com um clique
mindsdk-referenceapps
mindsdk-referenceapps contém 25 skills coletadas de Ascend, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
基于FastAPI知识库服务实现的RAG知识管理与检索技能，支持文档上传、解析、入库、删除、列表查询、内容检索、全文检索等能力，兼容PDF/DOCX/TXT/MD等格式，支持图片解析与多粒度描述入库，可直接对接Agent/机器人进行知识问答。
Analyzes pull requests and codebases for implementation and architecture issues, outputs structured analysis reports and refactoring suggestions. Use when reviewing PRs, examining code changes, conducting periodic codebase reviews, or when the user asks for refactoring/architecture analysis.
模型资源收集。联网搜索最新免费/优惠的AI模型资源信息（如各大云厂商优惠活动、免费API、Coding计划等），整理并生成配置指南文档。适用于用户询问"有什么便宜的模型推荐"、"免费模型有哪些"、"模型优惠"等场景。
系统化、安全地代码重构技能。能够识别代码坏味道、提供重构手法，支持制定计划、执行重构并验证结果。适用于代码质量提升、技术债清理、可维护性改进、代码优化、代码改进等场景。当用户请求重构代码、优化代码质量、修复代码问题或清理技术债时触发。
GitCode PR安全审查技能。用于自动审查GitCode仓库的Pull Request中的代码安全问题，使用sdk-security-audit技能进行代码安全分析，并将审查结果作为评论发布到对应的PR上。当用户需要对GitCode仓库的PR进行安全代码审查时使用此技能。
Generate reply drafts for a single GitCode issue; maintainer reviews before posting. Use when user asks to reply to or comment on an issue and provides a GitCode issue link; do not use when user only wants to fetch or query issue data. 针对单个 GitCode Issue 生成回复草稿，维护者审阅后可发送评论；仅当用户要回复或评论且提供链接时使用，仅获取或查询 issue 信息时勿用。Python 3.7+ standard library only.
Write README-style technical documentation for AscendC custom operators by reading local source files and adapting an existing template. Use when Codex needs to document an AscendC operator, compare a target operator repo against a reference README, turn `op_host` and `op_kernel` implementations into structured docs, or generate per-operator documentation from code with the model instead of a parser script.
Generate daily operations reports for GitCode repositories with key metrics, AI summaries and Markdown output. 将 GitCode 上配置的仓库运营数据整理成日报输出；支持关键指标统计、AI 摘要与 Markdown。Python 3.7+ standard library only, no pip dependencies.
收集并生成AI领域热门报告。触发条件：用户要求获取AI相关信息，如"收集AI新闻"、"获取AI信息"、"有什么AI新动态"、"AI今天发生了什么"、"生成AI报告"、"AI摘要"、"AI周报"、"AI今日动态"等。支持用户指定具体领域（如LLM、CV、NLP、机器人等），支持指定收集条数（不指定默认10条），支持指定时间段（不指定默认"今日"），输出包含md、html、pdf多个版本的文件。
通过SMTP发送邮件。触发条件：(1) 用户要求"发送邮件"；(2) 用户要求"发邮件到xxx"；(3) 用户要求"把内容发送到邮箱"。支持纯文本和HTML格式，需要用户提供SMTP服务器、端口、邮箱地址和授权码/密码。
操作系统适配工具，用于生成和管理不同操作系统的适配方案。当需要为新 OS 创建适配或更新 OS 配置时调用。
Ascend 故障诊断工具，提供日志采集、清洗、诊断全流程。支持集群/单机/超节点故障诊断，当用户需要排查 NPU 训练推理故障或性能劣化问题时调用。
Detect AI-generated text, analyze content credibility (credible/suspicious/fabricated), and verify resource accessibility (URLs, citations, package names). Use when users want to check if text is AI-written, verify facts in AI-generated content, validate links and references, or assess the trustworthiness of generated content.
