sample-size-basic

Basic sample size estimator for clinical research planning. Computes per-group and total N for two-sample/paired t-tests, chi-square tests, and proportion comparisons, reporting alpha, power, effect size, and statistical assumptions summary for grant proposals and preliminary ...

Quality

66%

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/sample-size-basic/SKILL.md

Quality

Content

58%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 has a strong, well-validated workflow and clean reference structure, but it is padded with generic boilerplate and lacks an executable command demonstrating an actual sample-size calculation.

Suggestions

Remove the generic Evaluation Criteria, Test Cases, Lifecycle Status, Risk Assessment, and Security Checklist sections (or move them to a reference file) — they add tokens without skill-specific guidance.

Add a concrete invocation example, e.g. `python scripts/main.py --test_type t_test --alpha 0.05 --power 0.80 --effect_size 0.5`, so the primary action is copy-paste executable.

Move the time-sensitive 'Next Review Date' out of the main body or into a deprecated/maintenance section so it does not penalize conciseness.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: generic boilerplate sections (Evaluation Criteria/Success Metrics, Test Cases, Lifecycle Status with a time-sensitive 'Next Review Date', Risk Assessment table, Security Checklist) pad the body without adding skill-specific value Claude does not already know.	2 / 5
Actionability	Concrete validation commands, named parameters, return values, and a worked example are present, but the actual invocation that performs a sample-size calculation is never shown — only `py_compile` and `--help` — leaving a key execution detail missing.	3 / 5
Workflow Clarity	A clear 7-step sequence with explicit validation ('Verify alpha in (0,1)... If invalid, report exact error and stop'), a confirmation checkpoint (step 4), and a fallback that presents options and asks the user to clarify (step 7).	5 / 5
Progressive Disclosure	Good structure with a real, clearly signaled one-level-deep reference (references/audit-reference.md) and a referenced scripts/main.py; minor organization gaps from inlined generic sections that clutter the overview.	4 / 5
	Total	14 / 20 Passed

Description

75%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 is specific and distinct, clearly conveying what the skill computes, but it lacks an explicit 'Use when...' trigger clause and a few natural user phrases, which limits trigger-term quality and completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user says "sample size", "power analysis", "how many subjects", or "n per group" for t-test, chi-square, or proportion studies.'

Include natural synonyms users actually say ('power analysis', 'how many subjects', 'n per group') alongside the technical terms.

Complete the truncated closing ('... for grant proposals and preliminary ...') so the 'when' context is not cut off.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Computes per-group and total N for two-sample/paired t-tests, chi-square tests, and proportion comparisons, reporting alpha, power, effect size, and statistical assumptions summary' — with comprehensive coverage of what the skill does.	5 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause — the only 'when' signal is the weakly implied 'for grant proposals and preliminary ...', so completeness is capped at 3 per the missing-trigger guideline.	3 / 5
Trigger Term Quality	Good keyword coverage including 'sample size', 't-tests', 'chi-square', 'proportion', 'alpha', 'power', and 'grant proposals', but missing common natural variations users say such as 'power analysis', 'how many subjects', or 'n per group'.	4 / 5
Distinctiveness Conflict Risk	A clear niche — clinical research sample-size estimation for specific test families — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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/sample-size-basic/SKILL.md
Commit: 63c61d3

Reviewed: 7 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.