adaptive-trial-simulator

Design and simulate adaptive clinical trials with interim analyses, sample size re-estimation, and early stopping rules. Evaluate Type I error control, power, and expected sample size via Monte Carlo simulation before trial initiation.

7.30x

Quality

60%

Does it follow best practices?

Impact

73%

7.30x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Evidence insights/adaptive-trial-simulator/SKILL.md

Quality

Discovery

82%

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

This is a well-crafted description with excellent specificity and domain-appropriate trigger terms that clearly define a specialized clinical trial simulation capability. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill over others.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about designing adaptive trials, simulating clinical studies, or evaluating statistical properties of trial designs.'

Consider adding common variations like 'clinical study design', 'Bayesian adaptive design', or 'group sequential trials' to capture additional user phrasings.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'design and simulate adaptive clinical trials', 'interim analyses', 'sample size re-estimation', 'early stopping rules', 'evaluate Type I error control, power, and expected sample size', and 'Monte Carlo simulation'.	3 / 3
Completeness	Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied (before trial initiation).	2 / 3
Trigger Term Quality	Includes strong natural keywords users in clinical research would say: 'adaptive clinical trials', 'interim analyses', 'sample size re-estimation', 'early stopping rules', 'Type I error', 'power', 'Monte Carlo simulation', 'trial initiation'.	3 / 3
Distinctiveness Conflict Risk	Highly specialized domain with distinct terminology like 'adaptive clinical trials', 'Type I error control', and 'Monte Carlo simulation' that would not conflict with general statistics or other skills.	3 / 3
	Total	11 / 12 Passed

Implementation

37%

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

This skill provides a solid CLI reference with clear parameter documentation and output examples, but lacks the workflow guidance essential for a complex statistical simulation task. The content is padded with administrative sections (security checklist, risk assessment, lifecycle) that don't help Claude execute the task, while missing critical guidance on interpreting results, validating designs, and iterating when simulations reveal problems.

Suggestions

Add a clear workflow section showing the iterative design process: initial simulation → interpret results → adjust parameters → re-simulate, with explicit validation checkpoints (e.g., 'If Type I error > 0.05, reduce alpha spending aggressiveness')

Include concrete examples of interpreting simulation output - what constitutes acceptable Type I error control, how to decide if power is sufficient, when to increase sample size

Remove or relocate administrative sections (security checklist, risk assessment, lifecycle status) to separate files - these don't help with task execution

Add Python code examples for programmatic usage and result analysis, not just CLI invocations

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient but includes some unnecessary sections like the extensive security checklist, risk assessment table, and lifecycle status that add bulk without providing actionable guidance for the core task. The parameter tables are useful but could be more compact.	2 / 3
Actionability	Provides concrete CLI commands and parameter tables, but lacks executable Python code examples showing how to interpret results or customize simulations programmatically. The commands are copy-paste ready but the skill doesn't show how to work with the output or handle common scenarios.	2 / 3
Workflow Clarity	No clear workflow for the multi-step process of designing, simulating, validating, and iterating on adaptive trial designs. Missing validation checkpoints - how do you verify Type I error is controlled? What if power is insufficient? No feedback loops for the iterative design optimization process.	1 / 3
Progressive Disclosure	References to 'references/' directory exist but are vague ('Adaptive design statistical theory'). The content is somewhat organized with tables and sections, but mixes quick-start usage with detailed parameter documentation and administrative sections (lifecycle, security) that could be separated.	2 / 3
	Total	7 / 12 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: aipoch/medical-research-skills
Commit: ca9aaa4

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.