Loading...
Loading...
Found 2,256 Skills
Static inspection of Triton operator code quality (Host side + Device side) for Ascend NPU. Used when users need to identify potential bugs, API misuses, and performance risks by reading code. Core capabilities: (1) Ascend API constraint compliance check (2) Mask integrity verification (3) Precision processing review (4) Code pattern recognition. Note: This Skill only focuses on static code analysis; compile-time and runtime issues are handled by other Skills.
Guide Catlass operator performance tuning. Process: Read the Catlass optimization guide, obtain/update profiler baseline, modify tiling according to the guide, recompile, **mandatorily generate and display performance comparison report**, iterate and compare. Tuning strategies are based on Catlass documentation. Ask for clarification if conditions are unclear.
HCCL (Huawei Collective Communication Library) performance testing for Ascend NPU clusters. Use for testing distributed communication bandwidth, verifying HCCL functionality, and benchmarking collective operations like AllReduce, AllGather. Covers MPI installation, multi-node pre-flight checks (SSH/CANN version/NPU health), and production testing workflows.
昇腾（Ascend）推理生态开源代码仓库智能问答专家旨在为 vLLM、vLLM-Ascend、MindIE-LLM、MindIE-SD、MindIE-Motor、MindIE-Turbo 以及 msModelSlim (MindStudio-ModelSlim) 等仓库提供专家级且易于理解的解释。在处理昇腾（Ascend）推理生态相关项目的用户询问时，务必触发此技能（Skill），可解答使用方法、部署流程、支持模型、支持特性、系统架构、配置管理、调试、测试、故障排查、性能优化、定制开发、源码解析以及其他技术问题。支持中英文双语回复，并可借助 deepwiki MCP 工具检索仓库知识库，生成具备上下文感知且基于证据的回答。Ascend inference ecosystem open-source code repository intelligent question-and-answer (Q&A) expert. Provide expert-level yet comprehensible explanations for repositories such as vLLM, vLLM-Ascend, MindIE-LLM, MindIE-SD, MindIE-Motor, MindIE-Turbo, and msModelSlim (MindStudio-ModelSlim). Use this skill when addressing user inquiries related to these Ascend inference ecosystem projects, including topics such as usage, deployment process, supported models, supported features, system architecture, configuration management, debugging, testing, troubleshooting, performance optimization, custom development, source code analysis, and any other technical issues about these projects. Support responses in both Chinese and English. Use deepwiki MCP tools to query repository knowledge bases and generate context-aware, evidence-based responses.
Use when app feels slow, memory grows, battery drains, or diagnosing ANY performance issue. Covers memory leaks, profiling, Instruments workflows, retain cycles, performance optimization.
Application performance profiling and bottleneck identification — Node.js profiling, Chrome DevTools, flame graphs, memory leak detection, CPU profiling, React rendering performance. Activate on "profiling", "performance bottleneck", "flame graph", "memory leak", "slow app", "CPU profiling", "heap snapshot", "React re-renders", "EXPLAIN ANALYZE", "event loop lag", "clinic.js", "Core Web Vitals". NOT for infrastructure monitoring or observability (use logging-observability), load testing (use a load-testing skill), or database schema optimization.
Use when analyzing e-commerce performance on Xiaohongshu, tracking live stream sales data, researching product trends, monitoring competitor shops, or optimizing e-commerce strategies with data insights
Use when analyzing Xiaohongshu account performance, researching competitor strategies, finding trending topics and hashtags, or needing detailed audience insights beyond platform-native analytics
Analyze hashtag performance and discover trending tags. Use when: researching hashtags for posts; finding related hashtags; analyzing hashtag reach; planning hashtag strategy; competitor hashtag research
Use when context is growing large (50k+ tokens), performance is degrading, instructions are being ignored mid-conversation, or planning multi-agent workflows. Triggers on "lost context", forgotten instructions, or sessions exceeding 30 minutes.
Enter this sub-process when conducting code optimization — handle tasks where 'behavior remains unchanged, structure changes' (structure / performance / readability). Shift single-module internal optimization from 'AI random refactoring' to 'first scan to generate a checklist, confirm each item with the user, execute step-by-step according to the method library, and require manual approval for each step'. Trigger scenarios: Users mention phrases like 'optimize it / refactor / rewrite / split it / poor performance / code is too long' without any accompanying behavior changes. Do not handle new requirements (route to feature), bugs (route to issue), or cross-module architecture restructuring (route to architecture + decisions).
Grafana Cloud Application Observability (APM), Frontend Observability (RUM/Faro), and AI Observability. Covers RED metrics (Rate/Error/Duration), service maps, span metrics from traces, Faro JavaScript/React SDK for browser instrumentation, session replay, AI/LLM model monitoring, and integration with traces/logs/profiles for full-stack correlation. Use when setting up APM, configuring frontend monitoring, analyzing service performance, or monitoring AI/LLM applications.