prompt-testing
A/B testing and performance metrics for prompts
npx skills add majiayu000/claude-skill-registry --skill prompt-testing --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Prompt Testing Skill for testing, comparing, and measuring prompt performance. ## Documentation - [metrics.md](docs/metrics.md) - Performance metrics definition - [methodology.md](docs/methodology.md) - A/B testing protocol ## Testing Workflow ```text 1. DEFINE └── Test objective └── Metrics to measure └── Success criteria 2. PREPARE └── Variants A and B └── Test dataset └── Baseline (if existing) 3. EXECUTE └── Run on dataset └── Collect results └── Document observations 4. ANALYZE └── Calculate metrics └── Compare variants └── Identify patterns 5. DECIDE └── Recommendation └── Statistical confidence └── Next iterations ``` ## Performance Metrics ### Quality | Metric | Description | Calculation | |--------|-------------|-------------| | **Accuracy** | Correct responses | Correct / Total | | **Compliance** | Format adherence | Compliant / Total | | **Consistency** | Response stability | 1 - Variance | | **Relevance** | Meeting the need | Average score (1-5) | ### Efficiency | Metric | Description | Calculation | |--------|-------------|-------------| | **Tokens Input** | Prompt size | Token count | | **Tokens Output** | Response size | Token count | | **Latency** | Response time
- Documentation
- Testing Workflow
- Performance Metrics
- Quality
- Efficiency
- Robustness
- Test Format
- Test Dataset
- Test Report
- Commands
- Decision Criteria
- When to adopt variant B?
- Best Practices
Create a test Run an A/B test View results Compare two tests
What does the prompt-testing skill do?
A/B testing and performance metrics for prompts
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill prompt-testing --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.