“coding”的搜索结果

在编写代码前，从技术角度审查实施计划，检查系统结构、数据流、边界情况、测试覆盖和性能。通过讨论各项问题与建议方案，确定后续实施方向。

• 实施前审查计划
• 检查系统结构和数据流
• 检查边界情况与测试覆盖

为编码代理配置可调用的gbrain，安装命令行工具，使用本地PGLite或Supabase初始化brain，注册MCP，并记录各远程连接的信任策略。

• 在新机器上首次安装gbrain
• 使用本地PGLite初始化
• 配置Supabase方案

按任务整理提供给AI智能体的规则、规范和相关代码，选择所需文件与实现示例，汇总长对话，并记录决定、验证结果和待办问题以交接到新会话。

• 整理AI辅助开发的规则
• 选择任务所需文件
• 整理长对话中的信息

将模糊想法整理为明确目标、工作范围和验收条件的规格文档，梳理多个功能的划分与依赖，并经人工审批逐步进入规划、任务拆分和实现。

• 在实现前明确想法
• 编写包含验收条件的需求文档
• 将大型需求拆分为独立功能

将落地页或产品网站的设计方案按区块生成为独立横向参考图，统一配色、字体与图片处理方式，同时变化构图、留白和按钮呈现，供开发人员或编程代理参考。

• 逐区块讨论落地页设计
• 研究首屏构图
• 向开发人员分享参考图

在编写代码前，将功能或变更需求整理为按文件列出的最小实施计划，说明修改原因和必要接口，并标明影响范围扩大或权限增加的地方，供实施人员接手。

• 添加功能前制定实施计划
• 明确需要修改的文件
• 检查影响范围和权限变更

通过分配和切换编写代码与指导工作的角色，让人与AI协作开发。支持生成测试、持续代码审查、排查错误，以及面向学习的分步讲解。

• 编写代码时接受AI审查
• 提供方向并让AI负责实现
• 先写测试再开发功能

用于代码新增、修改和审查，先判断实现是否必要，优先复用现有代码与标准库，在保留安全措施和验证的前提下，将改动缩减到必要范围。

• 减少不必要的代码和依赖
• 修复多个调用方的共同根因
• 审查过度抽象的代码

在Grok Build中组建具有名称和角色的多智能体团队，管理设计、实现、测试与审查的执行顺序，以及成员间的消息交接、进度查看和团队关闭。

• 分工完成设计到审查的流程
• 在Grok Build中交接工作
• 管理多个团队的消息和进度

在Flow Nexus中按能力和学习目标选择编程挑战，验证提交的解答并检查效率、代码质量及改进空间，同时管理排名、徽章和学习进度。

• 寻找适合当前水平的挑战
• 复查已提交的解答
• 查看排名、徽章和学习进度

通过多个专业AI智能体审查GitHub变更提案，检查安全、性能、架构及编码规范问题，汇总问题说明与修复示例，并按标准发布批准或修改要求。

• 检查身份验证变更的安全性
• 排查数据库变更导致的性能下降
• 检查界面无障碍与编码规范

指导安装和运行用于协调多个 AI 编程代理的 Ruflo，支持任务分工、跨会话信息保存与检索、运行状态检查，以及按工作需求选择插件。

• 搭建多代理开发环境
• 协调代理之间的并行工作
• 跨会话保存和检索信息

Manage Flow Nexus accounts, run code in sandboxes, deploy app templates, and track credits. The skill guides platform operations through connected tools, including file storage, execution monitoring, and coding challenge submissions.

中文简介正在准备中。当前显示英语简介。

• Create a sandbox and run development code
• Find and deploy an app template
• Check credit balances and payment history

通过分配和切换编写代码与指导工作的角色，让人与AI协作开发。支持生成测试、持续代码审查、排查错误，以及面向学习的分步讲解。

• 编写代码时接受AI审查
• 提供方向并让AI负责实现
• 先写测试再开发功能

Review website JPEGs for progressive encoding, which displays a blurry preview before sharpening. Identify images that could use this format, consider file size and loading behavior together, and explain how to confirm the change in browser developer tools.

中文简介正在准备中。当前显示英语简介。

• Reviewing how JPEGs appear during loading
• Checking JPEG fallbacks for WebP or AVIF
• Reviewing image delivery through a CDN or build process

Set up ESLint, a tool that checks JavaScript for errors and coding rule violations. Configure shared rules, connect checks to editors and automated workflows, and review flagged code alongside its behavior in the browser.

中文简介正在准备中。当前显示英语简介。

• Setting up ESLint for a JavaScript project
• Applying consistent coding rules across a team
• Adding code checks to editors and CI/CD

Check whether HTML, JavaScript, and CSS are delivered with Gzip or Brotli compression. Use measured loading problems and response headers to guide server or CDN changes that reduce the amount of data downloaded.

中文简介正在准备中。当前显示英语简介。

• Investigating slow page loads on mobile networks
• Checking compression headers for text resources
• Reviewing Gzip or Brotli settings on a server or CDN

Study AI engineering through interactive terminal lessons with explanations, coding exercises, and quizzes. The tutor follows your recorded progress, revisits previous material, adapts to your answers, and logs results and topics that need review.

中文简介正在准备中。当前显示英语简介。

• Resuming lessons from recorded progress
• Learning concepts through coding exercises
• Checking understanding with lesson quizzes

Research a coding task before implementation and turn it into a detailed work plan with decisions, dependencies, and verification steps. The plan is written after approval, while code changes remain a separate workflow.

中文简介正在准备中。当前显示英语简介。

• Planning a large change before implementation
• Turning a vague request into concrete tasks
• Preparing a plan for another agent to execute

Recover context from local coding-agent transcripts and produce a checkpoint covering the objective, completed work, blockers, and next step. Explicit import requests support read-only recovery, with continuation governed by the current workspace rules and the user's request.

中文简介正在准备中。当前显示英语简介。

• Recover context using a session ID
• Summarize unfinished work from local logs
• Review JSONL exports or Markdown handoffs

Manage coding-agent sessions across connected machines through Herdr, tmux, and MSP. See which sessions need attention, review their output, open sessions with a brief, send instructions, answer approval dialogs, and stop or close sessions.

中文简介正在准备中。当前显示英语简介。

• Find sessions waiting for approval or review
• Read another session and send follow-up instructions
• Open an agent session on a named machine

Find facts and data with web search, prioritizing primary or authoritative sources. Record exact figures, units, time periods, and source URLs in shared history so later calculation, coding, or writing can use traceable evidence.

中文简介正在准备中。当前显示英语简介。

• Finding facts backed by primary or authoritative sources
• Recording figures with units, time periods, and source URLs
• Collecting evidence before calculation or writing

Set up and customize Pi, a terminal coding agent framework. This skill guides model configuration, extension development, terminal interfaces, and integration with other applications through its SDK, a software development kit, or process messaging.

中文简介正在准备中。当前显示英语简介。

• Install Pi and configure model access
• Create custom tools and terminal interfaces
• Embed Pi in another application

Delegate repository analysis and coding tasks to GitHub Copilot CLI without an interactive session. The skill reads structured output, checks errors, and summarizes the final result along with any denied tool requests.

中文简介正在准备中。当前显示英语简介。

• Ask Copilot to explain a failing test
• Delegate repository analysis to Copilot
• Request code changes with narrowly scoped tool permissions