ab-test-setup

Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.

Quality

60%

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 ./skills/ab-test-setup/SKILL.md

Quality

Content

66%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 skill is an exceptionally well-sequenced, gate-driven workflow with strong validation checkpoints, but loses points on conciseness (motivational/boilerplate filler) and actionability (the statistical sample-size computation is specified as a requirement but not as executable how-to guidance).

Suggestions

Provide a concrete method for the sample-size step — a formula, a named calculator/tool, or a code snippet — since 'Estimate required sample size per variant' is currently a requirement with no executable guidance.

Remove or tighten the 'Final Reminder' motivational section and the generic 'When to Use'/'Limitations' boilerplate to reclaim token budget without losing signal.

De-duplicate 'Key Principles (Non-Negotiable)' against the earlier gates, or fold it into the relevant gate sections to avoid restating 'one hypothesis', 'one primary metric', and 'no peeking' twice.

Dimension	Reasoning	Score
Conciseness	Mostly lean bullet checklists that assume Claude knows MDE/statistical power/guardrails, but the 'Key Principles' section repeats earlier gates, the 'Final Reminder' is motivational filler, and 'When to Use'/'Limitations' are generic boilerplate that could be trimmed.	3 / 5
Actionability	Tracking verification gives concrete thresholds ('30 seconds', '5+ events per variant', '±5%', 'first 100 records') and gates/refusal conditions are explicit, but the core sample-size step only lists what to define with no formula, tool, or command for how to compute it — a key missing detail.	3 / 5
Workflow Clarity	A strongly sequenced numbered workflow (1-8) with explicit hard gates, validation checkpoints (assumptions check, tracking verification before Gate 8), and feedback loops ('if any fails, stop and resolve before Gate 8'), matching the anchor for clear sequence with explicit validation and checklists.	5 / 5
Progressive Disclosure	No bundle files exist and the ~250-line file is monolithic (so the under-50-line exception does not apply), but it is well organized with numbered headers and logical flow, with little content that genuinely belongs in separate files; minor organization gaps keep it below 5.	4 / 5
	Total	15 / 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 clearly states the skill's purpose and names a distinct niche, but lacks a 'when to use' clause and broad trigger-term coverage, which cap completeness and trigger quality at the midpoint.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when designing, planning, or reviewing A/B tests, experiments, or split tests before launch.'

Broaden trigger terms with synonyms users actually say — 'experiments', 'split tests', 'experimentation', 'control and treatment' — alongside 'A/B tests'.

Reframe 'guide for setting up' into concrete actions to lift specificity, e.g. 'Designs A/B tests, locks hypotheses, defines metrics, and verifies execution readiness before launch.'

Dimension	Reasoning	Score
Specificity	Names the domain ('setting up A/B tests') and three gate components (hypothesis, metrics, execution readiness), but frames them as a 'guide for setting up' rather than enumerating concrete distinct actions like the anchor-4 example, so it sits at domain + 1-2 concrete actions.	3 / 5
Completeness	The 'what' is clear (A/B test setup with mandatory gates), but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines this caps completeness at 3.	3 / 5
Trigger Term Quality	'A/B tests' is a natural term users would say, but common synonyms and variations ('experiments', 'split tests', 'experimentation', 'control/treatment') are absent, leaving keyword coverage incomplete.	3 / 5
Distinctiveness Conflict Risk	'A/B test setup with mandatory gates' carves a clear niche with only minor overlap risk against general experimentation or analytics skills; not a 5 because no unmistakable explicit trigger phrase distinguishes it.	4 / 5
	Total	13 / 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: sickn33/antigravity-awesome-skills
Path: skills/ab-test-setup/SKILL.md
Commit: 1f67c44

Reviewed: about 16 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.