- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add Aperivue/medsci-skills --skill design-study -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add Aperivue/medsci-skills --skill design-study -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add Aperivue/medsci-skills --skill design-study -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add Aperivue/medsci-skills --skill design-study -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/Aperivue/medsci-skills/tree/HEAD/skills/design-studyDe l'éditeur
Always inspect:
/define-variables before drafting Methods.## Study Design Review
Question: ...
Study type: ...
Analysis unit: ...
Index date / prediction timepoint: ...
### Strengths
- ...
### Major validity risks
1. ...
2. ...
### Minimal fixes
- ...
### Reporting fit
- Recommended guideline: ...
### Decision
- Ready for analysis / Needs redesign / Drafting can proceed with limitations
Cite a reference only with a /search-lit-confirmed DOI or PMID; mark any other [UNVERIFIED - NEEDS MANUAL CHECK]. Never invent a clinical definition, diagnostic criterion, or guideline recommendation: flag an unconfirmed one [VERIFY] and ask the user.
Extract from the protocol, draft, slides, tables, or notes: clinical problem, intended use case, population, inputs, outputs, outcome definition, and timing of variable availability.
Gate: Present the reconstructed study summary (question, analysis unit, intended use) to the user and confirm it before proceeding — a wrong reconstruction misdirects the entire validity review.
Read a reference only when its condition holds:
Look for mismatches: a patient-level claim from lesion-level analysis; an exam-level split with patient overlap; phase-level samples treated as independent.
Look for:
For any time-to-event or incident/transition design, check before drafting:
Check who established ground truth, when, whether blinding was possible, and whether only a subset had gold-standard verification. Then:
variable_operationalization.md. Methods definitions must match the
/define-variables operationalization table verbatim, and a blinded re-classification form must
quote the analytic protocol's definition verbatim. A paraphrase or "common-sense extension" in the
form is the documented cause of a low κ that is a definition mismatch, not real disagreement.Classify: apparent only, internal split, cross-validation, temporal, external, or multi-center external.
When the study elicits expert ratings — a reader study, an annotation panel, an AI-output evaluation —
read references/reader_elicitation_design.md before data collection. The acceptance ceiling of a
perceptual / reader AI study is fixed at design time: no quality of execution lifts a ceiling baked
into the comparator, the estimand, or the reader cohort. For an AI-system-versus-human-expert
benchmark, route to /design-ai-benchmarking (arm definition, LLM-as-judge versus human-as-judge
adjudication, structured export schema).
Ask whether the comparator and endpoint support the stated claim:
incremental_value.md; Kerr et
al., Epidemiology 2014). A standalone discrimination number does not support a "beyond X"
claim, and the nested-model comparison cannot be added post hoc without the baseline model.references/combine_models_ablation_design.md;references/multi_model_comparison_design.md;references/segmentation_failure_characterization_design.md. A mean DSC cannot be converted into
a usability claim after the fact.Recommend one primary guideline — TRIPOD+AI, CLAIM, STARD, STROBE (TARGET for a
target-trial emulation), PRISMA, CARE, or ARRIVE — plus journal-specific additions if needed.
No clinically relevant comparator; exam-level instead of patient-level split; unclear reference standard; AUROC-only reporting without threshold metrics.
Unclear time zero; immortal time bias; feature timing mismatch; no calibration.
references/target_trial_emulation.md.scripts/adjustment_set_helper.py (flags mediator /
collider / descendant adjustment and omitted confounders, and proposes a candidate backdoor set),
then derive the minimal sufficient set with dagitty — see references/dag_adjustment.md. At
review time /self-review Phase 2.5e and the O-probes in observational_confounding.md (O1–O18)
check this against Table 1 — including O7 over-adjustment, O10 overlapping-subset-gradient
discipline, O11 design-based weighting for complex-survey data, O12 data-driven-threshold mining,
O13 (a cross-sectional mediation claim cannot order X→M→Y), and O14 (a synergy/joint-effect claim
needs the additive interaction scale — RERI/AP/S — not a multiplicative-only test).No clear rubric for clinical correctness; benchmark labels derived from noisy reports without adjudication; unsupported claims about safety or workflow benefit; input text containing the target label or diagnosis being predicted; no same-backbone zero-shot/few-shot baseline for a fine-tuning or prompt-engineering claim.
Overlapping cohorts; paired modalities analyzed as independent; heterogeneity metrics missing; zero-cell handling unspecified.
Recommend the smallest feasible repair first: clarify the claim, narrow the target population, add a limitation statement, add a clinically relevant baseline, re-run one key sensitivity analysis, or redefine the endpoint more explicitly. Escalate to redesign only when the central claim is not defensible otherwise.
analyze-stats when the design is basically sound but analysis details need refinementcheck-reporting after the design is lockedself-review when the user wants a pre-submission quality check on their own manuscriptwrite-paper only after the main validity risks are documentedThis skill does not compute statistics, draft full manuscript prose, resolve raw data-engineering issues, or replace a full peer review when journal-facing tone is required.
Use when checking a radiology or medical AI study design before drafting or submission. Reviews the analysis unit, cohort logic, leakage risks, comparator, validation strategy and reporting-guideline
---name: design-studydescription: Use when checking a radiology or medical AI study design before drafting or submission. Reviews the analysis…---# skills/design-study/SKILL.mdVue d'ensemble
Use when checking a radiology or medical AI study design before drafting or submission. Reviews the analysis unit, cohort logic, leakage risks, comparator, validation strategy and reporting-guideline fit. AI-vs-expert benchmarks are /design-ai-benchmarking.
FAQ
Téléchargez skills/design-study/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/Aperivue/medsci-skills.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.
/self-reviewcheck_scope_coherence.pyCROSS_SECTIONAL_PROGNOSTICSURROGATE_CARE_DIRECTIVE