adaptive-trial-simulator

Design and simulate adaptive clinical trials with interim analyses, decision rules, and operating-characteristic summaries; use when planning adaptive designs or comparing stopping, enrichment, or sample-size re-estimation strategies.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Protocol Design/adaptive-trial-simulator/SKILL.md

Quality

Content

50%Weight 40%Scale 1-5

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

The body delivers executable commands and useful reference tables but is weighed down by large amounts of generic, templated boilerplate and redundant sections. Domain-specific guidance is diluted across process-governance scaffolding rather than concentrated in well-split reference files.

Suggestions

Remove or consolidate the generic boilerplate sections (Output Requirements, Response Template, Output Contract, Failure Handling, User Checkpoints, Quick Validation) that are not specific to adaptive trial simulation, and merge the two duplicated References sections into one.

Move the parameter, design-type, spending-function, and output-schema tables into a reference file (e.g. references/design-reference.md) and keep SKILL.md as a concise overview with one-level-deep links.

Replace the abstract 5-step Workflow with a concrete simulation sequence that includes an explicit validate-run-check-output feedback loop for batch simulations, and update or remove the stale 'Next Review Date: 2026-03-15'.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, padded with generic process boilerplate (Output Requirements, Response Template, Required Inputs, Output Contract, Failure Handling, User Checkpoints, Quick Validation) that applies to any skill, plus a duplicated References section and time-sensitive dates (Next Review Date 2026-03-15) that are now stale.	2 / 5
Actionability	Provides concrete, executable CLI commands with real flags and defaults (e.g. 'python scripts/main.py --design group_sequential --n-simulations 50'), a full parameter table, and a representative output JSON; minor gaps as no inline programmatic API usage is shown.	4 / 5
Workflow Clarity	A sequence is present (5-step Workflow) plus py_compile validation in Quick Check, but the workflow steps are generic process governance rather than concrete simulation steps, and there is no validate-fix-retry feedback loop for the batch simulation itself.	3 / 5
Progressive Disclosure	Structure exists with clearly signaled one-level reference to references/audit-reference.md, but the bulk of detailed content (parameters, design types, spending functions, output schema) is inlined in SKILL.md and a second 'References' section lists abstract topics with no actual files.	3 / 5
	Total	12 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

A strong, third-person description that states concrete capabilities and an explicit 'use when' trigger clause covering several adaptive-design scenarios. It is specific, complete, and clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Design and simulate adaptive clinical trials', 'interim analyses', 'decision rules', and 'operating-characteristic summaries' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Design and simulate adaptive clinical trials with interim analyses, decision rules, and operating-characteristic summaries') and when ('use when planning adaptive designs or comparing stopping, enrichment, or sample-size re-estimation strategies') with concrete triggers.	5 / 5
Trigger Term Quality	Covers natural biostatistics phrases a user would actually say — 'adaptive clinical trials', 'interim analyses', 'adaptive designs', 'stopping', 'enrichment', 'sample-size re-estimation' — including synonyms and strategy variants.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (adaptive clinical trial simulation) with distinct, specialized triggers that are unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Protocol Design/adaptive-trial-simulator/SKILL.md
Commit: 63c61d3

Reviewed: 3 hours 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.