Loading...
Loading...
Found 231 Skills
Create optimized, secure multi-stage Dockerfiles for React applications (Vite, CRA, Next.js static). Use when (1) creating a new Dockerfile for a React project, (2) containerizing a React/Vite application, (3) optimizing an existing React Dockerfile, (4) setting up Docker for React with Nginx, or (5) user mentions React and Docker/container together.
Guidelines for organizing .NET projects, including solution structure, project references, folder conventions, .slnx format, centralized build properties, and central package management. Use when setting up a new .NET solution with modern best practices, configuring centralized build properties across multiple projects, implementing central package version management, or setting up SourceLink for debugging.
Linux server administration expert. Ubuntu/Debian, Nginx, Apache, SSL, firewall, systemd, server hardening. Use for server setup and config.
Train custom TTS voices for Piper (ONNX format) using fine-tuning or from-scratch approaches. Use when creating new synthetic voices, fine-tuning existing Piper checkpoints, preparing audio datasets for TTS training, or deploying voice models to devices like Raspberry Pi or Home Assistant. Covers dataset preparation, Whisper-based validation, training configuration, and ONNX export.
Expert blueprint for VR platforms (Meta Quest, PSVR, SteamVR, Pico) covering XR toolkit (OpenXR), comfort settings (vignetting, snap turning, teleport), motion controls, hand tracking, and 90+ FPS requirements. Use when targeting VR headsets or implementing immersive 3D experiences. Keywords VR, XR, OpenXR, Meta Quest, motion sickness, comfort, locomotion, XRController3D, foveated rendering.
Document undocumented public APIs in PyTorch by removing functions from coverage_ignore_functions and coverage_ignore_classes in docs/source/conf.py, running Sphinx coverage, and adding the appropriate autodoc directives to the correct .md or .rst doc files. Use when a user asks to remove functions from conf.py ignore lists.
Configures API gateways for routing, authentication, rate limiting, and request transformation in microservice architectures. Use when setting up Kong, Nginx, AWS API Gateway, or Traefik for centralized API management.
Configures nginx load balancing with upstream servers, health checks, and failover strategies. Use when setting up load balancing, distributing traffic across multiple servers, or configuring upstream backends.
Self-contained deploy automation — invoke directly, do not decompose. Deploys a Vibes app to exe.dev VM hosting. Uses nginx on persistent VMs with SSH automation. Supports client-side multi-tenancy via subdomain-based Fireproof database isolation.
Deployment & Operations Expert responsible for securely, rollbackable, and observably deploying builds that pass Reviewer and QA gates to servers (PM2 3-process cluster + Nginx reverse proxy + BT Panel). Adheres to engineering baselines including zero-downtime deployment, health checks, rollback within ≤3 minutes, and post-release smoke testing. Handles deployment orchestration, configuration management, traffic management, and monitoring & alerting. Applicable when receiving task cards from the Deploy department or needing to release to production.
Use this skill for project schedule management — tracking modules, milestones, and delivery phases stored in YAML. Invoke whenever the user asks about: project progress or delivery status, module status (planned/in_progress/done/deferred), weekly task breakdown, milestone countdowns, risk analysis, linking OpenSpec changes to modules, or syncing schedule data to Yunxiao. Triggers on: "planning", "schedule", "progress", "milestone", "what's this week", "what's left", "mark as done", "排期", "进度", "本周任务", "里程碑", "模块状态", "还剩多少". Do NOT trigger for: calendar reminders, weekly work reports, or Yunxiao tasks without schedule context.
Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation. Workflow 1 auto-discovers input shapes and parameters from user source code. Workflow 2 exports PyTorch models to ONNX. Workflow 3 converts ONNX to .om via ATC with multi-CANN version support. Workflow 4 adapts the user's full inference pipeline (preprocessing + model + postprocessing) to run end-to-end on NPU. Workflow 5 verifies precision between ONNX and OM outputs. Workflow 6 generates a reproducible README. Supports any standard PyTorch/ONNX model. Use when converting, testing, or deploying models on Ascend AI processors.