clinical-trial

Stars870

Forks101

UpdatedMarch 12, 2026 at 04:53

Designs and analyzes clinical trials including sample size calculation, randomization schemes, endpoint selection, CONSORT reporting, and interim analysis planning; trigger when users ask about RCTs, Phase I-IV trials, or clinical study design.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

beita6969

beita6969/ScienceClaw

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

EpidemiologistsLife, Physical, and Social Science Occupations·SOC 19-1041

SKILL.md

readonly

name	clinical-trial
description	Designs and analyzes clinical trials including sample size calculation, randomization schemes, endpoint selection, CONSORT reporting, and interim analysis planning; trigger when users ask about RCTs, Phase I-IV trials, or clinical study design.

When to Trigger

Activate this skill when the user mentions:

Clinical trial design, RCT, randomized controlled trial
Sample size calculation, power analysis for trials
CONSORT, STROBE, SPIRIT guidelines
Phase I, II, III, IV trials
Primary/secondary endpoints, composite endpoints
Interim analysis, adaptive trial design, futility
Blinding, randomization, allocation concealment
Intention-to-treat (ITT), per-protocol analysis

Step-by-Step Methodology

Define the research question - Specify PICO (Population, Intervention, Comparator, Outcome). Determine if superiority, non-inferiority, or equivalence design is appropriate.
Select trial phase and design - Choose phase (I: safety/dose, II: efficacy signal, III: confirmatory, IV: post-market). Consider parallel, crossover, factorial, or adaptive designs.
Primary endpoint selection - Define primary outcome (must be clinically meaningful). Specify measurement timing and minimal clinically important difference (MCID).
Sample size calculation - Specify alpha (typically 0.05, two-sided), power (typically 80-90%), expected effect size, and dropout rate. Use appropriate formula for the endpoint type (continuous, binary, time-to-event).
Randomization and blinding - Recommend randomization method (simple, block, stratified, minimization). Specify blinding level (open-label, single, double, triple).
Statistical analysis plan - Pre-specify primary analysis method (t-test, chi-square, log-rank, mixed models). Define interim analysis schedule with alpha-spending function (O'Brien-Fleming, Lan-DeMets).
Reporting - Follow CONSORT for RCTs, STROBE for observational, SPIRIT for protocols. Include flow diagram, enrollment numbers, and all pre-specified analyses.

Key Databases and Tools

ClinicalTrials.gov - Trial registration and results
Cochrane Library - Systematic reviews of trials
FDA / EMA guidance documents - Regulatory requirements
nQuery / PASS / G*Power - Sample size software
CONSORT / SPIRIT checklists - Reporting standards

Output Format

Sample size as a table: assumptions, formula, per-arm and total N.
Trial design as a structured summary: phase, design type, arms, blinding, duration.
CONSORT flow diagram description with all participant numbers.
Statistical analysis plan with pre-specified primary and secondary analyses.

Quality Checklist

PICO clearly defined
Primary endpoint is clinically meaningful and measurable
Sample size assumptions explicitly stated with references
Dropout rate factored into sample size
Randomization and blinding method specified
Multiple comparison adjustment for secondary endpoints
Interim analysis boundaries pre-specified if applicable
ITT and per-protocol populations defined
Regulatory guideline alignment noted (FDA/EMA/ICH)

More from this repository

same repository

academic-deep-research

beita6969/ScienceClaw

Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.

2026-03-12870

academic-literature-search

beita6969/ScienceClaw

# Academic Literature Search — 学术文献检索与引用管理

2026-03-12870

arxiv-database

beita6969/ScienceClaw

Search and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors, arXiv IDs, date ranges, or categories.

2026-03-12870

arxiv-search

beita6969/ScienceClaw

Search arXiv for preprints in physics, math, CS, quantitative biology, quantitative finance, statistics, electrical engineering, economics. Use when: (1) finding preprints by topic, (2) searching by author, (3) browsing arXiv categories, (4) getting paper metadata/abstracts. NOT for: published journal articles (use crossref-search), biomedical (use pubmed-search).

2026-03-12870

asreview-screening

beita6969/ScienceClaw

Screen papers for systematic reviews using ASReview active learning. Use when: user has a large set of papers to screen for inclusion/exclusion, wants to prioritize relevant papers, or needs to reduce manual screening workload. NOT for: searching papers (use literature-search) or meta-analysis (use meta-analysis).

2026-03-12870

astronomy-cosmology

beita6969/ScienceClaw

Analyzes astronomical observations and cosmological models including telescope data processing, celestial mechanics calculations, stellar evolution, galaxy classification, and cosmological parameter estimation; trigger when users discuss stars, galaxies, exoplanets, dark matter, or the universe's large-scale structure.

2026-03-12870

name	clinical-trial
description	Designs and analyzes clinical trials including sample size calculation, randomization schemes, endpoint selection, CONSORT reporting, and interim analysis planning; trigger when users ask about RCTs, Phase I-IV trials, or clinical study design.

When to Trigger

Activate this skill when the user mentions:

Clinical trial design, RCT, randomized controlled trial
Sample size calculation, power analysis for trials
CONSORT, STROBE, SPIRIT guidelines
Phase I, II, III, IV trials
Primary/secondary endpoints, composite endpoints
Interim analysis, adaptive trial design, futility
Blinding, randomization, allocation concealment
Intention-to-treat (ITT), per-protocol analysis

Step-by-Step Methodology

Define the research question - Specify PICO (Population, Intervention, Comparator, Outcome). Determine if superiority, non-inferiority, or equivalence design is appropriate.
Select trial phase and design - Choose phase (I: safety/dose, II: efficacy signal, III: confirmatory, IV: post-market). Consider parallel, crossover, factorial, or adaptive designs.
Primary endpoint selection - Define primary outcome (must be clinically meaningful). Specify measurement timing and minimal clinically important difference (MCID).
Sample size calculation - Specify alpha (typically 0.05, two-sided), power (typically 80-90%), expected effect size, and dropout rate. Use appropriate formula for the endpoint type (continuous, binary, time-to-event).
Randomization and blinding - Recommend randomization method (simple, block, stratified, minimization). Specify blinding level (open-label, single, double, triple).
Statistical analysis plan - Pre-specify primary analysis method (t-test, chi-square, log-rank, mixed models). Define interim analysis schedule with alpha-spending function (O'Brien-Fleming, Lan-DeMets).
Reporting - Follow CONSORT for RCTs, STROBE for observational, SPIRIT for protocols. Include flow diagram, enrollment numbers, and all pre-specified analyses.

Key Databases and Tools

ClinicalTrials.gov - Trial registration and results
Cochrane Library - Systematic reviews of trials
FDA / EMA guidance documents - Regulatory requirements
nQuery / PASS / G*Power - Sample size software
CONSORT / SPIRIT checklists - Reporting standards

Output Format

Sample size as a table: assumptions, formula, per-arm and total N.
Trial design as a structured summary: phase, design type, arms, blinding, duration.
CONSORT flow diagram description with all participant numbers.
Statistical analysis plan with pre-specified primary and secondary analyses.

Quality Checklist

PICO clearly defined
Primary endpoint is clinically meaningful and measurable
Sample size assumptions explicitly stated with references
Dropout rate factored into sample size
Randomization and blinding method specified
Multiple comparison adjustment for secondary endpoints
Interim analysis boundaries pre-specified if applicable
ITT and per-protocol populations defined
Regulatory guideline alignment noted (FDA/EMA/ICH)