ml-experiment-standards

ml-experiment-standards is a skill for Claude Code, Codex from muend/geoai-skills. It costs 83 tokens per session (1,439 once invoked), scanned A, original, MIT.

A set of standards for training and testing predictive machine-learning models. It covers how data is explored, split, measured, and documented so results can be repeated and trusted.

In plain words
What is it for?
Use it when training, validating, tuning, benchmarking, or judging whether a predictive model is ready for use.
Why use it?
It helps prevent data leakage, where test information accidentally influences training, and avoids using unsuitable tests or metrics for time, location, or grouped data.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the geoai plugin — 18 skills shipped together

Good fit Use it when training, validating, tuning, benchmarking, or judging whether a predictive model is ready for use.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/muend/geoai-skills/ml-experiment-standards
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.

Any agent
npx skills add muend/geoai-skills --skill ml-experiment-standards
Clone the repo
git clone --depth 1 https://github.com/muend/geoai-skills

Made for: Claude Code, Codex.

Or install geoai, the plugin that ships this one along with the rest of its 18 skills.

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 ml-experiment-standards

README.md
[![agentmods](https://agentmods.dev/badge/skills/muend/geoai-skills/ml-experiment-standards/github.svg)](https://agentmods.dev/skills/muend/geoai-skills/ml-experiment-standards)
Your own site
<a href="https://agentmods.dev/skills/muend/geoai-skills/ml-experiment-standards"><img src="https://agentmods.dev/badge/skills/muend/geoai-skills/ml-experiment-standards/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.

agentmods 80×15 button for ml-experiment-standards

Your own site · 80×15
<a href="https://agentmods.dev/skills/muend/geoai-skills/ml-experiment-standards"><img src="https://agentmods.dev/badge/skills/muend/geoai-skills/ml-experiment-standards.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00083 $0.01439
Opus 5 $0.00042 $0.00720
Sonnet 5 $0.00017 $0.00288
Haiku 4.5 $0.00008 $0.00144

Measured 11d ago against content hash ee9407d47e45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ml-experiment-standards 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 11d 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.

skills/ml-experiment-standards/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ML Experiment Standards

Purpose: every ML job (quick prototypes included) is reproducible, leakage-free, and metric-justified. These are not optional polish; every skipped item typically returns as "the model collapsed in production" or "the result didn't replicate".

1. EDA comes first

Before any model, produce and show: distributions, missingness rates, outliers, target balance, salient correlations. Metric and loss choice depend on this information; a model recommendation without EDA is a guess.

2. Leakage audit

At every split decision, answer explicitly (and write the answer as a code comment): "Does the training set contain indirect information about any test sample?"

Data type Correct split Why
Independent samples Stratified k-fold Preserves class ratios
Time series TimeSeriesSplit / walk-forward Future must not leak into past
Spatial data Spatial block CV — see references/spatial-cv-protocol.md Neighbors are near-duplicates
Grouped data (patient, parcel, scene) GroupKFold A group must not straddle the split
  • Scalers/encoders/imputers are fit on train only; the clean path is sklearn.pipeline.Pipeline — CV then fits correctly by construction.
  • Target-derived features (target encoding etc.) must be computed out-of-fold, and shown to be.

The spatial protocol in references/spatial-cv-protocol.md is the single canonical source for this repo — other skills link here; do not restate it.

3. Metric selection — justified

Never choose a metric by default; write a one-sentence rationale:

  • Imbalanced classes → F1 / AUC-PR, not accuracy (accuracy rewards majority-class memorization).
  • Segmentation → IoU/Dice (pixel accuracy is inflated by background).
  • Regression → RMSE (sensitive to large errors) vs MAE (robust) vs R² (variance explained) — justify from the use case.
  • Every point estimate gets uncertainty: bootstrap CI or mean ± std across CV folds. A single number hides whether a difference is signal or noise.

Read the full file on GitHub · 143 lines

Files

What ships with it

3 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.

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. 11d ago First seen · 143 lines · 83 tokens per session scan A ee9407d47e45

Subscribe to this mod's changes

ml-experiment-standards is a skill published in the GitHub repository muend/geoai-skills (17 stars, last pushed 7d ago), licensed MIT. It adds 83 tokens to every session and 1,439 once invoked, about $0.0004 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.