self-contained-python-script
Write self-installing self-contained Python scripts using uv and PEP 723
alibabacloud-cms-alert-rule-create
Create Alibaba Cloud CMS alert rules via CLI (write-operation skill). Supports CMS 1.0 cloud resource monitoring for ALL CMS-integrated cloud products. This skill performs write operations: creating alert rules, contacts, and contact groups. Use when: creating monitoring alerts, setting up alarm rules, configuring CMS alert policies for any cloud product, or managing cloud monitoring notifications. Triggers: "create alert", "setup monitoring", "configure alarm", "CMS alert", "cloud monitor rule", "告警规则", "创建告警", "监控报警".
triton-ascend-migration
将 GPU/CUDA Triton 算子迁移为 Triton-Ascend，或将 Python/PyTorch 算子改写为可在 Ascend NPU 上运行的 Triton-Ascend 实现，并在发现明确优化空间时直接输出优化后的代码、最小验证脚本和排障说明。用户只要提到 昇腾、Ascend、NPU、triton-ascend、Triton 算子迁移、PyTorch 算子改写、coreDim、UB overflow、1D grid、物理核绑定、block_ptr、stride、访存对齐、mask 性能、dtype 退化、算子优化，或者直接问“这个 skill 怎么用”“怎么在命令行里跑”“怎么在容器里执行迁移/验证”，就应优先使用本 skill，即使用户没有明确说“写 skill”或“做迁移”。
torch-npu-comm-test
通过 PyTorch torch.distributed 接口测试昇腾 NPU 通信算子性能。支持指定任意 tensor shape、dtype，使用 torchrun 启动，贴近真实训练场景的通信算子测试与性能分析。Use for testing collective communication operators (AllReduce, AllGather, ReduceScatter, etc.) with specific tensor shapes via torch.distributed on Ascend NPU.
external-gitcode-ascend-simple-vector-triton-gpu-to-npu
将简单Vector类型Triton算子从GPU迁移到昇腾NPU。当用户需要迁移Triton代码到NPU、提到GPU到NPU迁移、Triton迁移、昇腾适配时使用。注意：无法自动迁移存在编译问题的算子。
ascend-opplugin
Installs op-plugin (torch_npu operator plugin) environment and guides custom NPU operator integration with PyTorch via three patterns (A: no workspace, B: workspace+tiling, C: OpCommand reuse). Covers kernel implementation, host registration, build, and test. Use when working with op-plugin, operator integration, torch_npu custom ops, Ascend C, NPU operators, cpp_extension, xpu_kernel, or running custom operators on NPU.
ai-for-science-proteinbert
ProteinBERT 昇腾 NPU 部署与迁移 Skill，适用于将 TensorFlow 或 Keras 版 ProteinBERT 转成基于 PyTorch 与 torch_npu 的实现，覆盖权重转换、embedding 提取、微调训练、注意力可视化和 GPU 与 NPU 精度验证。
ghidra-mcp
Reverse engineering with Ghidra via MCP. Use when analyzing binaries, decompiling code, managing functions/symbols/data types, or performing any Ghidra-related reverse engineering task.
mcaf-devex
Improve developer experience for multi-component solutions: onboarding, F5 contract, cross-platform tasks, local inner loop, and reproducible setup. Use when the repo is hard to run, debug, test, or onboard into.
python-code
Make sure to ALWAYS use this skill when working with python code! Help designing, structuring, and maintaining Python projects, including virtualenvs, packaging, SQLite (sql3) usage, documentation of bug fixes, and clear commenting practices.
dependency-update
Process for safely adding or updating npm dependencies
bats-testing-patterns
"\"Master Bash Automated Testing System (Bats) for comprehensive shell script testing. Use when writing tests for shell scripts, CI/CD pipelines, or requiring test-driven development of shell utilities.\""
design
Unified design system for data/ML dashboards. Quick reference for brand vs data color decisions, component patterns, typography, spacing. Auto-invokes on styling, CSS, design, colors, UI, visualization keywords. Tiered loading - core always, philosophy/implementation on-demand.
context7-usage
Patterns for using Context7 MCP for library documentation (v2.25)
typescript
TypeScript strict patterns and best practices. Trigger: When writing TypeScript code - types, interfaces, generics.
sandi-metz-rules
This skill should be used when users request code review, refactoring, or code quality improvements for Ruby codebases. Apply Sandi Metz's four rules for writing maintainable object-oriented code - classes under 100 lines, methods under 5 lines, no more than 4 parameters, and controllers instantiate only one object. Use when users mention "Sandi Metz", "code quality", "refactoring", or when reviewing Ruby code for maintainability.
