Name: experiment-designer
Rating: 65.60000000000001 (1 reviews)
Author: alirezarezvani

experiment-designer

Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical statistical rigor.

Quality

79%

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 ./.gemini/skills/experiment-designer/SKILL.md

The canonical home for this skill is experiment-designer in alirezarezvani/claude-skills

Quality

Content

75%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 well-structured, mostly lean skill body with an executable sample-size command and a clear sequenced workflow. The main gaps are missing validation checkpoints in the flow and referenced bundle files that are absent from the skill bundle.

Suggestions

Add the missing bundle files (references/experiment-playbook.md, references/statistics-reference.md, scripts/sample_size_calculator.py) or remove the references, since dangling links break navigation.

Insert explicit validation checkpoints between workflow steps, e.g., 'Before sizing: confirm the hypothesis passes the Hypothesis Quality Checklist.'

Tighten the 'Statistical Interpretation Guardrails' section by pruning statements that restate standard statistical knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized with bullet points and no basic-concept padding, but the 'Statistical Interpretation Guardrails' section restates some truisms Claude already knows (e.g., 'p-value < alpha indicates evidence against null'), keeping it just below a 5.	4 / 5
Actionability	Provides a copy-paste-ready command with full flags ('python3 scripts/sample_size_calculator.py --baseline-rate 0.10 --mde 0.015 ...') and a concrete ICE formula, but the hypothesis, metrics, and prioritization steps lack worked examples, leaving minor gaps.	4 / 5
Workflow Clarity	A clearly sequenced 6-step workflow (hypothesize → metrics → sample size → prioritize → launch → interpret) is present with a supporting Hypothesis Quality Checklist, but no explicit validation checkpoints are woven between steps (e.g., 'verify hypothesis passes the checklist before sizing'), so it does not reach 5.	4 / 5
Progressive Disclosure	Structure is good with a clearly signaled one-level-deep 'See:' section pointing to references/experiment-playbook.md, references/statistics-reference.md, and scripts/sample_size_calculator.py, but those bundle files do not actually exist in the skill, creating a navigation gap that prevents a 5.	4 / 5
	Total	16 / 20 Passed

Description

83%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.

A strong, concrete description with an explicit 'Use when' trigger and a distinct experimentation niche. Its only weakness is that the capability statement ('what') is folded into the trigger list rather than declared separately.

Suggestions

Lead with a short declarative capability sentence (e.g., 'Design, prioritize, and evaluate product experiments with statistical rigor.') before the 'Use when' clause to cleanly separate 'what' from 'when'.

Add a few more natural trigger synonyms such as 'experiment results', 'conversion rate optimization', or 'power analysis' to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists five concrete actions — 'planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes' — giving comprehensive coverage of the experimentation lifecycle, matching the score-5 anchor.	5 / 5
Completeness	Has an explicit 'Use when...' trigger with concrete phrases, but the 'what' is only conveyed through the trigger action list rather than a standalone declarative capability statement, so it falls between the 4 and 5 anchors.	4 / 5
Trigger Term Quality	Includes natural terms users would say ('A/B outcomes', 'sample size', 'hypotheses', 'prioritizing tests') with the synonym 'A/B', but omits common variants like 'experiment results', 'conversion rate', or 'power analysis', placing it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — product experimentation with A/B testing, sample sizing, and statistical rigor — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/experiment-designer/SKILL.md
Commit: 19392f7

Reviewed: ~3 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.