skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
skills.volces.com70 installs

ml-evolution-agent

Auto-evolving ML competition agent. Learns from each experiment, accumulates HCC multi-layer memory, and continuously improves LB scores. Inspired by MLE-Bench #1 ML-Master methodology.

How do I install this agent skill?

npx skills add https://skills.volces.com --skill ml-evolution-agent
view source ↗

Is this agent skill safe to install?

No partner audit is available yet. Read the source before installing.

What does this agent skill do?

ML Evolution Agent 🤖

Auto-evolving ML competition agent that learns from every experiment.

What This Skill Does

  1. Auto-evolves ML models for Kaggle-style competitions
  2. HCC Multi-layer Memory - Episodic, Pattern, Knowledge, Strategic layers
  3. Continuous improvement - Each phase learns from previous failures/successes
  4. Resource-aware - Respects system limits (time, memory, API quotas)

When to Use

  • User mentions Kaggle competition
  • Tabular data classification/regression tasks
  • Need to beat a target LB score
  • User wants automated ML experimentation

Quick Start

# Initialize
from ml_evolution import MLEvolutionAgent

agent = MLEvolutionAgent(
    competition="playground-series-s6e2",
    target_lb=0.95400,
    data_dir="./data"
)

# Run evolution
agent.evolve(max_phases=10)

HCC Memory Architecture

Layer 1: Episodic Memory
├── Experiment logs (phase, CV, LB, features, params)
├── Success/failure records
└── Resource usage tracking

Layer 2: Pattern Memory
├── What works (success patterns)
├── What fails (failure patterns)
└── When to use each approach

Layer 3: Knowledge Memory
├── Feature engineering techniques
├── Model configurations
├── Hyperparameter knowledge
└── Domain-specific features

Layer 4: Strategic Memory
├── Auto-evolution rules
├── Resource management rules
├── Exploration-exploitation balance
└── Competition-specific strategies

Proven Techniques (from real competitions)

Feature Engineering

TechniqueEffectBest For
Target Statistics+0.00018 LBAll tabular data
Frequency Encoding+0.00005 LBHigh-cardinality features
Smooth Target Encoding+0.00003 LBPrevent overfitting
Medical Indicators+0.00006 CVHealth data

Model Configurations

ModelBest ParamsWeight
CatBoostiter=1000-1200, lr=0.04-0.05, depth=6-750%
XGBoostn_est=1000-1200, lr=0.04, max_depth=625-30%
LightGBMn_est=1000-1200, lr=0.04, leaves=4020-25%

Resource Limits

  • Features: < 60 (avoids timeout)
  • Iterations: < 1200 (avoids SIGKILL)
  • Training time: < 20 min (system limit)
  • Submissions: 10/day (Kaggle quota)

Evolution Rules

# Auto-evolution decision tree
if phase_improved:
    keep_features()
    try_similar_approach()
elif phase_degraded > 0.0001:
    rollback()
    try_new_direction()
else:
    fine_tune_params()

# Overfitting detection
if cv_lb_gap > 0.002:
    increase_regularization()
    reduce_features()
    simplify_model()

Files Structure

ml-evolution-agent/
├── SKILL.md              # This file
├── HCC_MEMORY.md         # Memory architecture details
├── FEATURE_ENGINEERING.md # Feature techniques library
├── MODEL_CONFIGS.md      # Optimal model configurations
├── EVOLUTION_RULES.md    # Auto-evolution decision rules
└── templates/
    ├── train_baseline.py # Baseline training script
    ├── train_evolved.py  # Evolution training script
    └── memory.json       # Example memory state

Example Results

Playground S6E2 (Feb 2026)

  • Started: LB 0.95347
  • Best: LB 0.95365 (+0.00018)
  • Phases: 14
  • Success rate: 36%
  • Target beaten: Yes (0.95361 → 0.95365)

Key Learnings

  1. Simple > Complex - Target stats beat complex feature engineering
  2. Resource limits matter - Too many features = timeout
  3. CatBoost is king - Consistently best for tabular data
  4. Daily quota awareness - Kaggle limits submissions

Installation

clawhub install ml-evolution-agent

Built from real competition experience. Evolved through 14 phases of experimentation.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/skills.volces.com/ml-evolution-agent">View ml-evolution-agent on skillZs</a>