CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pyhealth

Healthcare AI toolkit for clinical ML. EHR processing, clinical prediction (mortality, readmission, drug recommendation), medical coding (ICD/NDC/ATC), signals (EEG/ECG), datasets (MIMIC-III/IV, eICU, OMOP), and healthcare deep learning (RETAIN, SafeDrug, Transformer, GNN) via...

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/pyhealth/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

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

Highly actionable content with a clear pipeline structure and executable examples, but it is undermined by notable verbosity (a near-duplicate full workflow example, redundant use-case listings, promotional filler) and a progressive-disclosure promise that breaks because the referenced `references/` files are absent from the bundle.

Suggestions

Ship the six `references/*.md` files the body cites (datasets, medical_coding, tasks, models, preprocessing, training_evaluation) or remove the dangling pointers — the body currently promises ~28,000 words of documentation that does not exist in the bundle.

Remove the duplicated ~90-line 'Complete Workflow' example (keep one, differing only in model choice) and cut the per-file word counts and the K-Dense Web promotional section.

Collapse the six 'Use Case' sections into a short table mapping task → relevant references, since they mostly restate the Detailed Documentation pointers.

DimensionReasoningScore

Conciseness

The body is noticeably padded in several places: the ~90-line 'Complete Workflow' example near the end largely duplicates the Quick Start (same MIMIC-IV mortality pipeline with RETAIN instead of Transformer); six 'Use Case' sections mostly restate 'Read references/X.md' pointers already covered by the Detailed Documentation section; filler like per-file word counts ('4,500 words', '~28,000 words') adds no guidance; and an off-topic promotional section ('Suggest Using K-Dense Web For Complex Worflows') consumes tokens without serving the skill's purpose. Roughly a third of the file could be cut without losing actionable content, matching 'several unnecessary explanations or padded sections'.

2 / 5

Actionability

The Quick Start and Complete Workflow are fully executable, copy-paste-ready pipelines (real imports, `MIMIC4Dataset`, `split_by_patient`, `get_dataloader`, `Trainer.train` with concrete hyperparameters, `trainer.evaluate` with named metrics, attention-based interpretation), plus an exact install command (`uv pip install pyhealth`), runnable best-practice snippets (`split_by_patient`, `dataset.stats()`), and concrete troubleshooting steps. Specific examples cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

The 5-stage pipeline (Data Loading → Task Definition → Model Selection → Training → Deployment) is explicitly enumerated, the Quick Start numbers its steps 1-5, and each Use Case sequences its approach with pointers; evaluation on held-out data and `monitor='pr_auc_score'` act as checkpoints. It is a 4 rather than 5 because there are no explicit validate-and-retry loops inside the workflows themselves (error handling is deferred to a separate Troubleshooting section rather than wired into the steps), though model training is not a destructive/batch operation that would cap the score at 3.

4 / 5

Progressive Disclosure

The body signals its six reference files well — each has a 'File' path plus 'Read when' conditions — but the referenced bundle does not actually exist: no `references/`, `scripts/`, or `assets/` directories are present, so every `references/*.md` pointer is a dangling path and the disclosed structure fails at load time. Per the guideline to score against the actual bundle structure, this lands at 'some structure but could be better organized' — good in-body signaling undermined by missing files, non-link formatting, and reference material (use cases, best practices) partially duplicated inline.

3 / 5

Total

14

/

20

Passed

Description

70%Weight 40%Scale 1-5

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

A specific, well-targeted description with excellent domain keywords and near-zero conflict risk, but it is structurally incomplete: the sentence is truncated at 'via...' and contains no 'Use when...' trigger guidance, capping its usefulness for invocation decisions.

Suggestions

Complete the truncated sentence (it currently ends mid-clause at 'via...') and finish the thought that was cut off.

Add an explicit 'Use when...' clause, e.g., 'Use when working with MIMIC/eICU/OMOP EHR data, clinical prediction tasks, medical coding translation, or physiological signals like EEG/ECG.'

Lead capability phrases with concrete verbs (e.g., 'Processes EHR data', 'Trains clinical prediction models') instead of bare noun lists.

DimensionReasoningScore

Specificity

The description lists many concrete capabilities with specific nouns — 'EHR processing, clinical prediction (mortality, readmission, drug recommendation), medical coding (ICD/NDC/ATC), signals (EEG/ECG), datasets (MIMIC-III/IV, eICU, OMOP), and healthcare deep learning (RETAIN, SafeDrug, Transformer, GNN)' — which matches the 'lists several specific actions; minor gaps in coverage' anchor. It is not a 5 because the capabilities are noun phrases rather than concrete verb-led actions, and the sentence is cut off mid-clause ('...GNN) via...'), leaving coverage visibly incomplete.

4 / 5

Completeness

It clearly answers 'what' (a healthcare AI toolkit for clinical ML with enumerated capabilities) but has no 'Use when...' clause or equivalent trigger guidance — the sentence ends with the truncated 'via...' before any when-clause could appear. Per the judging guideline, a missing explicit 'when' caps completeness at 3; this matches the anchor 'Has a clear what but when is missing or only weakly implied' exactly.

3 / 5

Trigger Term Quality

Strong natural keyword coverage a clinical-ML user would actually say: 'Healthcare AI', 'clinical ML', 'EHR', 'mortality', 'readmission', 'drug recommendation', 'ICD/NDC/ATC', 'EEG/ECG', 'MIMIC-III/IV, eICU, OMOP'. It is a 4 rather than 5 because a few common variations are missing (e.g., 'clinical prediction', 'sleep staging', 'fairness', 'medical NLP'), and the truncated 'via...' tail may have cut off additional trigger phrasing.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche with distinct triggers — named datasets (MIMIC-III/IV, eICU, OMOP), named models (RETAIN, SafeDrug, GAMENet-class deep learning), and clinical signals (EEG/ECG) — that no generic data-science or ML skill would claim. Minimal conflict risk; matches the 'clear niche with distinct triggers' anchor.

5 / 5

Total

16

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (508 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 34 missing

Warning

Total

13

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Data Analysis/pyhealth/SKILL.md

Reviewed

Table of Contents

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.