pyhealth

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.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured overview: an executable canonical pipeline, a high-value gotchas checklist, and a clean reference table pointing to real one-level-deep files. It respects the token budget while remaining fully actionable.

Dimension	Reasoning	Score
Conciseness	The body is lean: a compact 5-stage pipeline, a gotchas checklist, and a topic→file reference table, with no padding explaining concepts Claude already knows (e.g., no "what is an EHR" preamble). Not a level 2 — there is no discernible unnecessary explanation to tighten.	3 / 3
Actionability	The canonical pipeline is fully executable — real imports, a working synthetic MIMIC-III URL, split-by-patient, and metric printing — and the "Critical things to get right" section gives concrete API-level fixes (e.g., pass SampleDataset not BaseDataset, use ehr_root= for MIMIC-IV). Copy-paste ready.	3 / 3
Workflow Clarity	The pipeline is explicitly numbered 1–5 (Dataset→Task→Split/Loaders→Model→Train+evaluate) and backed by a "Critical things to get right" checklist plus a monitor= checkpoint for best-model selection. Not capped at 2 because this is training rather than a destructive/batch operation and the sequence + checklist are unambiguous.	3 / 3
Progressive Disclosure	SKILL.md is an overview that defers detail to six one-level-deep reference files via a clear "If the user is asking about… → Read" table, plus a starter asset; all referenced files (installation/datasets/tasks/models/medcode/examples.md, starter_pipeline.py) were verified to exist. Well-signaled, easy navigation with no nested-reference chains.	3 / 3
	Total	12 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete — it states concrete capabilities and an explicit "Use when…" clause with natural keywords. It is distinctive to the PyHealth/healthcare-ML niche and free of vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "loading EHR/signal/imaging datasets", "defining tasks", "instantiating models", "training with the PyHealth Trainer", "computing clinical metrics", and "medical code utilities… cross-mapping" — matching the top anchor for specific concrete actions. Imperative voice ("Build…") matches the rubric's good examples, so no voice penalty applies.	3 / 3
Completeness	Explicitly answers "what" (build clinical/healthcare DL pipelines with the listed capabilities) and "when" via the clause "Use this skill whenever the user mentions PyHealth, MIMIC, eICU, OMOP…". Both halves are present and explicit, so it is not capped at 2.	3 / 3
Trigger Term Quality	Covers natural terms users would actually say — PyHealth, MIMIC, eICU, OMOP, EHR modeling, clinical prediction, drug recommendation, sleep staging, ICD/ATC codes — with good breadth, not just technical jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (PyHealth healthcare-ML pipelines fitting the dataset→task→model→trainer→metrics pattern) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/pyhealth/SKILL.md
Commit: 757b63b

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.