sample-size-power-calculator

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

Quality

46%

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

38%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 is a heavily templated stub: it signals concrete commands and a parameter table but points to bundle files (scripts/main.py, references/audit-reference.md) that do not exist, and is padded with irrelevant boilerplate sections. Workflow steps are generic process guidance rather than a validated computational pipeline.

Suggestions

Ship the referenced bundle (scripts/main.py, requirements.txt, references/audit-reference.md) or remove the references; dead links make the skill non-executable and break progressive disclosure.

Cut the templated boilerplate that is irrelevant to a local statistical calculation — Security Checklist items like 'API requests use HTTPS only', the Risk Assessment 'Network Access: External API calls: High' row, Lifecycle Status, and Evaluation Criteria test cases — and remove the circular 'See ## X above' fillers.

Replace the abstract Workflow steps with a concrete computational sequence with checkpoints: choose test type → supply effect/alpha/power → run script → verify achieved power and plausible N → report assumptions.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded with templated boilerplate that adds no value (Risk Assessment table, a Security Checklist with irrelevant items like 'API requests use HTTPS only' for a local stats script, Lifecycle Status, Evaluation Criteria test cases, and circular 'See ## Prerequisites above for related details' fillers), matching 'noticeably verbose; several unnecessary ... padded sections'; it is not 1 because it does not extensively explain basic concepts Claude already knows.	2 / 5
Actionability	Concrete guidance is present — real example invocations ('python scripts/main.py --test ttest --effect 0.5 --alpha 0.05 --power 0.8') and a parameter table with specific flags — but the referenced scripts/main.py does not exist in the bundle, so the commands are incomplete and not actually executable as packaged, fitting 'some concrete guidance but incomplete; missing key details' rather than the 'minor gaps' level above.	3 / 5
Workflow Clarity	A 5-step Workflow and a py_compile 'Quick Check' checkpoint plus an Error Handling fallback give a sequenced path, but the workflow is generic project-management boilerplate ('confirm objective', 'validate scope') rather than a validated computational pipeline with checkpoints on the actual calculation; it is not 4 because verification of computed output (e.g., achieved power, plausible N) is implicit or missing.	3 / 5
Progressive Disclosure	Header structure exists, but the body references four bundle files that are absent (scripts/main.py, references/, references/audit-reference.md, requirements.txt), so the signaled references are dead promises, and inline boilerplate (Security Checklist, Risk Assessment, Lifecycle) that belongs elsewhere is kept in SKILL.md; this matches 'minimal structure; content that clearly belongs in separate files is inlined' rather than 3, and is not 1 because it is not a monolithic wall of text.	2 / 5
	Total	10 / 20 Passed

Description

53%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 states a specific, well-scoped purpose but omits any explicit 'when to use' trigger guidance, capping completeness. Trigger terms are relevant but lack common synonyms like 'power analysis'. It is reasonably distinct from generic statistics skills.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when calculating sample size or power for survival, clustered, or multi-arm trials, or when sizing a non-inferiority study').

Include common synonyms a researcher would actually say, such as 'power analysis' and 'sample size calculation', alongside 'effect size' and 'minimum detectable effect'.

List a couple more concrete actions (e.g., 'compute required N, estimate achieved power, adjust for dropout') to raise specificity beyond a single 'calculations' verb.

Dimension	Reasoning	Score
Specificity	Names the domain ('sample size and power calculations') plus two concrete calculation actions and lists sub-designs (survival, clustered, multiple comparisons), but does not enumerate several distinct actions, fitting the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' level above.	3 / 5
Completeness	The description gives a clear 'what' but contains no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3; it is not 2 because the 'what' is specific, and not 4 because 'when' is entirely absent rather than merely weak.	3 / 5
Trigger Term Quality	It includes relevant natural terms ('sample size', 'power calculations', 'survival analysis', 'clustered designs', 'multiple comparisons'), but misses common phrasings a researcher would say such as 'power analysis', 'sample size calculation', and 'effect size', so it lands at 'some relevant keywords but missing common variations or synonyms' rather than good coverage.	3 / 5
Distinctiveness Conflict Risk	The 'Advanced ... complex study designs including survival analysis, clustered designs, and multiple comparisons' framing carves a mostly distinct niche with minor overlap risk against a more basic sample-size/power skill, matching 'mostly distinct; minor overlap risk with closely related skills' rather than the clear-niche/minimal-conflict level above.	4 / 5
	Total	13 / 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: 63c61d3

Reviewed: 5 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.