sample-size-power-calculator

Advanced sample size and power calculations for complex study designs including survival analysis, clustered designs, and multiple comparisons.

Quality

62%

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/Academic Writing/sample-size-power-calculator/SKILL.md

Quality

Content

48%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 contains genuinely useful, concrete material (usage commands, parameter table, error-handling fallback), but it is buried in large amounts of generic template boilerplate and internal-repo artifacts. Referenced bundle files (scripts/main.py, references/audit-reference.md, requirements.txt) are missing from the bundle, and duplicated command sections plus a non-functional cd path undermine executability.

Suggestions

Cut the generic boilerplate sections (Security Checklist, Risk Assessment, Evaluation Criteria, Lifecycle Status, Output Requirements) or move them to a reference file; they add tokens without skill-specific value.

Consolidate the duplicated command sections (Quick Check, Audit-Ready Commands, Example Usage) into one usage section, and remove the non-functional 'cd "20260318/scientific-skills/..."' internal path.

Ship the referenced bundle files (scripts/main.py, references/audit-reference.md, requirements.txt) or remove the references, and document '--hazard-ratio' and other test-specific flags in the Parameters table.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with several padded, generic sections: a Security Checklist with items irrelevant to a local stats script ("API requests use HTTPS only", "API timeout and retry mechanisms"), a Risk Assessment table, Lifecycle Status with time-sensitive dates ("Next Review Date: 2026-03-06"), and Evaluation Criteria boilerplate. The same two commands are also repeated across Quick Check, Audit-Ready Commands, and Example Usage.	2 / 5
Actionability	There are concrete, specific commands ("python scripts/main.py --test ttest --effect 0.5 --alpha 0.05 --power 0.8") and a parameter table, but guidance is incomplete: the Example Usage 'cd "20260318/scientific-skills/..."' path is non-functional, '--hazard-ratio' appears in Usage examples but not in the Parameters table, and the referenced scripts/main.py and requirements.txt are not present in the bundle.	3 / 5
Workflow Clarity	A clear sequence exists with most checkpoints present: a pre-execution parse check ("python -m py_compile scripts/main.py"), stop-early scope validation, and an explicit fallback path in Error Handling ("If scripts/main.py fails, report the failure point..."). It falls short of 5 because the workflow is scattered and duplicated across overlapping sections (Workflow, Example Usage run plan, Implementation Details) with circular 'See ## Usage above' cross-references.	4 / 5
Progressive Disclosure	There is real section structure and a clearly signaled References section linking references/audit-reference.md, but that file does not exist in the bundle, and substantial generic boilerplate (Security Checklist, Risk Assessment, Evaluation Criteria, Lifecycle Status) that belongs in a separate reference is inlined in SKILL.md.	3 / 5
	Total	12 / 20 Passed

Description

61%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.

The description clearly states what the skill does and covers a well-defined statistical niche, but it lacks any explicit 'when to use' trigger guidance and leans on vague qualifiers ('Advanced', 'complex') instead of enumerating more distinct concrete actions. Adding a use-when clause and natural synonyms like 'power analysis' would strengthen it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks how many participants/subjects a study needs, or requests a power analysis for survival, clustered, or multi-arm trial designs.'

Replace vague qualifiers ('Advanced', 'complex study designs') with concrete action verbs and outputs, e.g. 'Computes required sample size, achieved power, and dropout-adjusted N for survival, clustered, and multiple-comparison designs.'

Include common user phrasings such as 'power analysis' and 'clinical trial sample size' to improve trigger matching.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ("sample size and power calculations") with specific design contexts ("survival analysis, clustered designs, and multiple comparisons"), but "Advanced" and "complex" are vague qualifiers rather than distinct actions, matching the '1-2 concrete actions, not comprehensive' anchor better than the several-distinct-actions anchor.	3 / 5
Completeness	The 'what' is clear (sample size and power calculations for named complex designs), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Good natural keyword coverage with "sample size", "power", "survival analysis", and "multiple comparisons", but common variations users would say are missing, e.g. "power analysis", "how many participants", or "clinical trial".	4 / 5
Distinctiveness Conflict Risk	The niche (sample size/power for survival, clustered, and multiple-comparison designs) is mostly distinct with specific triggers, though it could overlap with a general statistics or basic sample-size skill.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 13 missing	Warning

	Total	13 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Academic Writing/sample-size-power-calculator/SKILL.md
Commit: 686e09d

Reviewed: 13 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.