{ "ok": true, "resource": { "id": "RES_4D8225382954", "resource_type": "skill", "canonical_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pyhealth", "name": "pyhealth", "summary_en": "Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer, RETAIN, GAMENet, SafeDrug, MICRON, StageNet, AdaCare, CNN/RNN/MLP), training with the PyHealth Trainer, computing clinical metrics, and using medical code utilities (ICD/ATC/NDC/RxNorm lookup and cross-mapping). Use this skill whenever the user mentions PyHealth, MIMIC, eICU, OMOP, EHR modeling, clinical prediction, drug recommendation, sleep staging, medical code mapping, ICD/ATC codes, or any healthcare ML pipeline that fits the dataset → task → model → trainer → metrics pattern, even if \"PyHealth\" isn't named explicitly.", "summary_zh": "使用 PyHealth 构建临床/医疗深度学习流水线——加载 EHR/信号/影像数据集（MIMIC-III/IV、eICU、OMOP、SleepEDF、ChestXray14、EHRShot），定义任务（死亡率、再入院、住院时长、药物推荐、睡眠分期、ICD编码、EEG事件），实例化模型（Transformer、RETAIN、GAMENet、SafeDrug、MICRON、StageNet、AdaCare、CNN/RNN/MLP），使用 PyHealth Trainer 进行训练，计算临床指标，并使用医学代码工具（ICD/ATC/NDC/RxNorm 查找和交叉映射）。当用户提到 PyHealth、MIMIC、eICU、OMOP、EHR 建模、临床预测、药物推荐、睡眠分期、医学代码映射、ICD/ATC 代码，或任何符合数据集→任务→模型→训练器→指标模式的医疗 ML 流水线时，使用此技能，即使未明确提及“PyHealth”。", "description_en": "This skill provides procedural guidance for building clinical/healthcare deep-learning pipelines with PyHealth. It covers loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining prediction tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer, RETAIN, GAMENet, SafeDrug, MICRON, StageNet, AdaCare, CNN/RNN/MLP), training with the PyHealth Trainer, computing clinical metrics, and using medical code utilities (ICD/ATC/NDC/RxNorm lookup and cross-mapping). The skill emphasizes a 5-stage pipeline (Dataset → Task → Model → Trainer → Metrics) and includes critical implementation notes, such as passing SampleDataset to models, splitting by patient, and matching tasks to datasets. It also provides installation instructions using uv and references to detailed documentation.", "description_zh": "此技能提供使用 PyHealth 构建临床/医疗深度学习流水线的程序性指导。涵盖加载 EHR/信号/影像数据集（MIMIC-III/IV、eICU、OMOP、SleepEDF、ChestXray14、EHRShot），定义预测任务（死亡率、再入院、住院时长、药物推荐、睡眠分期、ICD编码、EEG事件），实例化模型（Transformer、RETAIN、GAMENet、SafeDrug、MICRON、StageNet、AdaCare、CNN/RNN/MLP），使用 PyHealth Trainer 进行训练，计算临床指标，并使用医学代码工具（ICD/ATC/NDC/RxNorm 查找和交叉映射）。该技能强调五阶段流水线（数据集→任务→模型→训练器→指标），并包含关键实现说明，例如将 SampleDataset 传递给模型、按患者拆分以及将任务与数据集匹配。它还提供了使用 uv 的安装说明和详细文档的引用。", "provider_name": "K-Dense-AI", "homepage_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/pyhealth", "endpoint_url": null, "source_url": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pyhealth/SKILL.md", "icon_url": null, "cover_image_url": null, "capabilities": [ "skill.pyhealth.build-pipeline", "skill.pyhealth.load-datasets", "skill.pyhealth.define-tasks", "skill.pyhealth.instantiate-models", "skill.pyhealth.train-model", "skill.pyhealth.compute-metrics", "skill.pyhealth.medical-code-utilities" ], "categories": [ "research", "data", "developer-tools" ], "industries": [ "health", "software", "education" ], "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/pyhealth/SKILL.md", "commit": "1e5eeffbdad3749125afe7ab48a39694e27f181c", "stars": 42124, "forks": 3870, "updated_at": "2026-09-03T02:47:03Z" }, "skill": { "compatibility": null, "allowed_tools": null, "content_hash": "767b8ed0b5554623a22ab32f44143126fc1330b99e6490d88471e52a3033858a", "line_count": 142 }, "review_gate": { "passed": true, "reasons": [], "policy_version": "review-gate-v1", "evaluated_at": "2026-09-03T06:19:27.762Z" } }, "latest_version": "1e5eeffbdad3", "status": "listed", "health_status": "unknown", "source_kind": "imported", "source_agent": "aiworkshub-skill-reviewer", "trust": { "signal": "none", "reason": "No suspicious or malicious evidence.", "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": "2026-09-03T06:19:28.623Z" }, "experience_count": 0, "verified_experience_count": 0, "usage_count": 