mohitagw15856
f3b9d008fe
New skills added: - teaching-lesson-plan: structured lesson plans for any subject/audience/setting - seo-content-brief: complete SEO briefs with intent, competitor gaps, and outline - media-pitch: story-first journalist pitches with angle development framework - change-management-plan: stakeholder analysis, comms strategy, adoption metrics - workshop-facilitation-guide: activity instructions, decision protocols, facilitator moves - sales-forecasting-model: pipeline model, scenario analysis, assumption log - tax-planning-checklist: year-end tax planning across income, pension, CGT, reliefs Quality improvements across all 93 existing skills: - Standardised description format: "Verb the thing. Use when X. Produces Y." - Added Required Inputs section to all skills missing it (prompts for missing info) - Added Quality Checks section to all skills missing it (specific, not generic) - Fixed broken multiline YAML descriptions - Removed non-standard frontmatter keys (tool_integration, metadata blocks) README updated to v6.0.0 with 100-skill count, new skill tables, and article series Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
3.2 KiB
3.2 KiB
name, description
| name | description |
|---|---|
| experiment-designer | Design statistically rigorous A/B tests and interpret experiment results. Use when asked to design an experiment, run an A/B test, calculate sample size, interpret test results, or assess whether an experiment was successful. Produces a complete experiment design with hypothesis, sample size, run time, success criteria, and risk flags — or a results interpretation with ship/iterate/kill recommendation. |
Experiment Designer Skill
Produce rigorous experiment designs from product hypotheses, and interpret results with statistical and practical significance — so you can defend every decision to a sceptical engineering lead or data scientist.
Required Inputs
Ask the user for these if not provided: For experiment design:
- Hypothesis (what change, what metric, what expected movement)
- Current baseline metric value
- Minimum detectable effect (MDE) — the smallest lift worth caring about
- Available daily sample size
For results interpretation:
- Control and variant results (raw numbers or percentages)
- P-value or confidence interval
- Run duration (days)
- Any anomalies observed during the test
Two-Phase Process
Phase 1: Experiment Design
- Restate hypothesis as: "If we [change], we expect [metric] to [move by X%] because [reason]"
- Define control and variant clearly
- Select primary metric (one only) and secondary guardrail metrics (2-3 max)
- Calculate required sample size from MDE and baseline
- Estimate run time in days
- Set pre-defined success criteria before the test runs — no moving goalposts
- Flag design risks: novelty effects, seasonal confounds, multiple testing issues, network effects, sample ratio mismatch
Phase 2: Results Interpretation
- Assess statistical significance (p < 0.05 threshold)
- Assess practical significance: was the lift meaningful for the business, not just real?
- Interpret confidence intervals
- Investigate confounding factors
- Recommend: Ship / Iterate / Kill / Run follow-up test
- Validate — Confirm the test ran for the full planned duration. Flag if it was stopped early (peeking problem). Confirm sample ratio mismatch did not occur.
Output Structure
[Design or Results header based on phase]
Hypothesis: "If we [change], we expect [metric] to [move by X%] because [reason]"
Primary metric: [One metric only] Guardrail metrics: [2-3 max] Required sample size: [n per variant] Estimated run time: [days] Pre-defined success threshold: [specific number] Design risk flags: [any concerns]
Results (Phase 2 only): Statistical significance: [p-value and conclusion] Practical significance: [lift size vs. business threshold] Recommendation: Ship / Iterate / Kill / Follow-up — [rationale]
Quality Checks
- Hypothesis specifies the change, the metric, the direction, and the reason
- Primary metric is singular — guardrail metrics are secondary
- Success criteria are defined before the test launches (not after seeing results)
- Test was not stopped early (or flagged clearly if it was)
- Practical significance assessed separately from statistical significance
- Sample ratio mismatch is checked in results interpretation