Imported from phulin/poker2 (src/p2/models/cnn/AGENTS.md). Install upstream with npx skills add phulin/poker2 --skill cnn. Copyright stays with the author.
Directory summary
CNN model family for policy/value self-play using card and action tensor planes.
Source files
__init__.py: Package marker.
cards_encoder.py: Converts card state into plane features.
actions_encoder.py: Encodes heads-up action history into tensor features.
cnn_embedding_data.py: Dataclass container for CNN embeddings.
state_encoder.py: Combines environment state into CNN-ready embeddings.
siamese_convnet.py: SiameseConvNetV1 trunks and policy/value heads.
Subdirectories
There are no child source directories.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
yaml
targets:
- https://api.opensmartroute.ai/api/v1/registry/phulin-poker2-cnn/manifest # or paste the manifest below
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
phulin-poker2-cnn.ocm.jsonjson
{
"ocm": "1",
"id": "phulin-poker2-cnn",
"kind": "skill",
"name": "cnn",
"description": "Directory summary CNN model family for policy/value self-play using card and action tensor planes.",
"publisher": "phulin",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Directory summary CNN model family for policy/value self-play using card and action tensor planes."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/phulin/poker2",
"path": "src/p2/models/cnn/AGENTS.md",
"ref": "984fe7a6bd25f16bd16ae73cb4448f8d9cd32033",
"url": "https://github.com/phulin/poker2/blob/984fe7a6bd25f16bd16ae73cb4448f8d9cd32033/src/p2/models/cnn/AGENTS.md",
"key": "phulin/poker2/src/p2/models/cnn/AGENTS.md"
}
},
"instructions": "## Directory summary\nCNN model family for policy/value self-play using card and action tensor planes.\n\n### Source files\n- `__init__.py`: Package marker.\n- `cards_encoder.py`: Converts card state into plane features.\n- `actions_encoder.py`: Encodes heads-up action history into tensor features.\n- `cnn_embedding_data.py`: Dataclass container for CNN embeddings.\n- `state_encoder.py`: Combines environment state into CNN-ready embeddings.\n- `siamese_convnet.py`: SiameseConvNetV1 trunks and policy/value heads.\n\n### Subdirectories\nThere are no child source directories.",
"cost": {
"context_tokens": 141
}
}
Fetch it by URL: GET /api/v1/registry/phulin-poker2-cnn/manifest?version=1.0.0
Reviews
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.
