Design reproducible ML experiments with valid splits, baselines, metrics, seeds, configurations, and traceable conclusions. Use for model development and comparative experiments.
Free account. Installing gives you the manifest plus copy-paste snippets.
See reviewsImported from shinevijayan03/FounderLoop (
.agents/skills/ml-experiment-design/SKILL.md). Install upstream withnpx skills add shinevijayan03/FounderLoop --skill ml-experiment-design. Copyright stays with the author.
Separate hypothesis, method, observation, and conclusion.
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "shinevijayan03-founderloop-ml-experiment-design",
"kind": "skill",
"name": "ml-experiment-design",
"description": "Design reproducible ML experiments with valid splits, baselines, metrics, seeds, configurations, and traceable conclusions. Use for model development and comparative experiments.",
"publisher": "shinevijayan03",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Design reproducible ML experiments with valid splits, baselines, metrics, seeds, configurations, and traceable conclusions. Use for model development and comparative experiments."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/shinevijayan03/FounderLoop",
"path": ".agents/skills/ml-experiment-design/SKILL.md",
"ref": "5567b65cf08c56973b6d3fc9b784f4adf49df7f1",
"url": "https://github.com/shinevijayan03/FounderLoop/blob/5567b65cf08c56973b6d3fc9b784f4adf49df7f1/.agents/skills/ml-experiment-design/SKILL.md",
"key": "shinevijayan03/FounderLoop/.agents/skills/ml-experiment-design/SKILL.md"
}
},
"instructions": "# Requirements\n- explicit hypothesis;\n- deployment-realistic split;\n- frozen evaluation protocol;\n- meaningful baseline;\n- reproducible preprocessing;\n- controlled comparison;\n- appropriate metrics;\n- uncertainty and limitations.\n\nSeparate hypothesis, method, observation, and conclusion.",
"cost": {
"context_tokens": 72
}
}Fetch it by URL: GET /api/v1/registry/shinevijayan03-founderloop-ml-experiment-design/manifest?version=1.0.0
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.