Agent skill

Model Selection Guide

ML 문제 유형별 모델 선택 매트릭스, 하이퍼파라미터 튜닝 전략, 앙상블 방법론 가이드. An agent skill from revfactory/harness-100.

Apache-2.0Auto-check passedData & Analytics

Install Model Selection Guide

skills CLI

$ npx skills add revfactory/harness-100 --skill model-selection-guide -a claude-code

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

GitHub CLI

$ gh skill install revfactory/harness-100 model-selection-guide --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/revfactory/harness-100.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ko/31-ml-experiment/.claude/skills/model-selection-guide .claude/skills/model-selection-guide && 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/

Paste into Claude Code

Install the "model-selection-guide" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/31-ml-experiment/.claude/skills/model-selection-guide into .claude/skills/model-selection-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-guide", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/revfactory/harness-100/tree/main/ko/31-ml-experiment/.claude/skills/model-selection-guide

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add revfactory/harness-100 --skill model-selection-guide -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 model-selection-guide --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .agents/skills && cp -r skills-src/ko/31-ml-experiment/.claude/skills/model-selection-guide .agents/skills/model-selection-guide && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "model-selection-guide" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/31-ml-experiment/.claude/skills/model-selection-guide into .agents/skills/model-selection-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-guide", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add revfactory/harness-100 --skill model-selection-guide -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 model-selection-guide --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/ko/31-ml-experiment/.claude/skills/model-selection-guide .cursor/skills/model-selection-guide && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "model-selection-guide" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/31-ml-experiment/.claude/skills/model-selection-guide into .cursor/skills/model-selection-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-guide", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/revfactory/harness-100.git --path ko/31-ml-experiment/.claude/skills/model-selection-guide

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add revfactory/harness-100 --skill model-selection-guide -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 model-selection-guide --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/ko/31-ml-experiment/.claude/skills/model-selection-guide .gemini/skills/model-selection-guide && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "model-selection-guide" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/31-ml-experiment/.claude/skills/model-selection-guide into .gemini/skills/model-selection-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-guide", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install revfactory/harness-100 model-selection-guide

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add revfactory/harness-100 --skill model-selection-guide -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .github/skills && cp -r skills-src/ko/31-ml-experiment/.claude/skills/model-selection-guide .github/skills/model-selection-guide && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "model-selection-guide" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/31-ml-experiment/.claude/skills/model-selection-guide into .github/skills/model-selection-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-guide", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add revfactory/harness-100 --skill model-selection-guide -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 model-selection-guide --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/ko/31-ml-experiment/.claude/skills/model-selection-guide .opencode/skills/model-selection-guide && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "model-selection-guide" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/31-ml-experiment/.claude/skills/model-selection-guide into .opencode/skills/model-selection-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-guide", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: model-selection-guide
GitHub stars: 1.3k
Token cost: ~952 tokens
SKILL.md length: 198 words
Files: 1
Skills in repo: 464
Repo updated: Mar 22, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

ML 문제 유형별 모델 선택 매트릭스, 하이퍼파라미터 튜닝 전략, 앙상블 방법론 가이드. An agent skill from revfactory/harness-100.

Tasks that involve Machine learning
SKILL.md covers 문제 유형별 모델 추천, XGBoost vs LightGBM vs CatBoost, 하이퍼파라미터 튜닝 and 교차 검증 전략, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Model Selection Guide is an agent skill from revfactory/harness-100. ML 문제 유형별 모델 선택 매트릭스, 하이퍼파라미터 튜닝 전략, 앙상블 방법론 가이드. '모델 선택', '알고리즘 비교', '하이퍼파라미터 튜닝', 'Optuna', '앙상블', 'XGBoost vs LightGBM', '모델 비교', '교차 검증' 등 ML 모델 선택 및 설계 시 이 스킬을 사용한다. model-designer와 evaluation-analyst의 모델 설계 역량을 강화한다. 단, 데이터 전처리나 학습 인프라 관리는 이 스킬의 범위가 아니다.

Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering Machine learning. The licence is Apache-2.0.

When your agent uses it

Tasks that involve Machine learning

Example prompts

“Optuna”
“XGBoost vs LightGBM”
“/model-selection-guide”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 8e8d35c. 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 (its code samples are python).
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

Model Selection Guide loads about 952 tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 198 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~71
When it runs · the whole SKILL.md, loaded when a task matches: ~952

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 revfactory/harness-100 at commit 8e8d35c, republished under its Apache-2.0 licence (© revfactory). 198 words, ~952 tokens.

Download SKILL.mdSave it as .claude/skills/model-selection-guide/SKILL.md (or your agent's skills folder).

name: model-selection-guide
description: ML 문제 유형별 모델 선택 매트릭스, 하이퍼파라미터 튜닝 전략, 앙상블 방법론 가이드. '모델 선택', '알고리즘 비교', '하이퍼파라미터 튜닝', 'Optuna', '앙상블', 'XGBoost vs LightGBM', '모델 비교', '교차 검증' 등 ML 모델 선택 및 설계 시 이 스킬을 사용한다. model-designer와 evaluation-analyst의 모델 설계 역량을 강화한다. 단, 데이터 전처리나 학습 인프라 관리는 이 스킬의 범위가 아니다.

Model Selection Guide — ML 모델 선택 매트릭스 가이드

문제 유형, 데이터 특성, 제약 조건에 따른 최적 모델 선택과 튜닝 전략.

문제 유형별 모델 추천

정형 데이터 (Tabular)

문제 유형	베이스라인	최적 후보	비고
이진 분류	LogisticRegression	XGBoost, LightGBM	트리 기반 대부분 최적
다중 분류	LogisticRegression(OVR)	LightGBM, CatBoost	CatBoost: 범주형 다수
회귀	LinearRegression	XGBoost, LightGBM	랜덤포레스트: 과적합 방지
순위	—	LambdaMART (LightGBM)	검색/추천
이상 탐지	IsolationForest	AutoEncoder, LOF	비지도/준지도
시계열	ARIMA	Prophet, LightGBM	피처 기반 시계열은 트리

비정형 데이터

데이터	모델	프레임워크
이미지	ResNet, EfficientNet, ViT	PyTorch, timm
텍스트	BERT, RoBERTa	HuggingFace Transformers
음성	Whisper, Wav2Vec	HuggingFace
그래프	GCN, GAT	PyG, DGL

XGBoost vs LightGBM vs CatBoost

기준	XGBoost	LightGBM	CatBoost
속도	중간	빠름	느림
메모리	많음	적음	중간
범주형 처리	인코딩 필요	내장 지원	최고 성능
결측치 처리	내장	내장	내장
과적합 방지	regularization	GOSS, EFB	Ordered Boosting
GPU 지원	✅	✅	✅
기본 추천	범용	대용량, 속도 중시	범주형 다수

하이퍼파라미터 튜닝

Optuna 기본 구조

python

import optuna

def objective(trial):
    params = {
        'n_estimators': trial.suggest_int('n_estimators', 100, 1000),
        'max_depth': trial.suggest_int('max_depth', 3, 10),
        'learning_rate': trial.suggest_float('learning_rate', 0.01, 0.3, log=True),
        'subsample': trial.suggest_float('subsample', 0.6, 1.0),
        'colsample_bytree': trial.suggest_float('colsample_bytree', 0.6, 1.0),
        'reg_alpha': trial.suggest_float('reg_alpha', 1e-8, 10.0, log=True),
        'reg_lambda': trial.suggest_float('reg_lambda', 1e-8, 10.0, log=True),
    }
    model = XGBClassifier(**params)
    score = cross_val_score(model, X, y, cv=5, scoring='f1').mean()
    return score

study = optuna.create_study(direction='maximize')
study.optimize(objective, n_trials=100)

