mlp

Name: mlp
Author: jt-09

Trains sklearn MLP and PyTorch embedding MLP on Adult Income data. Use for MODEL-005, mlp_torch.py, script 10, Figure 9 training curves.

by jt-09(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from jt-09/uci-adult-data-ml (.cursor/skills/mlp/SKILL.md). Install upstream with npx skills add jt-09/uci-adult-data-ml --skill mlp. Copyright stays with the author.

MLP Skill

Workflow

Sklearn: mlp_sklearn via pipelines.build_model_pipeline + 05_tune_models or 10_run_mlp_experiments.
PyTorch: mlp_torch.train_embedding_mlp with categorical embeddings.
Save training curves to results/metrics/mlp_*.json.

Rules

Same train/test split as other models.
Selection metric: macro F1 (5-fold CV on train).

Use it

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}'

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

jt-09-uci-adult-data-ml-mlp.ocm.jsonjson

{
  "ocm": "1",
  "id": "jt-09-uci-adult-data-ml-mlp",
  "kind": "skill",
  "name": "mlp",
  "description": "Trains sklearn MLP and PyTorch embedding MLP on Adult Income data. Use for MODEL-005, mlp_torch.py, script 10, Figure 9 training curves.",
  "publisher": "jt-09",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Trains sklearn MLP and PyTorch embedding MLP on Adult Income data. Use for MODEL-005, mlp_torch.py, script 10, Figure 9 training curves."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/jt-09/uci-adult-data-ml",
      "path": ".cursor/skills/mlp/SKILL.md",
      "ref": "0c47670223755a1e0dc3299ee526665ccc39f216",
      "url": "https://github.com/jt-09/uci-adult-data-ml/blob/0c47670223755a1e0dc3299ee526665ccc39f216/.cursor/skills/mlp/SKILL.md",
      "key": "jt-09/uci-adult-data-ml/.cursor/skills/mlp/SKILL.md"
    }
  },
  "instructions": "# MLP Skill\n\n## Workflow\n\n1. Sklearn: `mlp_sklearn` via `pipelines.build_model_pipeline` + `05_tune_models` or `10_run_mlp_experiments`.\n2. PyTorch: `mlp_torch.train_embedding_mlp` with categorical embeddings.\n3. Save training curves to `results/metrics/mlp_*.json`.\n\n## Rules\n\n- Same train/test split as other models.\n- Selection metric: macro F1 (5-fold CV on train).",
  "cost": {
    "context_tokens": 92
  }
}

Fetch it by URL: GET /api/v1/registry/jt-09-uci-adult-data-ml-mlp/manifest?version=1.0.0