Dyca

Organization

Optima-CityU

dyca

DyCA (Dynamic Clustering Algorithm) method skill. USE WHEN the user explicitly requests DyCA / dynamic clustering adaptive evolution, or wants instance-aware search that clusters problem instances and allocates specialized algorithm pools via dynamic reclustering and resource allocation.

Overview

Publisher	Optima-CityU
Repository	`LLM4AD_Next`
Skill name	`dyca`
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 Dyca 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/dyca
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/dyca .claude/skills/dyca

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

Use it in TypingMind

Enable Dyca 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 Dyca 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 Dyca 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.

DyCA (Dynamic Clustering Adaptive) Skill

Reference: LLM4AD_Next instance-aware multi-pool evolution model (DyCA, Dynamic Clustering Algorithm).

1. Method Essence

DyCA is an instance-aware search method. Instead of treating all problem instances uniformly, it dynamically partitions the training instances into clusters and maintains heterogeneous algorithm pools specialized to those clusters. The search then allocates LLM effort across pools based on observed difficulty and cluster stability.

Three heterogeneous pools:

Pool	Role
Generalist pool	Global best algorithms that perform well across all clusters
Specialist pools	Per-cluster optimized algorithms (one pool per cluster)
Complementary pool	Cross-cluster diversity algorithms that complement others

Core mechanisms:

Per-instance evaluation and cluster-specific fitness
Dynamic reclustering based on Adjusted Rand Index (ARI) stability
SOS (Save Our Specialist) inter-cluster collaboration to escape local optima
Macro (ARI-based) and micro (gap-based) resource allocation

2. Recommended Parameters

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

What Happens During Evolution

Build instance feature vectors using n_anchors anchor algorithms
Cluster instances via clustering_method into n_clusters clusters
Every recluster_interval generations, check ARI stability; recluster if unstable
Each generation produces offspring_per_generation new individuals
Allocate effort across generalist / specialist / complementary pools
Trigger SOS when a cluster stagnates for sos_stagnation_threshold generations
using_mode=true freezes clustering and runs only specialist evolution (mature clusters)

Common Pitfalls

Too few/too many clusters → poor specialization; tune n_clusters
Reclustering too often → instability; raise recluster_interval / lower ari_threshold
Anchors too few → weak feature vectors; increase n_anchors
Complementary pool starved → raise base_complementary_ratio
Clusters already stable → enable using_mode to stop reclustering

4. Acceptance Criteria

Instances cleanly clustered; each cluster has a specialist pool
Reclustering only on ARI instability (not every generation)
Resource allocation responds to per-cluster difficulty
SOS triggers on stagnation and recovers a better solution
Using mode works for already-stable datasets

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 Dyca AI skill do?

Why use Dyca on TypingMind?

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

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

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 Dyca?

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

Is the Dyca 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

Prototype Openclaw Tui

openclaw

OrganizationPopular

Build throwaway, fixture-driven OpenClaw Clack or Pi TUI prototypes and compare multiple interactive variants side by side in tmux without running the full application or touching live state.

Slacrawl

Slack archive: search, sync freshness, threads/DMs, SQL counts, and Slacrawl repo work.

Obsidian Vault Maintainer

openclaw

OrganizationPopular

Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.

Control Ui

Operate and troubleshoot the OpenClaw Control UI: navigate connected clients, organize sessions, build session dashboards, and handle direct or Tailscale-hosted Gateways.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

DyCA (Dynamic Clustering Adaptive) 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