ab-test-setup
tessl i github:sickn33/antigravity-awesome-skills --skill ab-test-setupStructured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.
Validation
69%| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_examples | No examples detected (no code fences and no 'Example' wording) | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 11 / 16 Passed | |
Implementation
63%This skill excels at workflow clarity with explicit gates and validation checkpoints that prevent common A/B testing mistakes. However, it lacks concrete examples (sample hypothesis, actual sample size calculation formula) and could be more concise by removing philosophical statements. The procedural guidance is strong but would benefit from executable templates.
Suggestions
Add a concrete example hypothesis that demonstrates all required components (observation, change, direction, audience, success criteria)
Include the actual sample size calculation formula or a specific tool/calculator reference rather than just listing the inputs needed
Remove or condense philosophical statements like 'A/B testing is not about proving ideas right' and 'Final Reminder' section to improve token efficiency
Consider splitting metrics definition and analysis sections into separate reference files given the document length
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary philosophical statements ('A/B testing is not about proving ideas right') and repetitive emphasis. The checklists are useful but some sections could be tightened. | 2 / 3 |
Actionability | Provides clear checklists and decision criteria, but lacks concrete examples of hypotheses, sample size calculations, or specific tool commands. The guidance is procedural but not executable—no formulas, code, or copy-paste ready templates. | 2 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit hard gates ('Do NOT proceed until confirmed'), clear sequencing from hypothesis through execution, and validation checkpoints at each stage. The execution readiness gate is a strong feedback loop. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and headers, but everything is in a single file. For a skill of this length (~200 lines), some content like the metrics definition or analysis discipline could be split into referenced files. | 2 / 3 |
Total | 9 / 12 Passed |
Activation
33%The description identifies a clear domain (A/B testing) and hints at a structured workflow with mandatory checkpoints, which is useful. However, it lacks explicit trigger guidance ('Use when...'), misses common synonym terms users might say, and doesn't enumerate specific concrete actions the skill performs.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to design an A/B test, set up an experiment, or needs help with split testing methodology'
Include natural keyword variations such as 'split test', 'experiment design', 'variant testing', 'conversion optimization'
List more specific concrete actions like 'define hypotheses, select success metrics, calculate sample sizes, document test parameters'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (A/B tests) and mentions some actions (setting up, gates for hypothesis, metrics, execution readiness), but doesn't list comprehensive concrete actions like 'define control groups', 'calculate sample sizes', or 'analyze results'. | 2 / 3 |
Completeness | Describes what it does (structured guide for A/B test setup with gates) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'A/B tests' which is a natural term users would say, but misses common variations like 'split testing', 'experiment', 'variant testing', 'conversion testing', or 'experimentation'. | 2 / 3 |
Distinctiveness Conflict Risk | The A/B testing focus provides some distinctiveness, but 'hypothesis' and 'metrics' are generic terms that could overlap with general experiment design, data analysis, or product management skills. | 2 / 3 |
Total | 7 / 12 Passed |
Reviewed
Table of Contents
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.