statistical-power

Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers closed-form power for t-tests, ANOVA, proportions, correlations, chi-square, and regression, plus simulation-based (Monte Carlo) power for designs with no formula — logistic/Poisson regression, mixed models, cluster-randomized trials, survival, and interactions. Use this skill even when the request only mentions an effect size, alpha, or "80% power" without saying "power analysis" explicitly. For laying out the study (randomization, blocking, factorial/DOE, crossover, sequential designs) use experimental-design; for analyzing data already collected and reporting it use statistical-analysis.

Quality

94%

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

Quality

Content

88%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.

A high-quality, well-structured skill body that balances executable recipes with a clear workflow and appropriately offloads detail to genuine bundle files. It is slightly more discursive than strictly necessary in the overview and pitfalls sections, but every section earns its place.

Suggestions

Tighten the Overview and 'Common pitfalls' sections — the conceptual framing about under/overpowered studies restates knowledge Claude already has and could be cut to save tokens.

The 'Adjustments people forget' section mixes guidance with formulas; moving the formula derivations (DEFF, n_enroll) into the references and keeping only the commands inline would improve conciseness.

Consider a one-line 'Verify before reporting' checkpoint in the Workflow that points to the Monte Carlo CI / sensitivity range as the acceptance criterion, making the existing feedback loop explicit.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (skips explaining what a t-test is), but the Overview and several prose passages around effect-size philosophy and pitfalls are somewhat discursive and could be trimmed without losing actionability.	4 / 5
Actionability	Provides copy-paste-ready, executable code for both closed-form (`scripts/power.py`) and simulation (`scripts/simulate_power.py`) paths, with concrete worked examples covering the common cases and an explicit reporting template.	5 / 5
Workflow Clarity	The numbered Workflow section sequences every step from stating the design through sensitivity analysis and adjustments, and the simulation recipe includes explicit validation feedback (report Monte Carlo CI, re-search for target n), giving clear checkpoints and error-recovery guidance.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview with one-level-deep, clearly signaled references to real files (`references/closed_form_recipes.md`, `references/simulation_based_power.md`, `references/effect_sizes.md`) and scripts (`scripts/power.py`, `scripts/simulate_power.py`), all of which exist in the bundle; navigation is easy.	5 / 5
	Total	19 / 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.

An exemplar description: third-person, concrete, comprehensive, and rich with natural trigger phrases, while explicitly delineating its boundary against related skills. The only minor weakness is length, but it earns every token.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'sample-size and statistical power calculations', 'a priori power analysis, a minimum detectable effect (MDE), a power curve', and both closed-form and Monte Carlo approaches — covering the domain comprehensively.	5 / 5
Completeness	Explicitly answers both what it does (sample-size and power calculations across named test families and simulation) and when to use it via repeated 'Use whenever...'/'Use this skill even when...' trigger clauses with concrete phrases.	5 / 5
Trigger Term Quality	Captures natural phrases users say ('how many subjects/samples/replicates do I need', '80% power', 'effect size', 'alpha') plus the concrete settings (grant, IRB protocol, pre-registration), giving broad keyword coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche and explicitly routes away from siblings ('for laying out the study ... use experimental-design; for analyzing data already collected ... use statistical-analysis'), minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/statistical-power/SKILL.md
Commit: b2a92ba

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.