openmoss
- 19 skills
- 0 followers
- 14 hours ago last updated
- ▌ Generate Profile · openmossGenerate an e2e profiling trace of an SGLang server run. Launches a server, validates accuracy, captures a Chrome-compatible trace, and returns the profile path.
- ▌ Sglang Auto Benchmark · openmoss bundleRun SGLang auto benchmark searches with tiered server-flag sweeps, canonical dataset preparation, ShareGPT auto-download, custom-data conversion/validation, SLA or fixed-QPS benchmarking, CSV export, and optional second-stage speculative/EAGLE tuning. Use when the user wants an AI-operated benchmark workflow rather than a one-off bench_serving command.
- ▌ Sglang Torch Profiler Analysis · openmoss bundleCompact SGLang torch-profiler triage skill. Use when Codex should inspect an existing `trace.json(.gz)` or profile directory, trigger `sglang.profiler` against a live server, and return one compact report with kernel, overlap-opportunity, and fuse-pattern tables. Single-trace triage is enough for quick diagnosis; mapping+formal two-trace triage gives stronger overlap conclusions.
- ▌ Freeride · openmoss bundleManages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
- ▌ API Gateway · openmoss bundleConnect to 100+ APIs (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to interact with external services. Security: The MATON_API_KEY authenticates with Maton.ai but grants NO access to third-party services by itself. Each service requires explicit OAuth authorization by the user through Maton's connect flow. Access is strictly scoped to connections the user has authorized. Provided by Maton (https://maton.ai).
- ▌ Moss Tts Voice · openmoss bundleMOSS-TTS 语音合成与音色克隆工具。生成适合各渠道的音频文件。 触发场景： - 用户要求生成语音、TTS - 用户提到"用我的声音"、"克隆声音"、"MOSS语音" - 需要生成语音文件用于发送 功能：文本转语音、实时克隆、预注册音色、多格式输出
- ▌ Add Jit Kernel · openmossStep-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jit_kernel module
- ▌ Add Sgl Kernel · openmossStep-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)
- ▌ Write Sglang Test · openmossGuide for writing SGLang CI/UT tests following project conventions. Covers CustomTestCase, CI registration, server fixtures, model selection, and test placement. Use when creating new tests, adding CI test cases, writing unit tests, or when the user asks to add tests for SGLang features.
- ▌
- ▌ Diffusion Perf · openmossMeasure and compare sglang-diffusion performance. Use when benchmarking a model, comparing before/after performance, or generating a perf report for a PR.
- ▌
- ▌ CI Workflow Guide · openmossGuide to SGLang CI workflow orchestration — stage ordering, fast-fail, gating, partitioning, execution modes, and debugging CI failures. Use when modifying CI workflows, adding stages, debugging CI pipeline issues, or understanding how tests are dispatched and gated across stages.
- ▌ Sglang Diffusion Add Model · openmoss bundleUse when adding a new diffusion model or Diffusers pipeline to SGLang.
- ▌ Sglang Diffusion Performance · openmossUse when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.
- ▌ Sglang Diffusion Ako4all Kernel · openmoss bundleUse when optimizing an existing SGLang diffusion kernel with AKO4ALL, including AKO4ALL repo hygiene, custom microbench setup, ncu-guided iteration, and end-to-end denoise validation. Also use when a sibling AKO4ALL repo must be cloned or refreshed before starting kernel tuning work.
- ▌ Sglang Diffusion Modelopt Quant · openmossUse when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.
- ▌ Sglang Diffusion Benchmark Profile · openmoss bundleUse when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
- ▌ Imclaw · openmoss bundleIMClaw 跨网通信能力 — 让 AI Agent 具备实时聊天能力。用于：(1) Agent 需要与其他 Agent 实时通信，(2) 管理群聊，(3) 订阅和接收群聊消息，(4) 构建聊天机器人或协作 Agent。触发词：imclaw、跨网通信、agent 聊天、群聊、实时消息、龙虾。