Meoh

Organization

Optima-CityU

meoh

Multi-objective Evolution of Heuristics (MEoH) method skill. USE WHEN the user explicitly requests MEoH / Multi-objective EoH, or wants Pareto-based population evolution with archive for multi-objective problems.

Overview

Publisher	Optima-CityU
Repository	`LLM4AD_Next`
Skill name	`meoh`
Stars	596
Forks	41
Bundled files	1
License	BSD-3-Clause
Links	Skill source Repository Homepage

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/meoh
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.

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/meoh .claude/skills/meoh

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Meoh 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 Meoh 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 Meoh 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.

Multi-objective Evolution of Heuristics (MEoH) Skill

Paper: Yao et al., "Multi-objective evolution of heuristic using large language model", AAAI 2025.

1. Method Essence

MEoH extends EOH's evolutionary operators (E1/E2/M1/M2) to multi-objective scenarios: individuals are evaluated with multiple objective vectors, Pareto non-dominated sorting determines selection pressure, and a non-dominated archive maintains the historical best front. The LLM sees multiple representative individuals from the front during generation, accommodating different objective preferences.

Key differences from single-objective EOH:

Selection is based on domination + crowding, not a single score
Front diversity must be maintained: both ends and the middle of the front must have representatives
Archive individuals can be "resurrected" for crossover (even if not in the current population)

2. Recommended Parameters

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

Note: The number of objectives is determined by the length of objective_metrics, not a separate num_objs parameter.

What Happens During Evolution

Population initialized; evaluate all individuals
Each generation:
- Identify non-dominated front (Pareto front)
- Archive front members
- Generate offspring via LLM operators, using front members as parents
- Evaluate offspring
- Merge offspring into population
- Non-dominated sorting + crowding distance truncation
Archive grows as better front members are found
Final archive contains the best Pareto front discovered

Common Pitfalls

Front not diverse → increase population_size or force exploration at front ends
Archive too large → increase crowding pressure; archive pruning is automatic
Convergence slow → check if objectives are truly conflicting; some problems may be easier with single-objective
Front biased toward one objective → manually set extreme weight vectors as seeds

4. Acceptance Criteria

Non-dominated front identified and archived
Front covers both objective extremes and balanced trade-offs
Archive members used as parents for crossover (not just current population)
Crowding distance prevents front collapse
Final archive represents the full Pareto front

Bundled files

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

params.yaml1 KB

Frequently asked questions

What does the Meoh AI skill do?

Why use Meoh on TypingMind?

Because you install it once and use it with any model. Meoh 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 Meoh in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/meoh. 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 Meoh?

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 Meoh?

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

Is the Meoh 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

Pytorch Lightning

NousResearch

OrganizationPopular

Clean training loops with built-in distributed support.

Troubleshoot

Investigate unexpected behavior in the current Copilot agent session by analyzing its event log. Use when the user asks why something happened, why a request was slow, why a tool was or was not used,…

Pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart,…

Ui Styling

Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Multi-objective Evolution of Heuristics (MEoH) Skill

1. Method Essence

2. Recommended Parameters

What Happens During Evolution

Common Pitfalls

4. Acceptance Criteria

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now