Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add khalilbenaz/claude-skills-collection --skill feature-engineering-guidegit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/feature-engineering-guide)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/feature-engineering-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/feature-engineering-guide/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/feature-engineering-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/feature-engineering-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.02272 |
| Opus 5 | $0.00028 | $0.01136 |
| Sonnet 5 | $0.00011 | $0.00454 |
| Haiku 4.5 | $0.00006 | $0.00227 |
Grade A, and why
feature-engineering-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Engineering Guide
Workflow en 8 étapes
1. Exploration et audit des données
import pandas as pd
import numpy as np
df.info() # types, nulls par colonne
df.describe(include="all") # stats descriptives
df.isnull().mean().sort_values() # % manquants
df.select_dtypes("number").skew() # skewness
df.duplicated().sum() # doublons
# Corrélations
corr = df.select_dtypes("number").corr("spearman")
# Outliers par IQR
Q1, Q3 = df["col"].quantile([0.25, 0.75])
iqr = Q3 - Q1
outliers = df[(df["col"] < Q1 - 1.5*iqr) | (df["col"] > Q3 + 1.5*iqr)]
Critère de décision : Si une colonne dépasse 60 % de valeurs manquantes → supprimer (sauf raison métier forte). Entre 5 % et 60 % → imputer.
2. Nettoyage et imputation
from sklearn.impute import SimpleImputer, KNNImputer
from sklearn.pipeline import Pipeline
# Imputation simple (train-only fit, jamais sur le test !)
imp_median = SimpleImputer(strategy="median")
X_train["col"] = imp_median.fit_transform(X_train[["col"]])
X_test["col"] = imp_median.transform(X_test[["col"]])
# Imputation avancée (MICE via IterativeImputer)
from sklearn.experimental import enable_iterative_imputer
from sklearn.impute import IterativeImputer
imp_mice = IterativeImputer(max_iter=10, random_state=0)
# Winsorisation (capping à 1er/99e percentile)
from scipy.stats.mstats import winsorize
df["col"] = winsorize(df["col"], limits=[0.01, 0.01])
Choix d'imputation :
| Mécanisme de manque | Méthode recommandée |
|---|---|
| MCAR (aléatoire) | Médiane / mode |
| MAR (conditionnel) | KNN, MICE |
| MNAR (non-aléatoire) | Indicateur binaire + imputation |
3. Encoding catégoriel
import pandas as pd
from sklearn.preprocessing import OrdinalEncoder, TargetEncoder
from sklearn.preprocessing import OneHotEncoder
# One-Hot (cardinalité < 15, modèles linéaires)
pd.get_dummies(df, columns=["ville"], drop_first=True)
# Ordinal (catégories avec ordre naturel)
oe = OrdinalEncoder(categories=[["bas","moyen","haut"]])
# Target encoding (haute cardinalité, ex : code postal)
# ⚠ Toujours avec cross-validation pour éviter le leakage
te = TargetEncoder(smooth="auto", cv=5)
# Fréquence encoding (cardinalité très élevée, sans leakage)
freq = df["col"].value_counts(normalize=True)
df["col_freq"] = df["col"].map(freq)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 247 lines · 56 tokens per session scan A 7046fab5f70b
feature-engineering-guide is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 16d ago), licensed MIT. It adds 56 tokens to every session and 2,272 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
saelens
Train sparse autoencoders to interpret model features.
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
transformer-lens-interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
LQF_Machine_Learning_Expert_Guide
LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…
scientific-data-preprocessing
⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSING ⚠️ Prevents catastrophic errors (88.9% error rate in V1.0 case study) through multi-level feature analysis, data leakage detection, and semantic validation. MANDATORY for: data preprocessing, feature engineering, standardization…