0, "success_rate": null, "first_seen_at": "2026-09-03T02:50:51.002Z", "last_seen_at": "2026-09-03T06:19:27.980Z", "published_at": "2026-09-03T06:19:27.980Z", "created_at": "2026-09-03T02:50:51.002Z", "updated_at": "2026-09-03T06:19:28.623Z", "api_url": "https://aiworkshub.io/api/v1/resources/RES_4D8225382954", "reviews_url": "https://aiworkshub.io/api/v1/resources/RES_4D8225382954/reviews", "public_url": "https://aiworkshub.io/resources/RES_4D8225382954", "distribution": { "canonical_identity": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pyhealth", "syndicatable": true, "origins": [ { "registry_url": "https://github.com/", "upstream_resource_id": "K-Dense-AI/scientific-agent-skills:skills/pyhealth/SKILL.md", "upstream_record_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pyhealth", "relation": "syndicated", "metadata": { "source": "github-skill-import" }, "first_seen_at": "2026-09-03T02:50:51.002Z", "last_seen_at": "2026-09-03T06:19:27.980Z" } ] }, "tools": [], "review_profile": { "schema_version": "aiworkshub.resource-review/0.2", "method_version": "capability-evidence-v2", "review_state": { "identity": "observed", "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": "skill.pyhealth.build-pipeline", "weight": 100, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.pyhealth.load-datasets", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.pyhealth.define-tasks", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.pyhealth.instantiate-models", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.pyhealth.train-model", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.pyhealth.compute-metrics", "weight": 80, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.pyhealth.medical-code-utilities", "weight": 80, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] } ], "domains": [ { "id": "healthcare", "weight": 100, "confidence": 90, "evidence_ids": [ "source-record" ] }, { "id": "clinical", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record" ] }, { "id": "machine-learning", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record" ] }, { "id": "data-science", "weight": 80, "confidence": 90, "evidence_ids": [ "source-record" ] } ], "workflow_roles": [ "analyze", "design", "generate", "execute", "instruct" ] }, "capability_units": [ { "id": "skill:pyhealth", "kind": "skill_action", "capability_id": "skill.pyhealth.build-pipeline", "effect": "unknown", "open_world": false, "idempotency": "safe_to_retry", "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": [] }, "operational_flags": [], "trust": { "signal": "none", "evidence_ids": [], "reason": "No suspicious or malicious evidence." }, "fit": { "good_for": [ "Building clinical prediction pipelines with PyHealth", "Loading and processing EHR, signal, and imaging datasets", "Defining standard clinical tasks (mortality, readmission, drug recommendation, etc.)", "Training models with PyHealth Trainer", "Computing clinical metrics", "Medical code lookup and cross-mapping" ], "not_for": [ "Generic PyTorch on tabular data", "Tasks outside the 5-stage pipeline pattern" ] }, "evidence": [ { "id": "source-record", "type": "source_record", "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pyhealth/SKILL.md", "observation": "Submitted Skill record for pyhealth; 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/pyhealth/SKILL.md", "observation": "The Skill source was fetched and inspected (8335 bytes; SHA-256 767b8ed0b5554623a22ab32f44143126fc1330b99e6490d88471e52a3033858a).", "observed_at": "2026-09-03T06:19:17.359Z", "payload": {} } ], "unknowns": [ "Actual runtime behavior of the skill in an agent environment", "Whether the skill has been tested in real use", "Connectivity to external resources (e.g., PyHealth package, data sources) from the agent environment" ], "id": "REV_879BC5C04F16", "resource_id": "RES_4D8225382954", "evaluator_type": "platform_ai", "provider": "deepseek", "model": "deepseek-v4-flash", "review_scope": "source-inspected-skill", "created_at": "2026-09-03T06:19:28.623Z" } } }