“patterns”的搜索结果

为电子病历中的诊疗记录、处方和检验结果界面提供设计指导。涵盖药物相互作用警告、异常值显示、签署后记录锁定、追补记录与审计历史，并兼顾患者安全和录入便利。

• 设计诊疗流程
• 实现药物相互作用警告
• 显示检验结果中的异常值

通过项目结构、API、数据访问和缓存示例，辅助设计、实现与审查Django应用，整理不同环境的配置及业务逻辑，并减少不必要的数据库查询。

• 整理Django项目结构与配置
• 设计Django REST Framework API
• 减少不必要的数据库查询

在编写或审查Dart和Flutter代码时，参考状态管理、页面导航、网络通信、错误处理和测试的实现模式，处理空值与异步任务，并整理应用结构。

• 为新功能选择状态管理方式
• 审查空值处理与异步代码
• 根据登录状态进行页面导航

依据共用规范审查和整理代码，检查命名、可读性、不直接修改原始数据的更新方式及错误处理，找出重复逻辑、过长函数与过度复杂的设计，便于后续维护。

• 审查现有代码的命名与可读性
• 整理过长函数与深层条件分支
• 统一新模块的编码规范

用于设计和审查Node.js、Express及Next.js的API与服务端数据处理，梳理业务逻辑、数据库查询、缓存、身份验证和错误处理。

• 设计API并分离业务逻辑与数据访问
• 减少重复的数据库查询
• 引入缓存和异步处理

帮助实现和排查使用PyTorch FSDP的大模型分布式训练代码。通过源自官方文档的说明与示例，比较分片策略，并查看混合精度和训练状态保存的实现。

• 实现大模型分布式训练
• 比较FSDP应用方法与分片策略
• 查看混合精度与检查点示例

使用mcp-use设计和实现MCP服务器，让AI调用外部操作与数据。指南涵盖认证、交互界面、错误处理及部署，并引导查阅各功能的配套资料。

• 新建MCP服务器
• 添加操作、数据及可复用提示词
• 构建浏览与选择数据的React界面

检查项目所用框架和库的版本，依据对应的官方文档实现代码，为设计决策提供来源链接，并标明已弃用的 API、未验证的方法及与现有代码的冲突。

• 依据所用版本的官方文档核对实现
• 创建附有来源的代码模板
• 检查代码是否使用已弃用的 API

Capture lessons from completed tasks, train patterns from explicit examples, and consolidate accumulated learning into long-term storage. Use SONA and MicroLoRA adaptation tools for individual domains, then verify results in the appropriate stores.

中文简介正在准备中。当前显示英语简介。

• Capturing lessons after a successful task
• Consolidating accumulated task histories
• Creating learning adapters for separate domains

Define reusable reasoning and decision patterns for agents, embed them in executable workflows, and review their performance. Share successful approaches, including conditional decision trees, stepwise problem solving, analogies, and evaluation from multiple perspectives.

中文简介正在准备中。当前显示英语简介。

• Define conditional rules for agent decisions
• Turn problem-solving steps into executable workflows
• Solve new problems using similar past cases

Choose the next task using patterns learned from completed work and current progress. The skill acts on confident predictions, falls back to task priorities when confidence is low, and updates its learning after completion.

中文简介正在准备中。当前显示英语简介。

• Choosing the next task from current progress
• Guiding repeated work within a /loop
• Finding relevant examples in past completions

Search document collections by meaning using embeddings, numerical representations of text. Compare text similarity, route queries among a few predefined patterns, and use a compressed search index when memory is limited.

中文简介正在准备中。当前显示英语简介。

• Finding documents with similar meaning
• Comparing the similarity of two pieces of text
• Reducing memory use for large vector collections

Find JavaScript code that changes existing objects or arrays, then replace those updates with modified copies. Review shared state and browser behavior to make data changes easier to trace and check fixes in context.

