Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →datadrivenconstruction/ml-model-retrainer
Automated pipeline for retraining ML models with new construction data. Monitor model drift, trigger retraining, and validate model performance.
Passed 8 of 20 test cases with the skill, and 4 of 20 without it.
and 5 more in the full report
6 fixed3 passed either way12 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
When registering a new version of our concrete strength predictor named 'concrete_compressive_strength', what naming format and timestamp layout should be assigned to version_id?
| Checked | Without skill | With skill |
|---|---|---|
| The model version ID concatenates the model name with -v followed by a datetime formatted string. | Missed | Passed |
| The timestamp portion of the version ID follows the exact strftime pattern %Y%m%d%H%M%S. | Missed | Passed |
The instructions your model reads when the skill loads.
Automated pipeline for keeping construction ML models up-to-date. Monitor for data drift, trigger retraining when needed, validate performance, and manage model versions.
ML models degrade over time as:
Continuous retraining ensures predictions remain accurate.
from dataclasses import dataclass, field
from typing import List, Dict, Any, Optional, Callable
from datetime import datetime, timedelta
import pandas as pd
import numpy as np
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
from sklearn.model_selection import cross_val_score
import pickle
import hashlib
import json
import os
@dataclass
class ModelVersion:
version_id: str
model_name: str
created_at: datetime
training_samples: int
metrics: Dict[str, float]
feature_columns: List[str]
hyperparameters: Dict[str, Any]
test cases passed, vs 4 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.