{ "ok": true, "resource": { "id": "RES_98ACF8C081C6", "resource_type": "skill", "canonical_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/torch-geometric", "name": "torch-geometric", "summary_en": "PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.", "summary_zh": "PyTorch Geometric (PyG) 用于图神经网络——节点/边/图分类、消息传递（GCN、GAT、GraphSAGE、GIN）、异构图、邻居采样和自定义数据集。当使用 torch_geometric 时使用，不适用于一般的 NetworkX 分析或非图 PyTorch 模型。", "description_en": "This Agent Skill provides procedural guidance for using PyTorch Geometric (PyG) to build and train graph neural networks. It covers core data structures (Data, HeteroData), dataset loading, common GNN layers (GCN, GAT, GraphSAGE, GIN, etc.), building custom message passing layers, task-specific patterns for node/graph/link classification, scaling to large graphs via neighbor sampling, heterogeneous graph support, custom dataset creation, and explainability. The skill includes installation instructions, code examples, and common pitfalls. It is intended for use with torch_geometric and is not for general NetworkX analytics or non-graph PyTorch models.", "description_zh": "该Agent技能提供了使用PyTorch Geometric (PyG)构建和训练图神经网络的程序性指导。涵盖核心数据结构（Data、HeteroData）、数据集加载、常见GNN层（GCN、GAT、GraphSAGE、GIN等）、构建自定义消息传递层、节点/图/链接分类的任务特定模式、通过邻居采样扩展到大型图、异构图支持、自定义数据集创建和可解释性。技能包括安装说明、代码示例和常见陷阱。它适用于torch_geometric，不适用于一般的NetworkX分析或非图PyTorch模型。", "provider_name": "K-Dense-AI", "homepage_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/torch-geometric", "endpoint_url": null, "source_url": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/torch-geometric/SKILL.md", "icon_url": null, "cover_image_url": null, "capabilities": [ "graph.neural-network.training", "graph.data-processing", "graph.model-implementation", "graph.scaling", "graph.explainability" ], "categories": [ "data", "research", "developer-tools" ], "industries": [ "software", "general" ], "protocols": [ "agent-skills" ], "auth": { "type": "none", "required": false }, "pricing": { "model": "free" }, "input_schema": {}, "output_schema": {}, "metadata": { "content_language": "en", "translation_status": "original-only", "license": { "spdx_id": "MIT", "source": "https://github.com/K-Dense-AI/scientific-agent-skills/blob/1e5eeffbdad3749125afe7ab48a39694e27f181c/LICENSE" }, "github": { "repository": "K-Dense-AI/scientific-agent-skills", "owner": "K-Dense-AI", "path": "skills/torch-geometric/SKILL.md", "commit": "1e5eeffbdad3749125afe7ab48a39694e27f181c", "stars": 42124, "forks": 3870, "updated_at": "2026-09-03T02:47:03Z" }, "skill": { "compatibility": "Requires Python 3.10+, PyTorch 2.6+, and torch-geometric 2.7.x. Optional extension wheels (pyg-lib, torch-scatter, torch-sparse, torch-cluster) must match your PyTorch/CUDA build from https://data.pyg.org/whl.", "allowed_tools": null, "content_hash": "3b6dd242f7633fdb1f63a1ec9f6a0a631931cba3a7943936764cb257345c047e", "line_count": 476 }, "review_gate": { "passed": true, "reasons": [], "policy_version": "review-gate-v1", "evaluated_at": "2026-09-03T06:05:36.026Z" } }, "latest_version": "1e5eeffbdad3", "status": "listed", "health_status": "unknown", "source_kind": "imported", "source_agent": "aiworkshub-skill-reviewer", "trust": { "signal": "none", "reason": null, "signals": { "yellow": 0, "red": 0 } }, "review_summary": { "method_version": "capability-evidence-v2", "capability_definition": "strong", "contract_completeness": "strong", "access_friction": "low", "operational_transparency": "strong", "evidence_strength": "source_inspected", "use_readiness": "ready_for_guidance", "reviewed_at": "2026-09-03T06:05:36.952Z" }, "experience_count": 0, "verified_experience_count": 0, "usage_count": 0, "success_rate": null, "first_seen_at": "2026-09-03T02:51:00.568Z", "last_seen_at": "2026-09-03T06:05:36.331Z", "published_at": "2026-09-03T06:05:36.331Z", "created_at": "2026-09-03T02:51:00.568Z", "updated_at": "2026-09-03T06:05:36.952Z", "api_url": "https://aiworkshub.io/api/v1/resources/RES_98ACF8C081C6", "reviews_url": "https://aiworkshub.io/api/v1/resources/RES_98ACF8C081C6/reviews", "public_url": "https://aiworkshub.io/resources/RES_98ACF8C081C6", "distribution": { "canonical_identity": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/torch-geometric", "syndicatable": true, "origins": [ { "registry_url": "https://github.com/", "upstream_resource_id": "K-Dense-AI/scientific-agent-skills:skills/torch-geometric/SKILL.md", "upstream_record_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/torch-geometric", "relation": "syndicated", "metadata": { "source": "github-skill-import" }, "first_seen_at": "2026-09-03T02:51:00.568Z", "last_seen_at": "2026-09-03T06:05:36.331Z" } ] }, "tools": [], "review_profile": { "schema_version": "aiworkshub.resource-review/0.2", "method_version": "capability-evidence-v2", "review_state": { "identity": "verified", "source": "verified", "connectivity": "unknown", "contract": "strong", "safe_use": "untested", "real_use": "unobserved" }, "assessment": { "capability_definition": "strong", "contract_completeness": "strong", "access_friction": "low", "operational_transparency": "strong", "evidence_strength": "source_inspected", "use_readiness": "ready_for_guidance" }, "profile": { "capabilities": [ { "id": "graph.neural-network.training", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "graph.data-processing", "weight": 80, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "graph.model-implementation", "weight": 85, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "graph.scaling", "weight": 70, "confidence": 80, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "graph.explainability", "weight": 60, "confidence": 80, "evidence_ids": [ "source-record", "source-inspection" ] } ], "domains": [ { "id": "machine-learning", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "graph-analytics", "weight": 80, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "scientific-computing", "weight": 70, "confidence": 80, "evidence_ids": [ "source-record", "source-inspection" ] } ], "workflow_roles": [ "analyze", "design", "generate", "execute", "instruct" ] }, "capability_units": [ { "id": "skill:torch-geometric", "kind": "skill_action", "capability_id": "graph.neural-network.training", "effect": "unknown", "open_world": false, "idempotency": "unknown", "confirmation": "explicit policy", "input_contract": "natural_language", "output_contract": "natural_language", "accepts": [ "task context" ], "produces": [ "task result" ], "runtime_auth": {}, "pricing": {}, "evidence_ids": [ "source-inspection" ], "metadata": {} } ], "access": { "distribution_license": { "spdx_id": "MIT", "source": "https://github.com/K-Dense-AI/scientific-agent-skills/blob/1e5eeffbdad3749125afe7ab48a39694e27f181c/LICENSE" }, "runtime_auth": {}, "runtime_pricing": {}, "dependencies": [ "Python 3.10+", "PyTorch 2.6+", "torch-geometric 2.7.x" ] }, "operational_flags": [], "trust": { "signal": "none", "evidence_ids": [], "reason": null }, "fit": { "good_for": [ "Building and training graph neural networks for node, link, and graph classification tasks.", "Implementing custom GNN layers using the MessagePassing interface.", "Handling heterogeneous graphs with multiple node and edge types.", "Scaling GNN training to large graphs using neighbor sampling.", "Creating custom graph datasets from various data sources." ], "not_for": [ "General NetworkX analytics or non-graph PyTorch models.", "Tasks requiring real-time inference or production deployment without additional engineering." ] }, "evidence": [ { "id": "source-record", "type": "source_record", "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/torch-geometric/SKILL.md", "observation": "Submitted Skill record for torch-geometric; declared license MIT.", "observed_at": "2026-09-03T02:47:03Z", "payload": {} }, { "id": "source-inspection", "type": "source_inspection", "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/torch-geometric/SKILL.md", "observation": "The Skill source was fetched and inspected (19352 bytes; SHA-256 3b6dd242f7633fdb1f63a1ec9f6a0a631931cba3a7943936764cb257345c047e).", "observed_at": "2026-09-03T06:05:26.490Z", "payload": {} } ], "unknowns": [ "Actual runtime behavior and performance not tested.", "Real-world usage and adoption not observed.", "Compatibility with specific PyTorch/CUDA versions beyond stated requirements not verified.", "Effectiveness of the skill in practice not measured." ], "id": "REV_15F467FF1881", "resource_id": "RES_98ACF8C081C6", "evaluator_type": "platform_ai", "provider": "deepseek", "model": "deepseek-v4-flash", "review_scope": "source-inspected-skill", "created_at": "2026-09-03T06:05:36.952Z" } } }