityU
Reflective Evolution (ReEvo) method skill.
SkillAFreshness: A★ 677Claude Code +9
Signals
- Stars
- 677
- Forks
- 44
- Open issues
- 1
- Last commit (this folder)
- Sep 8, 2026 (1 month ago)
- Last release
- Sep 29, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- BSD-3-Clause
- Repository
- github.com/Optima-CityU/LLM4AD_Next
- Website
- llm4ad-next.cn
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Optima-CityU
- 0.818score
proposal-literature-evidence
Optima-CityU
Use when researching, organizing, and citing the evidence base for a research proposal after its project foundation is established.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-innovation-plan
Optima-CityU
Use when distilling a proposal's innovations and defining milestones, annual plans, contingency points, and expected outcomes.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-objectives
Optima-CityU
Use when defining a proposal's objective hierarchy, research content, work packages, and key scientific or technical problems.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-rationale
Optima-CityU
Use when developing a proposal's research purpose, necessity, significance, application value, and practical problem framing from verified evidence.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-methods
Optima-CityU
Use when translating established proposal objectives into research methods, a technical route, formal definitions, and an evaluation plan.
SkillAFreshness: A★ 677Claude Code +9 - 0.818score
proposal-foundation-layout
Optima-CityU
Use when establishing a research proposal's project foundation, submission constraints, and presentation system before section drafting begins.
SkillAFreshness: A★ 677Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get diverse-island-ga running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
diverse-island-ga skill. Agent Mart. https://agentmart.dev/skills/optima-cityu-diverse-island-ga (last updated 2026-10-24)