eda-analysis

eda-analysis is a skill for Claude Code from DuqueOM/ML-MLOps-Portfolio. It costs 29 tokens per session (1,909 once invoked), scanned A, original, MIT.

A guided six-phase process for exploring a new dataset before building a machine-learning model. It examines the data, checks for information leakage, and creates files for training, schema generation, and production drift checks.

In plain words
What is it for?
Use it to ingest and profile raw CSV or Parquet files, study individual columns and relationships, audit leakage, and propose features. It also prepares a feature catalogue and baseline distributions for later parts of the service.
Why use it?
It gives data work a fixed order and records the checks needed before modelling. This helps catch malformed data and leakage, where training data contains information that would not be available when making real predictions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: $skill-name invocation.

Install

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.

agentmods
npx agentmods add skills/duqueom/ml-mlops-portfolio/eda-analysis
Any agent
npx skills add DuqueOM/ML-MLOps-Portfolio --skill eda-analysis
Clone the repo
git clone --depth 1 https://github.com/DuqueOM/ML-MLOps-Portfolio

Made for: Claude Code.

Wrote 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.

agentmods badge for eda-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/duqueom/ml-mlops-portfolio/eda-analysis.svg)](https://agentmods.dev/skills/duqueom/ml-mlops-portfolio/eda-analysis)
Your own site
<a href="https://agentmods.dev/skills/duqueom/ml-mlops-portfolio/eda-analysis"><img src="https://agentmods.dev/badge/skills/duqueom/ml-mlops-portfolio/eda-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,909 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.01909
Opus 5 $0.00015 $0.00955
Sonnet 5 $0.00006 $0.00382
Haiku 4.5 $0.00003 $0.00191

Measured 5d ago against content hash 6ee4ae0326d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

eda-analysis 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 5d 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.

.devin/skills/eda-analysis/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EDA Analysis Skill

Guides the agent through a 6-phase EDA pipeline that produces artifacts consumed by training (features.py), schema generation (schemas.py), and drift detection in production (baseline_distributions.parquet).

Inputs

  • $dataset-path: Path to raw data (e.g., data/raw/transactions.csv)
  • $service-slug: Optional — the snake_case service name the EDA belongs to

Goal

Complete EDA with all 6 artifacts produced, leakage audit passing (or explicitly resolved), and feature_catalog.yaml ready for features.py consumption.

Pre-conditions

  • templates/eda/eda_pipeline.py is available (copied by new-service.sh)
  • Dataset is in data/raw/ (NEVER read from production paths — invariant D-13)
  • Required deps installed: pip install -r eda/requirements.txt

Steps

Phase 0 — Ingest & Normalization

Trigger: Agent-DataValidator. Raw file arrives in data/raw/.

  1. Detect encoding with chardet (non-ASCII datasets are common)
  2. Load with pandas.read_csv / read_parquet
  3. Normalize columns: df.columns = df.columns.str.lower().str.replace(r'\W+', '_', regex=True)
  4. Drop fully-null columns
  5. dvc add data/raw/<file> if not already tracked

Output: data/processed/dataset_clean.parquet, eda/reports/00_ingest_report.md

Success criteria: File loads, all columns are snake_case, DVC hash recorded.

Phase 1 — Structural Profile

Trigger: Agent-EDAProfiler. Clean dataset available.

  1. Shape, dtypes, memory footprint
  2. Null counts + percentages per column
  3. Cardinality per column (distinguishes categorical from high-cardinality)
  4. Exact duplicates + near-duplicates (MinHash for >100k rows)
  5. Index integrity + temporal coverage (if datetime column detected)

Output: eda/reports/01_profile.html (ydata-profiling or lightweight), canonical eda/artifacts/schema_ranges.json

Success criteria: Profile report generated. schema_ranges.json enumerates every column with inferred dtype and observed range.

Read the full file on GitHub · 167 lines

Changes

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.

  1. 5d ago First seen · 167 lines · 29 tokens per session scan A 6ee4ae0326d7

Subscribe to this mod's changes

eda-analysis is a skill published in the GitHub repository DuqueOM/ML-MLOps-Portfolio (5 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 1,909 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

mlflow

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.

davila7/claude-code-templates · 33 tokens

setup

Configure MLflow tracing for Claude Code.

mlflow/mlflow · 10 tokens

ml-expert

Expert-level machine learning, deep learning, model training, and MLOps. Use when the user mentions machine learning, deep learning, neural networks, MLOps, or data science, or when the task involves Machine Learning Fundamentals, Data Preparation, or Model Training.

personamanagmentlayer/pcl · 58 tokens

mlflow

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.

OpenLAIR/dr-claw · 33 tokens

ecs-genai

Use whenever someone runs a GPU / ML / GenAI / LLM workload on Amazon ECS: GPU on ECS, ECS GPU-optimized AMI, g4dn/g5/g6/p4/p5 on ECS, which ECS launch type for GPU, Inferentia/Trainium/Neuron on ECS, distributed training, model inference or vLLM/Triton/TGI/Ray on ECS, Capacity Blocks, GPU sharing, ASG per GPU type.…

aws-samples/sample-apex-skills · 259 tokens

eks-genai

Use whenever someone is building, training, fine-tuning, or serving a generative AI / LLM workload on Amazon EKS — phrased as "GPU vs Trainium/Inferentia", "vLLM on EKS", "Ray Serve / KubeRay", "distributed training on EKS", "FSx for Lustre for ML", "Karpenter for GPU", "EFA / NCCL multi-node", "DCGM / Neuron…

aws-samples/sample-apex-skills · 275 tokens