New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Dyca

by Optima-CityU in Optima-CityU/LLM4AD_Next

DyCA (Dynamic Clustering Algorithm) method skill. An agent skill from Optima-CityU/LLM4AD_Next.

BSD-3-ClauseAuto-check passed

Install Dyca

skills CLI
$ npx skills add Optima-CityU/LLM4AD_Next --skill dyca -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Optima-CityU/LLM4AD_Next dyca --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Optima-CityU/LLM4AD_Next.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/algo-design/dyca .claude/skills/dyca && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dyca
GitHub stars
574
Token cost
~738 tokens
SKILL.md length
289 words
Files
2
Skills in repo
24
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

DyCA (Dynamic Clustering Algorithm) method skill. An agent skill from Optima-CityU/LLM4AD_Next.

  • Works in 3 steps: Method Essence → Recommended Parameters → Acceptance Criteria
  • The user explicitly requests DyCA / dynamic clustering adaptive evolution
  • SKILL.md covers 1. Method Essence, 2. Recommended Parameters and 4. Acceptance Criteria
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Dyca is an agent skill from Optima-CityU/LLM4AD_Next. 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.

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `params.yaml`).

The repository describes itself as: A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use. The licence is BSD-3-Clause.

When your agent uses it

  • The user explicitly requests DyCA / dynamic clustering adaptive evolution

Example prompts

  • “/dyca”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Method Essence
  2. Recommended Parameters
  3. Acceptance Criteria

What it can do on your machine

Read from SKILL.md and the folder at commit e3d3f7b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dyca loads about 738 tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 289 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~738

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Optima-CityU/LLM4AD_Next at commit e3d3f7b, republished under its BSD-3-Clause licence (© Optima-CityU). 289 words, ~738 tokens.

Download SKILL.mdSave it as .claude/skills/dyca/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
dyca
description
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.
triggers
dyca, dynamic clustering, dynamic clustering adaptive, instance-aware evolution

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:

PoolRole
Generalist poolGlobal best algorithms that perform well across all clusters
Specialist poolsPer-cluster optimized algorithms (one pool per cluster)
Complementary poolCross-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

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

What Happens During Evolution
  1. Build instance feature vectors using n_anchors anchor algorithms
  2. Cluster instances via clustering_method into n_clusters clusters
  3. Every recluster_interval generations, check ARI stability; recluster if unstable
  4. Each generation produces offspring_per_generation new individuals
  5. Allocate effort across generalist / specialist / complementary pools
  6. Trigger SOS when a cluster stagnates for sos_stagnation_threshold generations
  7. 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

© Optima-CityU, BSD-3-Clause. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/algo-design/dyca of Optima-CityU/LLM4AD_Next.

  • SKILL.md
  • params.yaml

Open the folder on GitHubat commit e3d3f7b

Compare with similar skills

Dyca next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dyca compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dyca this skillOptima-CityU/LLM4AD_Next574—~738Automated safety check: PassBSD-3-Clause
Running Clustering Algorithmsjeremylongshore/tons-of-skills-marketplace2.8k—~1kAutomated safety check: PassMIT
No Explicit Anythedaviddias/Front-End-Checklist74k—~565Automated safety check: PassMIT
Vector Clusterruvnet/ruflo74k—~540Automated safety check: NotesMIT
Dynamic Workflow Modeaffaan-m/ECC276k1 repos~1.3kAutomated safety check: PassMIT
Algorithmic Art with p5.jsanthropics/skills180k38 repos~4.9kAutomated safety check: PassApache-2.0

Similar skills

  • Running Clustering Algorithms

    jeremylongshore/tons-of-skills-marketplace

    Analyze datasets by running clustering algorithms (K-means, DBSCAN, hierarchical) to identify data groups.

    2.8k GitHub stars~1k tokensUpdated today
    Data & AnalyticsAuto-check passed

  • No Explicit Any

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing TypeScript files for type safety regressions, during code review of functions that handle external data, or when the codebase has ESLint warnings for…

    74k GitHub stars~565 tokensUpdated 3 days ago
    DevelopmentAuto-check passed

  • Vector Cluster

    ruvnet/ruflo

    Cluster code by graph community detection via npx ruvector@0.2.25 hooks graph-cluster (spectral / Louvain)

    74k GitHub stars~540 tokensUpdated today
    Auto-check: notes

  • Dynamic Workflow Mode

    affaan-m/ECC

    Design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses.

