Quantizing Models Bitsandbytes

Design, plan, and analyze A/B tests with statistical rigor. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, sample size calculation, test duration, multivariate testing, or conversion experiments. Trigger phrases include "A/B test", "split test", "experiment", "statistical significance", "sample size", "test duration", "which version wins", "conversion experiment", "hypothesis test", "variant testing".

Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.

Provides brand naming frameworks, evaluation criteria, and templates for startup naming work. Auto-activates during brand name development, name evaluation, domain checking, and trademark research. Use when discussing brand name, company name, product name, naming strategy, SMILE SCRATCH framework, domain availability, trademark, name evaluation, sound symbolism, or naming matrix.

Growth skills for indie Apple developers — user acquisition, analytics interpretation, press/media outreach, community building, and indie business operations. Also covers the stage-by-stage store-growth audit and the post-launch store-signals loop. Use when user asks about growing their app, auditing growth levers, understanding metrics, getting press coverage, or running an indie dev business.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory M_I (feasible/unsuccessful directions) and Experimentation Memory M_E (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after research-ideation), IVE (after experiment failure — classifies failures as implementation vs fundamental), ESE (after experiment success — extracts reusable strategies). Use when: updating memory after completing research-ideation cycles or experiment pipelines, classifying why a method failed (implementation vs fundamental failure), starting a new research cycle needing prior knowledge, user mentions 'update memory', 'classify failure', 'what worked before', 'research history', 'evolution'. Do NOT use for running experiments (use experiment-pipeline), debugging experiment code (use experiment-craft), or generating ideas (use research-ideation).