Menu
Use for Gemma 4 12B config, tokenizer, chat-template, prompt hashing, greedy parity, fixture creation, and reference comparison work.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Diagnose Gemma 4 MTP acceptance and speculative decoding behavior in Helios using real-context prompts, trace records, and exactness gates.
Profile and optimize Helios native MLX/C++ execution paths with A/B evidence, memory gates, and feature-flagged experimental kernels.
Build and run Helios real-context A/B benchmarks with deterministic workload manifests, correctness gates, and decision artifacts.
Use for tiny16 MacBook profiling: memory pressure, context-length limits, TTFT/decode metrics, cache effectiveness, MTP acceptance, and release-gate benchmark reports.
Use for dynamic LoRA/QLoRA adapter import, validation, loading, routing, adapter-aware KV cache keys, aLoRA planning, and adapter memory residency.
Use for Gemma4D KV cache, prefix cache, SSD cold tier, cache manifests, cache-key correctness, quantized/compressed KV experiments, and restore parity.
| name | gemma4d-model-correctness |
| description | Use for Gemma 4 12B config, tokenizer, chat-template, prompt hashing, greedy parity, fixture creation, and reference comparison work. |
Use for tokenizer/config/chat-template/logit parity and fixture work.