SDK UT边界用例自动生成。当用户请求单元测试生成、边界测试用例、UT用例、测试用例生成时使用。支持C/C++和Python SDK，自动识别项目已有的测试框架（GTest/pytest/unittest等），优先从API文档提取边界值定义，从SDK入口函数出发分析边界场景，生成完整的测试代码或手工测试建议。
自动化适配Agent后端，集成MSRL(MindSpeed-RL)、VERL、VLLM等训练推理框架。When users need to integrate training frameworks (MindSpeed-RL/VERL) with inference engines (vLLM), configure agent backend pipelines, generate training scripts, create adapter wrappers, or build complete training-inference pipelines for LLM agents, use this skill. Supports GRPO/PPO training algorithms, multi-NPU distributed inference on Ascend NPUs, and standalone code generation independent of OpenCode. This skill is optimized for Ascend NPU (昇腾) hardware.
Analyze AgentSDK/Agentic RL codebases for precision and performance issues on Ascend NPU. Use when users want to: diagnose training/inference precision problems (NaN, overflow, dtype mismatches) on NPU, identify performance bottlenecks (memory, latency, throughput), optimize model training speed on Ascend, debug memory issues, or get solutions for common AgentSDK performance/precision problems. This skill is specifically designed for Ascend NPU (Ascend 910/910B/910C) and CANN framework. This skill works standalone - no dependency on the main AgentSDK repository required.
Generate release notes for GitCode repositories from commits (by tag range or since-date), grouped as feat/fix/docs/other, output Markdown for Release pages. 按 tag 区间或日期拉取提交并生成版本发布公告 Markdown。Python 3.7+ standard library only.
执行 K8s Master 节点的 envCheck.sh 环境检测脚本。当用户询问"集群状态"、"K8s集群状态"、"环境检测"、"Ascend环境检查"、"任务为什么没调度起来"、"任务为什么pendding"、"NPU状态"或要求执行集群状态检测时使用。需要用户提供 master 节点 IP、用户名，以及密码或 SSH 密钥路径其中之一。
Quality audit for merged GitCode PRs: sample by time range or repo list, check compliance (labels, comments, tests, size, etc.), output table. Use when user asks to 抽检/质量检查 已合入的 PR 规范性、多仓库 PR、或 将结果整理成表格. Multi-repo (owner/repo). Python 3.7+ stdlib only.
C/C++ 和 Python SDK 代码安全审计。当用户请求安全审计、代码审计、漏洞扫描、安全检查时使用。支持本地仓库和远程 GitHub/GitLab/GitCode 仓库。从对外 SDK 函数入口出发，依据安全编码规范进行符号级分析，输出具备完整证据链的问题报告。
Analyzes user-provided error messages, logs, and environment information to identify root causes and generate customer-friendly responses for Ascend NPU hardware scenarios. Use when: (1) User provides error logs, stack traces, or crash reports, (2) User describes a problem with environment/context involving Ascend NPU hardware, (3) User requests debugging assistance or root cause analysis for MindSpeed, MultimodalSDK, Vision SDK, or other Ascend-related components, (4) User needs issue resolution guidance. This skill works independently from any specific codebase and can analyze errors based on built-in knowledge, common patterns, external documentation, and provided context. Supports multiple repositories by accepting configurable repository paths for source code reference. ALWAYS use this skill when user provides ANY error information in Ascend NPU context - do NOT attempt to analyze without it.
Fetch and query data from GitCode platform via its REST API: repositories, branches, issues, pull requests, commits, tags, users, organizations, search, webhooks, members, releases and more. 查询 GitCode 上的仓库、分支、议题、PR、提交、标签、用户、组织等数据。Python 3.7+ standard library only.
自动化大规模集群安装部署工具，用于 ascend-deployer 组件批量部署。当用户需要跨集群部署组件或执行批量安装操作时调用。
Analyze competitor multimodal preprocessing capabilities, identify user pain points, compare with current MultimodalSDK (Ascend) capabilities, provide NPU migration plans, and perform tool quantity analysis. Use this skill when users want to: - Understand competitor preprocessing solutions (NVIDIA DALI, OpenCV CUDA, etc.) - Compare their current pipeline with Ascend MultimodalSDK capabilities - Plan migration from GPU/CPU preprocessing to NPU (Ascend) - Analyze tool/operator count differences between implementations - Identify gaps and provide migration recommendations This skill is independent and decoupled from the main repository - it uses external research and standalone analysis methods.
获取并分析GitCode仓库的issue信息（open/closed）。当用户想从GitCode收集issue、分析已关闭issue的解决方案、或获取开启issue的处理建议时调用。支持Ascend项目如mind-cluster、RecSDK等。