菜单
Build the speech-swift package (release or debug). Use when preparing for testing, benchmarking, or running demos.
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。
Run tests. Use after code changes to validate. Arguments: unit (default, no GPU), e2e (with models), filter name, or all.
Review a pull request for conceptual fit, architecture impact, adversarial failure modes, security risk, docs impact, regression risk, test coverage, and merge readiness. Use when asked to review a PR, check whether a PR is safe to merge, decide if more tests are needed, perform adversarial or security review, or summarize PR risk.
Run performance + quality benchmarks. ASR reports WER, RTF, peak RSS, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.
基于 SOC 职业分类
| name | build |
| description | Build the speech-swift package (release or debug). Use when preparing for testing, benchmarking, or running demos. |
| disable-model-invocation | false |
| argument-hint | ["release|debug"] |
| allowed-tools | Bash |
Build the package in the specified configuration. Default: release.
config="${ARGUMENTS:-release}"
if [ "$config" = "debug" ]; then
make debug
else
make build
fi
The metallib step compiles MLX Metal shaders. Without it, inference runs ~5x slower due to JIT compilation. make build handles this automatically.