튜닝 우선순위

LightGBM 튜닝 순서:
1단계 (영향 大): learning_rate, n_estimators, num_leaves
2단계 (영향 中): max_depth, min_child_samples, subsample
3단계 (영향 小): reg_alpha, reg_lambda, colsample_bytree
4단계 (미세 조정): min_split_gain, path_smooth

교차 검증 전략

전략	적합	코드
K-Fold	범용 (충분한 데이터)	`KFold(n_splits=5)`
Stratified K-Fold	불균형 분류	`StratifiedKFold(n_splits=5)`
Time Series Split	시계열	`TimeSeriesSplit(n_splits=5)`
Group K-Fold	그룹 데이터 누수 방지	`GroupKFold(n_splits=5)`
Repeated K-Fold	더 안정적 추정	`RepeatedKFold(n_splits=5, n_repeats=3)`

앙상블 방법

Stacking

python

from sklearn.ensemble import StackingClassifier

estimators = [
    ('xgb', XGBClassifier()),
    ('lgbm', LGBMClassifier()),
    ('cat', CatBoostClassifier(verbose=0)),
]
stack = StackingClassifier(
    estimators=estimators,
    final_estimator=LogisticRegression(),
    cv=5
)

Blending 가중치

python

# 최적 가중치 탐색
from scipy.optimize import minimize

def objective(weights):
    pred = sum(w * p for w, p in zip(weights, predictions))
    return -f1_score(y_true, pred > 0.5)

result = minimize(objective, x0=[1/3]*3, constraints={'type': 'eq', 'fun': lambda w: sum(w)-1})

모델 선택 의사결정 트리

데이터 유형?
├── 정형 (테이블)
│   ├── 행 수 < 1000 → 로지스틱 회귀 / SVM
│   ├── 1000 < 행 수 < 100만 → XGBoost / LightGBM
│   └── 행 수 > 100만 → LightGBM (속도 우선)
├── 이미지 → CNN (EfficientNet, ViT)
├── 텍스트 → Transformer (BERT)
└── 시계열
    ├── 단변량 → Prophet / ARIMA
    └── 다변량 → LightGBM (피처 기반) / LSTM

Files

Just SKILL.md in ko/31-ml-experiment/.claude/skills/model-selection-guide of revfactory/harness-100.

Open the folder on GitHubat commit 8e8d35c

Compare with similar skills

Model Selection Guide 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.

Model Selection Guide compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Model Selection Guide this skillrevfactory/harness-100	1.3k	—	~952	Automated safety check: Pass	Apache-2.0	6 mo ago
Scikit LearnzLanqing/codex-claude-academic-skills	4.6k	17 repos	~3.9k	Automated safety check: Pass	BSD-3-Clause	4 mo ago
Senior Data ScientistRaidriar7170/hermes-skilleval	125	6 repos	~1.4k	Automated safety check: Pass	MIT	11 days ago
Agentic Kaggle WorkflowFrankS-IntelLab/agentic-kaggle-skill	188	—	~4k	Automated safety check: Pass	MIT	3 mo ago
Retention Analysisliangdabiao/claude-data-analysis-ultra-main	290	1 repos	~1.3k	Automated safety check: Notes	None	5 mo ago
Geomlitalo-goncalves/geoML	108	—	~4.2k	Automated safety check: Pass	GPL-3.0	5 days ago