    276k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

  • Algorithmic Art with p5.js

    anthropics/skills

    Official

    Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters.

    180k GitHub starsUsed in 38 repos~4.9k tokens
    Media & CreativeAuto-check passed

  • Molecular Dynamics

    K-Dense-AI/scientific-agent-skills

    Runs and analyzes molecular dynamics simulations with OpenMM and MDAnalysis.

    48k GitHub starsUsed in 1 repo~4.7k tokens
    Research & ScienceAuto-check passed

More from Optima-CityU/LLM4AD_Next

All 24 skills in this repo

  • Proposal Foundation Layout

    Optima-CityU/LLM4AD_Next

    A skill your agent uses when establishing a research proposal's project foundation, submission constraints, and presentation system before section drafting begins.

    574 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Llm4ad Task Builder

    Optima-CityU/LLM4AD_Next

    A skill your agent uses when a user wants to build an LLM4ADNext task package — a runnable directory that lets the LLM4AD platform evolve an algorithm for their problem.

    574 GitHub stars~3.7k tokensUpdated today
    Auto-check passed

  • Document Knowledge Organizer

    Optima-CityU/LLM4AD_Next

    Organize one or more Markdown source documents into high-fidelity, editable knowledge blocks.

    574 GitHub stars~695 tokensUpdated today
    Auto-check passed

  • Proposal Final Review

    Optima-CityU/LLM4AD_Next

    A skill your agent uses when assembling a completed staged Typst proposal and checking its evidence, logic, citations, structure, and export readiness.

    574 GitHub stars~774 tokensUpdated today
    Auto-check passed

  • Proposal Foundation Feasibility

    Optima-CityU/LLM4AD_Next

    A skill your agent uses when documenting a proposal's research foundation, available conditions, team support, feasibility, and risk controls from author-supplied facts.

    574 GitHub stars~613 tokensUpdated today
    Auto-check passed

  • Proposal Innovation Plan

    Optima-CityU/LLM4AD_Next

    A skill your agent uses when distilling a proposal's innovations and defining milestones, annual plans, contingency points, and expected outcomes.

    574 GitHub stars~578 tokensUpdated today
    Auto-check passed

Questions about Dyca

What does Dyca do?

DyCA (Dynamic Clustering Algorithm) method skill. An agent skill from Optima-CityU/LLM4AD_Next. Dyca is an agent skill from Optima-CityU/LLM4AD_Next. DyCA (Dynamic Clustering Algorithm) method skill.

When should I use Dyca?

Dyca fits situations like: the user explicitly requests DyCA / dynamic clustering adaptive evolution.

How do I install Dyca in Claude Code?

Run `npx skills add Optima-CityU/LLM4AD_Next --skill dyca -a claude-code`. Or copy the skill folder (skills/algo-design/dyca in Optima-CityU/LLM4AD_Next) into .claude/skills/dyca in your project. Claude Code loads it when a task matches its description.

How do I install Dyca in Codex?

Run `npx skills add Optima-CityU/LLM4AD_Next --skill dyca -a codex`. Or copy the skill folder (skills/algo-design/dyca in Optima-CityU/LLM4AD_Next) into .agents/skills/dyca in your project. Codex loads it when a task matches its description.

Can I use Dyca in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Optima-CityU/LLM4AD_Next --skill dyca -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dyca, .gemini/skills/dyca, .github/skills/dyca and .opencode/skills/dyca in your project.

What does Dyca need to run?

SKILL.md names no scripts, command-line tools or credentials: Dyca is instructions for the agent only.

Does Dyca access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Dyca safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dyca use?

Dyca is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dyca use?

About 738 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dyca?

Skills that share tags, products or a category with Dyca: Running Clustering Algorithms (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), No Explicit Any (thedaviddias/Front-End-Checklist, 74k stars), Vector Cluster (ruvnet/ruflo, 74k stars) and Dynamic Workflow Mode (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dyca?

Optima-CityU (a GitHub organization) maintains it in Optima-CityU/LLM4AD_Next, which has 574 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 9, 2026.

Source: Optima-CityU/LLM4AD_Next on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.