aledon8-openleukemia-ml-instructions.ocm.json json {
"ocm": "1",
"id": "aledon8-openleukemia-ml-instructions",
"kind": "skill",
"name": "ml",
"description": "ML Instructions",
"publisher": "Aledon8",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github-instructions"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"ML Instructions"
],
"primary": false,
"metadata": {
"source": {
"provider": "github-instructions",
"repository": "https://github.com/Aledon8/OpenLeukemia",
"path": ".github/instructions/ml.instructions.md",
"ref": "b9f1fd534e22ce7c5916f92a008d7f34ad0ec277",
"url": "https://github.com/Aledon8/OpenLeukemia/blob/b9f1fd534e22ce7c5916f92a008d7f34ad0ec277/.github/instructions/ml.instructions.md",
"key": "Aledon8/OpenLeukemia/.github/instructions/ml.instructions.md"
},
"applies_to": "ml/**/*"
},
"instructions": "# ML Instructions\n\n- Keep structured ML workflows separate from LLM explanation workflows.\n- Use measurable criteria: split, metric, threshold, calibration, and known failure modes.\n- Do not commit patient-identifying or sensitive medical data.\n- Model outputs support signals and trends, not diagnosis or treatment guidance.\n- Document label assumptions, cohort limitations, and evaluation caveats near the relevant code or report.",
"cost": {
"context_tokens": 108
}
}