Similar skills

Scikit Learn
zLanqing/codex-claude-academic-skills
Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.
4.6k GitHub starsUsed in 17 repos~3.9k tokens
Data & AnalyticsAuto-check passed
Senior Data Scientist
Raidriar7170/hermes-skilleval
World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics.
125 GitHub starsUsed in 6 repos~1.4k tokens
Data & AnalyticsAuto-check passed
Agentic Kaggle Workflow
FrankS-IntelLab/agentic-kaggle-skill
Takes a Kaggle competition from rules and validation design through baselines, ensembling and notebook architecture to a scored submission.
188 GitHub stars~4k tokensUpdated 3 mo ago
Data & AnalyticsAuto-check passed
Retention Analysis
liangdabiao/claude-data-analysis-ultra-main
Analyze user retention and churn using survival analysis, cohort analysis, and machine learning.
290 GitHub starsUsed in 1 repo~1.3k tokens
Data & AnalyticsAuto-check: notes
Geoml
italo-goncalves/geoML
Working knowledge of the geoML Python package (github.com/italo-goncalves/geoML): variational Gaussian processes for spatial data, implicit geological modelling, block models, drillhole data…
108 GitHub stars~4.2k tokensUpdated 5 days ago
Data & AnalyticsAuto-check passed
Radiomics ML
Aperivue/medsci-skills
A skill your agent uses when building or auditing a radiomics or tabular clinical-ML prediction model with a classical learner (LASSO, SVM, random forest, XGBoost and similar).
329 GitHub starsUsed in 1 repo~2.7k tokens
Data & AnalyticsAuto-check passed

Questions about Model Selection Guide

What does Model Selection Guide do?

ML 문제 유형별 모델 선택 매트릭스, 하이퍼파라미터 튜닝 전략, 앙상블 방법론 가이드. An agent skill from revfactory/harness-100. Model Selection Guide is an agent skill from revfactory/harness-100. ML 문제 유형별 모델 선택 매트릭스, 하이퍼파라미터 튜닝 전략, 앙상블 방법론 가이드.

When should I use Model Selection Guide?

Model Selection Guide fits situations like: tasks that involve Machine learning.

How do I install Model Selection Guide in Claude Code?

Run `npx skills add revfactory/harness-100 --skill model-selection-guide -a claude-code`. Or copy the skill folder (ko/31-ml-experiment/.claude/skills/model-selection-guide in revfactory/harness-100) into .claude/skills/model-selection-guide in your project. Claude Code loads it when a task matches its description.

How do I install Model Selection Guide in Codex?

Run `npx skills add revfactory/harness-100 --skill model-selection-guide -a codex`. Or copy the skill folder (ko/31-ml-experiment/.claude/skills/model-selection-guide in revfactory/harness-100) into .agents/skills/model-selection-guide in your project. Codex loads it when a task matches its description.

Can I use Model Selection Guide 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 revfactory/harness-100 --skill model-selection-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/model-selection-guide, .gemini/skills/model-selection-guide, .github/skills/model-selection-guide and .opencode/skills/model-selection-guide in your project.

What does Model Selection Guide need to run?

SKILL.md names no scripts, command-line tools or credentials: Model Selection Guide is instructions for the agent only. Our summary lists: Python 3.

Does Model Selection Guide 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 Model Selection Guide 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 Model Selection Guide use?

Model Selection Guide is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Model Selection Guide use?

About 952 tokens (SKILL.md is roughly 3.8k 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 Model Selection Guide?

Skills that share tags, products or a category with Model Selection Guide: Scikit Learn (zLanqing/codex-claude-academic-skills, 4.6k stars), Senior Data Scientist (Raidriar7170/hermes-skilleval, 125 stars), Agentic Kaggle Workflow (FrankS-IntelLab/agentic-kaggle-skill, 188 stars) and Retention Analysis (liangdabiao/claude-data-analysis-ultra-main, 290 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Model Selection Guide?

revfactory (a GitHub user) maintains it in revfactory/harness-100, which has 1,290 GitHub stars. The repository holds 464 skills in this directory. The repository was last updated on March 22, 2026.

Source: revfactory/harness-100 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Model Selection Guide

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Model Selection Guide — ML 모델 선택 매트릭스 가이드

문제 유형별 모델 추천

정형 데이터 (Tabular)

비정형 데이터

XGBoost vs LightGBM vs CatBoost

하이퍼파라미터 튜닝

Optuna 기본 구조

튜닝 우선순위

교차 검증 전략

앙상블 방법

Stacking

Blending 가중치

모델 선택 의사결정 트리

Files

Compare with similar skills

Similar skills

More from revfactory/harness-100

Related

Questions about Model Selection Guide