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 agentmods add skills/duqueom/ml-mlops-portfolio/eda-analysisnpx skills add DuqueOM/ML-MLOps-Portfolio --skill eda-analysisgit clone --depth 1 https://github.com/DuqueOM/ML-MLOps-PortfolioWrote 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/duqueom/ml-mlops-portfolio/eda-analysis)<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>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 | $0.00029 | $0.01909 |
| Opus 5 | $0.00015 | $0.00955 |
| Sonnet 5 | $0.00006 | $0.00382 |
| Haiku 4.5 | $0.00003 | $0.00191 |
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.
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.pyis available (copied bynew-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/.
- Detect encoding with
chardet(non-ASCII datasets are common) - Load with
pandas.read_csv/read_parquet - Normalize columns:
df.columns = df.columns.str.lower().str.replace(r'\W+', '_', regex=True) - Drop fully-null columns
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.
- Shape, dtypes, memory footprint
- Null counts + percentages per column
- Cardinality per column (distinguishes categorical from high-cardinality)
- Exact duplicates + near-duplicates (MinHash for >100k rows)
- 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.
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.
- 5d ago First seen · 167 lines · 29 tokens per session scan A 6ee4ae0326d7
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.
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.
setup
Configure MLflow tracing for Claude Code.
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.
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.
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.…
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…