Loading...
Loading...
Found 78 Skills
Use when "statistical modeling", "A/B testing", "experiment design", "causal inference", "predictive modeling", or asking about "hypothesis testing", "feature engineering", "data analysis", "pandas", "scikit-learn"
Use this skill when you need to test or evaluate LangGraph/LangChain agents: writing unit or integration tests, generating test scaffolds, mocking LLM/tool behavior, running trajectory evaluation (match or LLM-as-judge), running LangSmith dataset evaluations, and comparing two agent versions with A/B-style offline analysis. Use it for Python and JavaScript/TypeScript workflows, evaluator design, experiment setup, regression gates, and debugging flaky/incorrect evaluation results.
This skill should be used when the user asks to review, proofread, check, or evaluate content. It provides comprehensive text review (grammar, logic, compliance) and version evaluation (A/B testing, comparison analysis). Text review automatically adds AI disclaimer at the end.
When the user wants to optimize a signup or registration flow -- including field selection, social auth, single-step vs multi-step forms, or mobile signup. Also use when the user says "signup conversion," "registration form," "reduce signup friction," "signup A/B test," or "signup drop-off." For post-signup onboarding, see product-onboarding. For activation measurement, see activation-metrics.
Optimize landing pages for maximum conversions using proven frameworks from Unbounce and Oli Gardner—apply the "one goal, one message, one action" principle with data-driven design, copy, and CTA best practices. Use when: **Create a new landing page** for a campaign; **Optimize an existing landing page** that isn't converting; **Review landing page design** before launch; **Improve form conversion rates** on lead gen pages; **A/B test landing page elements** systematically
Statistical analysis: t-tests, chi-squared, Mann-Whitney, p-values, CIs, Bonferroni/BH, Bayesian A/B