Skip to content
mif-docs

Skill reference: clinical-submission

Skill reference: clinical-submission

Section titled “Skill reference: clinical-submission”

The clinical-submission skill authors one document genre: a clinical study report (CSR) on the ICH E3 skeleton — Synopsis through Tables/Figures/ Appendices, in fixed section order — situated in the CTD (Common Technical Document) five-module frame. This reference describes what that document type is, how the skill produces one, when it earns its place, and the provenance behind it.

PropertyValue
AuthorsA clinical study report (CSR) on the ICH E3 skeleton
Purpose groupRegulated and compliance reports
MIF conceptTypesemantic
Target MIF level3
Primary sourceICH E3: Structure and Content of Clinical Study Reports

What this document type is

Section titled “What this document type is”

A clinical study report reproduces the ICH E3 structure used across regulated submissions: Synopsis, Ethics, Investigators & Study Structure, Objectives, Investigational Plan, Methods (Efficacy & Safety), Results, Discussion & Conclusions, and Tables/Figures/Appendices, in that fixed order. Its defining trait is keeping efficacy and safety distinct throughout — in Methods, in Results, and in the Discussion’s benefit-risk weighing — with every claim resolving to a cited finding. The report is also situated in the five-module CTD frame (M1 regional administrative, M2 summaries, M3 quality, M4 nonclinical study reports, M5 clinical study reports), stating that an E3 CSR lives in Module 5. The genre reproduces structure only: it never asserts clinical validity, statistical adequacy, or regulatory acceptance, and the electronic packaging of a submission (eCTD v4.0) is out of scope.

This is declarative study-and-results knowledge, not a time-bound event or a step sequence, so it projects to MIF as semantic content at Level 3.

How the skill produces one

Section titled “How the skill produces one”

clinical-submission is a genre skill: it carries the ICH E3 / CTD pattern as durable instructions plus exemplars, and writes the artifact over a MIF floor so the result is at once a human-readable report and a machine-conformant unit.

  • Pattern, made operational. The skill encodes the nine-section ICH E3 skeleton in fixed order, the CTD module framing, and the efficacy/safety separation as a rule the report must not violate — a CSR that reorders or omits a required section, or merges efficacy and safety into one undifferentiated narrative, is not conformant.
  • Exemplars set the bar. Like every genre in the suite it ships good-l1.md (the MIF Level-1 floor), good.md (the Level-3 target), bad.md (a counter-example that collapses efficacy and safety together), and evals/evals.json. The check-exemplars gate proves good-l1.md validates at L1 and good.md at Level 3.
  • MIF projection. The document is authored with MIF frontmatter (via the shared mif-frontmatter substrate) and a conceptType of semantic. mif-validate proves the Markdown ↔ JSON-LD round-trip is lossless before the document is considered done.

When it is beneficial

Section titled “When it is beneficial”

Reach for clinical-submission when the deliverable must reproduce the clinical-study-report structure of a regulatory submission — a fixed section order, efficacy and safety kept distinct, and every result traceable to a cited source. It suits work that must read as a CSR sitting in CTD Module 5, with limitations and benefit-risk stated honestly rather than glossed over.

Do not use it for a scientific journal article reporting the same trial for peer review — that follows discipline-citation-style academic conventions, not the fixed ICH E3 skeleton or CTD module frame. Do not use it for a financial or legal disclosure filing — that is a filings genre driven by securities or contract-law disclosure obligations, not a clinical-trial write-up. Do not use it for the electronic packaging of a submission (eCTD v4.0) — that is a serialization/transport concern, not this document genre. If the mandatory artifact is instead a comparison of concrete options against decision drivers, use engineering instead.

Example

Section titled “Example”

A CSR titled “CARDIA-3 — A Phase III Trial of Cortivex in Essential Hypertension” opens with a Synopsis describing a randomized, double-blind, placebo-controlled Phase III trial of once-daily oral Cortivex 20 mg across 42 sites, states its primary objective (superiority in mean seated systolic blood pressure reduction at Week 12 versus placebo), and carries that objective through Investigational Plan, Methods, and Results with efficacy (a 9.4 mmHg between-arm reduction, 95% CI 7.1 to 11.7) and safety (mild dizziness the most common adverse event, comparable serious-adverse-event rates) analyzed and reported separately. Discussion & Conclusions weighs the benefit-risk profile against the trial’s limitation to a specific baseline blood-pressure band, and Tables, Figures & Appendices renders the SeSBP trend as a Mermaid xychart-beta and the adverse-event summary as a Markdown table, citing ICH E3 and ICH E9 throughout.

Provenance & citations

Section titled “Provenance & citations”