What are the required inputs for this skill?

It requires a structured trial metadata JSON file, which is typically produced by the trial-metadata-extractor skill as part of the protocol-to-tfl pipeline.

Does it follow regulatory standards like ICH E3?

Yes, the skill automatically assigns numbering and organization according to ICH E3 Section 14 guidelines for Subject Disposition, Efficacy, and Safety analyses.

What is a Mock TLG Generator?

It is a specialized skill that converts clinical trial metadata into structured Table, Listing, and Figure (TLG) shells used to plan and document Clinical Study Reports.

Can it generate figures like Kaplan-Meier curves?

Yes, it supports specific Figure shells including Kaplan-Meier survival curves, waterfall plots, and forest plots, including the necessary statistical annotations.

How does this help clinical programmers?

It provides precise column headers, row stubs, and programming notes that identify the necessary ADaM datasets and variables, reducing implementation ambiguity.

Mock TLG Shell Generator

Name: Mock TLG Shell Generator
Author: Appsilon

byAppsilon

•

Data Science & ML

Generates standardized clinical trial Table, Listing, and Figure (TLG) mock-up shells from structured trial metadata.

This skill automates the creation of reporting packages for Clinical Study Reports (CSR) by transforming trial metadata into comprehensive mock TLG shells. It bridges the gap between statistical analysis plans and programming by defining precise column headers, row stubs, footnotes, and statistical placeholders. Following ICH E3 standards, it ensures regulatory-aligned reporting for various study phases and therapeutic areas, particularly oncology, significantly reducing the manual effort required for trial planning and programming documentation.

Key Features

01Specialized oncology-specific TLG guidance including KM curves and response tables

02Automated generation of ICH E3-compliant Table, Listing, and Figure (TLG) shells

03Precise statistical placeholder formatting and ADaM dataset programming notes

0422 GitHub stars

05Support for complex study designs including randomized comparative and dose-finding trials

06Phase-specific catalog matching for Phase 1, 2, and 3 clinical trials

Use Cases

01Generating implementation guides for clinical programmers based on metadata

02Planning the reporting package for a Clinical Study Report (CSR)

03Standardizing TLG shell formats across multiple clinical trial programs

Key Features

01Specialized oncology-specific TLG guidance including KM curves and response tables

02Automated generation of ICH E3-compliant Table, Listing, and Figure (TLG) shells

03Precise statistical placeholder formatting and ADaM dataset programming notes

0422 GitHub stars

05Support for complex study designs including randomized comparative and dose-finding trials

06Phase-specific catalog matching for Phase 1, 2, and 3 clinical trials

Use Cases

01Generating implementation guides for clinical programmers based on metadata

02Planning the reporting package for a Clinical Study Report (CSR)

03Standardizing TLG shell formats across multiple clinical trial programs