中文简介正在准备中。当前显示英语简介。

• Finding direct changes to shared objects
• Replacing push and splice with copy-based updates
• Reviewing state updates in client components

Review supplied writing through twelve DHDNA dimensions, a framework for describing reasoning and expression. Receive observations supported by quotations, optional scores, and comparisons between samples, with clear limits separating textual patterns from psychological traits.

中文简介正在准备中。当前显示英语简介。

• Reflect on reasoning patterns in your writing
• Compare argumentation across selected texts
• Review how a text expresses assumptions and uncertainty

Design autonomous coding agents with patterns inspired by Cline and OpenAI Codex. Explore tool calling interfaces, permission and approval systems, browser automation, and workflows where people review or guide the agent's actions.

中文简介正在准备中。当前显示英语简介。

• Planning an autonomous coding agent
• Designing tool and function calling interfaces
• Defining permissions and approval steps

Build Python applications that keep other tasks moving while waiting for network, database, or file operations. Guides the choice of asyncio patterns, with timeouts, cancellation, error handling, and testing for asynchronous code.

中文简介正在准备中。当前显示英语简介。

• Build an asynchronous web API
• Fetch multiple web pages concurrently
• Develop a WebSocket server or chat system

Analyze audiences across Facebook, Instagram, YouTube, and TikTok using Apify Actors, tools that collect platform data. Gather follower, profile, or comment data, summarize audience characteristics and engagement patterns, and return results in chat, CSV, or JSON.

中文简介正在准备中。当前显示英语简介。

• Understanding follower and profile characteristics
• Analyzing audience reactions through comments
• Exporting audience data as CSV or JSON

Plan how an Angular app stores and updates data used by its screens. Covers local and shared state, choices involving Signals, NgRx, and RxJS, synchronization with server data, debugging, and migration from older patterns.

中文简介正在准备中。当前显示英语简介。

• Choose an Angular state management approach
• Design state shared across an app
• Manage data within individual components

Provides persistent project memory for AI agents through a local MCP server, a tool interface for agents. Stores and searches architecture decisions and implementation patterns, syncs with project documentation, and includes a dashboard for viewing memory usage.

中文简介正在准备中。当前显示英语简介。

• Save architecture decisions for later reference
• Search previously recorded implementation patterns
• Retrieve design notes by key

Create Hookify rules that detect command patterns, file edits, or session events and show warnings or block actions. Includes guidance on matching conditions, regular expressions for text patterns, and reminders before an agent finishes.

中文简介正在准备中。当前显示英语简介。

• Blocking potentially dangerous commands
• Warning about edits to sensitive files
• Adding reminders before an agent finishes

Build and debug asynchronous Rust applications with Tokio, a runtime for scheduling work while operations wait. Apply patterns for task management, channels, error handling, cancellation, and concurrency limits when developing network services and other concurrent systems.

中文简介正在准备中。当前显示英语简介。

• Build asynchronous network services
• Manage tasks and channel communication
• Design error handling and cancellation

Review Python code for common mistakes in error handling, asynchronous operations, type annotations, and tests. Use a practical checklist and correction examples to guide code reviews, investigate bugs, and improve existing implementations.

中文简介正在准备中。当前显示英语简介。

• Reviewing Python code before a merge
• Investigating bugs caused by common coding mistakes
• Refactoring legacy Python code

Analyze compiled programs without running them by recognizing branches, loops, data structures, and common instruction patterns. Use disassembly and decompilation, which translate machine code into readable representations, to reconstruct program logic and document findings.

中文简介正在准备中。当前显示英语简介。

• Understand an unfamiliar executable
• Reconstruct branches and loops from assembly
• Infer data structures and function parameters

Build Node.js APIs and backend services with Express/Fastify. The skill guides authentication, database integration, error handling, and operational practices such as logging and health checks, which report whether a service is working.

中文简介正在准备中。当前显示英语简介。

• Build a REST API with Express/Fastify
• Add authentication and database integration
• Organize middleware and error handling