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 vasilyu1983/AI-Agents-public --skill ai-ml-data-sciencegit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/ai-ml-data-science)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ai-ml-data-science"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-ml-data-science/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/vasilyu1983/ai-agents-public/ai-ml-data-science"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-ml-data-science.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 99 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 104 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00040 | $0.02935 |
| Opus 5 | $0.00020 | $0.01468 |
| Sonnet 5 | $0.00008 | $0.00587 |
| Haiku 4.5 | $0.00004 | $0.00294 |
Grade A, and why
ai-ml-data-science 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 8d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Science Engineering Suite
Use this skill for reproducible data-science work from problem framing through evaluation and handoff. The center of gravity is not "pick the fanciest model." It is framing the decision, building train-serve-safe features, and producing decision-ready evidence.
ASCII Flow
data question
|
v
problem framing
target + unit of analysis + leakage risks + decision/use case
|
v
data work
source checks + EDA + feature logic + split strategy + baseline
|
v
model/evidence
train or analyze + validate + interpret + quantify uncertainty
|
v
handoff
report, notebook, model candidate, or production path to MLOps
Quick Reference
| Need | Default Direction |
|---|---|
| reproducible Python workflow | uv plus scripts or git-friendly notebooks (marimo for reactive/diffable notebooks) |
| fast local analysis | DuckDB plus Polars (v1.x stable API as of 2026; pre-1.0 API-churn concerns no longer apply) |
| data contracts | Pandera or GX Core at dataset boundaries |
| tabular baseline | linear or logistic model plus tree-based candidate |
| feature engineering | explicit train-serve-safe transforms |
| unlabeled text corpus | embed -> UMAP -> HDBSCAN -> c-TF-IDF; LLM labels once per topic, never per document |
| tuning | Optuna only after the baseline is stable |
| evaluation | slices, threshold, calibration, uncertainty |
| handoff | model card, evaluation report, failure modes, monitoring expectations |
When To Use This Skill
- exploring datasets and checking modelling feasibility
- designing feature pipelines and leakage controls
- choosing and comparing model families
- clustering unlabeled text and discovering topics before a taxonomy or labeling effort exists
- building reproducible experiment workflows
- producing evaluation reports, model cards, and handoff artifacts
- reviewing whether an experiment is genuinely ready for production handoff
- explaining responsible-AI modelling mechanics: fairness and intersectionality, privacy, interpretability, poisoning, memorization, human oversight, and environmental trade-offs
- designing general multimodal models: contrastive image-text learning, fusion, VQA/document/video systems, diffusion control, adaptation, and quality-latency trade-offs
What ships with it
31 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 330 B
- assets/eda/template-eda.md 1.5 KB
- assets/evaluation/template-evaluation-report.md 2.3 KB
- assets/evaluation/template-model-card.md 1.2 KB
- assets/features/template-feature-engineering.md 2.0 KB
- assets/project/template-quick.md 1.1 KB
- assets/project/template-standard.md 3.9 KB
- assets/review/experiment-review-template.md 4.0 KB
- data/sample-model-spec.json 5.4 KB
- data/sources.json 21 KB
- learnings.consolidated.md 2.4 KB
- learnings.md 537 B
- references/class-imbalance-patterns.md 12 KB
- references/data-contracts-lineage.md 11 KB
- references/eda-best-practices.md 5.2 KB
- references/evaluation-patterns.md 10 KB
- references/feature-engineering-patterns.md 3.2 KB
- references/feature-freshness-streaming.md 10 KB
- references/hyperparameter-optimization.md 13 KB
- references/interpretability-explainability.md 15 KB
- references/llm-data-pipeline.md 8.5 KB
- references/ml-diagrams.md 15 KB
- references/modelling-patterns.md 20 KB
- references/multimodal-modeling.md 13 KB
- references/production-feedback-loops.md 13 KB
- references/reproducibility-checklist.md 12 KB
- references/responsible-ai-mechanics.md 11 KB
- references/text-clustering-topic-modeling.md 17 KB
- scripts/leakage_scan.py 8.9 KB runs code
- scripts/ml_toolkit.py 24 KB runs code
- scripts/README.md 4.5 KB
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.
- 8d ago Changed · +11 lines · +4 tokens per session 141f03413635
- 12d ago First seen · 226 lines · 36 tokens per session scan A 7e5c2f26d03e
ai-ml-data-science is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 9d ago), licensed MIT. It adds 40 tokens to every session and 2,935 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
scvi-tools
Deep learning for single-cell analysis using scvi-tools. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome RNA+ATAC analysis with MultiVI, (5) spatial transcriptomics…
experiment-bridge
A workflow tool that turns a research experiment plan into implemented code, deployed runs on GPUs, and initial results. It connects planning, code review, execution, and result collection.
saelens
Train sparse autoencoders to interpret model features.
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.