sample-size-power-calculator

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

Quality

50%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/sample-size-power-calculator/SKILL.md

Quality

Content

27%

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

The body is dominated by generic, skill-agnostic template filler with verbatim description repetition and dangling references to unbundled files. The few concrete elements (parameter table, usage commands) are undermined by the missing scripts/main.py and references bundle.

Suggestions

Strip the generic boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, Response Template, Evaluation Criteria) that adds no skill-specific value, and stop repeating the description verbatim.

Either bundle scripts/main.py and references/audit-reference.md so the referenced commands and links resolve, or remove the dangling references.

Replace the abstract Workflow steps with a concrete, calculation-specific sequence that validates inputs (effect size, alpha, power) and shows how to interpret/verify the produced sample size and power curve.

Dimension	Reasoning	Score
Conciseness	The ~210-line body is padded with generic template boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, Response Template) and repeats the description verbatim in "When to Use" and "Key Features" rather than adding skill-specific knowledge.	1 / 3
Actionability	It provides concrete commands (py_compile, --help), a parameter table, and copy-paste usage examples, but the primary surface scripts/main.py is referenced yet not bundled, so the guidance is incomplete.	2 / 3
Workflow Clarity	A 5-step workflow with a py_compile validation checkpoint and a fallback path is present, but the checkpoints are generic and lack a feedback loop tied to the actual calculation outputs.	2 / 3
Progressive Disclosure	All content sits in a single monolithic file, and the one signaled reference (references/audit-reference.md) does not exist — no references/, scripts/, or assets/ bundle directories are present — so navigation is broken.	1 / 3
	Total	6 / 12 Passed

Description

72%

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 is domain-specific and rich in natural trigger terms, but it omits an explicit "when to use" clause, leaving the completeness dimension capped. It is distinctive within a clear niche.

Suggestions

Append an explicit trigger clause, e.g. "Use when planning study sample size or power for survival, clustered, or multi-arm designs with multiple comparisons."

Add concrete actions to raise specificity, e.g. "compute required N, generate power curves, and adjust for dropout and multiple comparisons."

Consider adding the common phrasing "power analysis" alongside "power calculations" to match more natural user requests.

Dimension	Reasoning	Score
Specificity	It names the domain ("sample size and power calculations") and several design contexts (survival analysis, clustered designs, multiple comparisons), but does not enumerate multiple distinct concrete actions like computing N, generating power curves, or dropout adjustment.	2 / 3
Completeness	It clearly states what the skill does but lacks any "Use when…" clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	"sample size", "power calculations", "survival analysis", "clustered designs", and "multiple comparisons" are natural phrases a researcher would actually say when requesting this work.	3 / 3
Distinctiveness Conflict Risk	The biostatistical study-design niche (sample size/power for survival, clustered, multiple-comparison designs) is specific and unlikely to trigger competing skills.	3 / 3
	Total	10 / 12 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
Commit: 7cc5680

Reviewed: 3 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.