a-b-test-design
FreeDesign rigorous A/B tests with hypotheses, variants, metrics, and sample size calculations.
The English summary is being prepared. Showing the original description.
Find opportunities to add metrics and estimate numbers when exact data unavailable
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Use this skill when the user:
The Problem:
Studies Show:
1. Money
2. Time
3. Percentages
4. Volume/Scale
5. Quality
6. Frequency
For any experience, ask:
Scale Questions:
Impact Questions:
Comparison Questions:
Sales:
Marketing:
Customer Service:
Operations:
Engineering:
Project Management:
HR/Admin:
When you don't have exact numbers:
Principle: Estimate low to maintain credibility
Example:
Format: "X-Y" or "X to Y"
Examples:
Format: "X+" or "at least X"
Examples:
Format: Calculate from known totals
Example:
Format: Work backwards from frequency
Example:
"Improved [X] from [before number] to [after number], resulting in [Y]% improvement"
Example:
"Improved page load time from 8 seconds to 2 seconds, resulting in 75% reduction and 20% increase in user engagement"
"[Verb] [number] [things], resulting in [impact]"
Example:
"Managed 25 concurrent projects worth $3M, delivering 95% on-time with zero budget overruns"
"Processed [number] [items] per [time period], achieving [quality metric]"
Example:
"Resolved 50+ customer tickets daily, maintaining 98% satisfaction rating and 4-hour average response time"
"Ranked #[X] out of [Y] in [metric], [context]"
Example:
"Ranked #2 out of 45 sales representatives nationally, generating $3.2M in annual revenue"
Solution: Focus on YOUR contribution
Example:
Solution: Quantify activities and inputs
Example:
Solution: Measure the work itself
Example:
Solution: Use percentages or ranges
Example:
Solution: Quantify learning, throughput, accuracy
Example:
When quantifying a resume:
# RESUME QUANTIFICATION
## Analysis Summary
**Bullets without numbers:** X
**Bullets with numbers:** Y
**Target:** 100% of bullets should have at least one metric
## Quantified Bullets
### Original Bullet #1:
"Managed customer accounts"
### Questions to Find Metrics:
- How many accounts? → [User answer: ~40]
- What was the revenue? → [User answer: ~$2M]
- What results did you achieve? → [User answer: retained most]
### Quantified Version:
"Managed portfolio of 40 enterprise accounts representing $2M ARR, achieving 95% retention rate"
### Metrics Added:
- Account count: 40
- Revenue: $2M ARR
- Retention: 95%
---
### Original Bullet #2:
[Continue for each bullet]
## Estimation Notes
- [Metric]: Estimated based on [reasoning]
- [Metric]: Conservative estimate using [method]
## Remaining Questions
- [Questions to ask user for missing information]
For each bullet:
Every bullet can be quantified. If you think your work can't be measured, you haven't asked the right questions yet.
The goal isn't to have impressive numbers—it's to have SPECIFIC numbers that show the scope and impact of your work.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design rigorous A/B tests with hypotheses, variants, metrics, and sample size calculations.
The English summary is being prepared. Showing the original description.
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," or "experiment playbook." Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics. For page-level conversion optimization, see cro.
The English summary is being prepared. Showing the original description.
Format CVs for academic positions with publications, grants, and teaching
The English summary is being prepared. Showing the original description.
Conduct a comprehensive accessibility audit against WCAG guidelines with severity ratings and remediation steps.
The English summary is being prepared. Showing the original description.
Create accessibility testing plans covering assistive technologies and WCAG criteria.
The English summary is being prepared. Showing the original description.
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative testing,' 'ad performance optimization,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' or 'I need more ad variations.' Use this whenever someone needs to produce ad copy at scale or iterate on existing ads. For campaign strategy and targeting, see ads. For landing page copy, see copywriting.
The English summary is being prepared. Showing the original description.