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 muend/geoai-skills --skill ml-experiment-standardsgit clone --depth 1 https://github.com/muend/geoai-skillsWrote 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/muend/geoai-skills/ml-experiment-standards)<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.
<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>- 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 | $0.00083 | $0.01439 |
| Opus 5 | $0.00042 | $0.00720 |
| Sonnet 5 | $0.00017 | $0.00288 |
| Haiku 4.5 | $0.00008 | $0.00144 |
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.
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.
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.
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.
- 11d ago First seen · 143 lines · 83 tokens per session scan A ee9407d47e45
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.
Other skills, from other repositories
detect-objects
Run pre-trained AI models on geospatial imagery. Detect buildings, cars, ships, solar panels, agriculture fields, or use text-prompted segmentation with GroundedSAM. Requires GPU for best performance.
process-raster
Process raster data: clip by bounding box, stack multiple bands, mosaic GeoTIFFs, or convert between raster and vector formats.
download-data
Download NAIP aerial imagery for a bounding box. Specify coordinates as minx,miny,maxx,maxy in WGS84 and optionally a year.
inspect-geo
Inspect any raster or vector geospatial file. Returns CRS, bounds, bands, resolution, dtype, attribute summaries, and band statistics. Supports GeoTIFF, Shapefile, GeoJSON, GeoPackage, GeoParquet, and more.
search-stac
Search and download satellite imagery from Microsoft Planetary Computer. Browse available collections, search by bbox and time range, list assets, and download specific items.
agent-auto-sci-ai-ml
A research workflow for building and checking machine-learning and artificial-intelligence models, including models that work with maps, time-based data, text, or images.