菜单
Build and run Helios real-context A/B benchmarks with deterministic workload manifests, correctness gates, and decision artifacts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
Use to execute one Gemma4D milestone end-to-end with scoped tasks, verification commands, evidence capture, and blocker reporting. Trigger on milestone implementation, Codex Goals, task planning, or release gates.
| name | helios-real-workload-ab |
| description | Build and run Helios real-context A/B benchmarks with deterministic workload manifests, correctness gates, and decision artifacts. |
Use this skill when a task mentions Helios performance, A/B benchmarking, real workloads, benchmark corpus, repeated-prefix testing, or tiny16 performance decisions.
BENCHMARKS.md, docs/xr-real-workload-methodology.md, and docs/xr-ab-methodology.md.records.jsonl, summary.json, report.md, blockers.md, and decision.md for every Goal.Use exactly one:
accept_candidatereject_candidatekeep_experimentalneeds_more_datablocked_with_evidence