2180 个 · 按相关度排序
Acelere a inferência de LLMs usando especulative decoding, múltiplas cabeças Medusa e técnicas de lookahead decoding. Use ao otimizar velocidade de inferência (aceleração de 1,5-3,6×), reduzir latência em aplicações em tempo real ou fazer deploy de modelos com recursos computacionais limitados. Cobre modelos draft, atenção em árvore, iteração de Jacobi, geração paralela de tokens e estratégias de deploy em produção.
中文简介正在准备中。当前显示原文说明。
Implement Swift Codable models for JSON and property-list encoding and decoding with JSONDecoder, JSONEncoder, CodingKeys, and custom init(from:) or encode(to:). Use when parsing API responses, remapping keys, flattening nested JSON, handling date or data decoding strategies, decoding heterogeneous arrays, or integrating Codable with URLSession, SwiftData, or UserDefaults.
中文简介正在准备中。当前显示原文说明。
2025年最前沿的AI原生开发范式——VibeCoding。覆盖：Prompt-to-Product工作流、多轮对话管理、AI编码助手协作策略、代码质量保障、v0.dev/Lovable/Claude Code/Replit Agent工具链集成。触发词：vibecoding、VibeCoding、AI原生开发、提示即产品、AI pair programming、conversation-driven coding、prompt engineering for products
中文简介正在准备中。当前显示原文说明。
将功能开发、大规模代码重构和拉取请求审查交给Codex、Claude Code或OpenCode在后台执行，并处理独立检出目录、进度监控及完成或失败通知。
按统一标准检查变量和函数命名、代码可读性、数据更新方式及错误处理，用于新项目开发、代码审查和重构，帮助团队统一便于维护的写法。
用实际开发任务比较多个编程智能体，记录成功率、可获取的API费用、耗时和重复运行的稳定性，为工具选型及更新后的性能评估提供数据。
Turn a broad coding request into a concrete work plan grounded in the codebase. After user approval, it documents affected files, decisions, dependencies, and verification steps so a separate worker can carry out the implementation.
中文简介正在准备中。当前显示英语简介。
Delegates repository analysis or coding tasks to MiniMax Code without opening its interactive interface. It runs one task in the specified project with a time limit, then uses the final response as the result.
中文简介正在准备中。当前显示英语简介。
Delegate repository analysis or coding tasks to Qwen Code without opening its interactive interface. Run within a specified project and time limit, then check the JSON response and exit status before summarizing the result.
中文简介正在准备中。当前显示英语简介。
Guide AI coding work toward simple implementations, focused edits, and explicit assumptions. Use it when writing, reviewing, or refactoring code to keep changes tied to the request and define success through tests or other concrete checks.
中文简介正在准备中。当前显示英语简介。
Define security controls for AI coding agents used by a team. Covers command and file permissions, secret scanning, isolated execution environments, code review gates, and audit trails, with configuration examples to adapt.
中文简介正在准备中。当前显示英语简介。
Inspect local AI coding session logs with agenttrace to identify cost spikes, delays, failed tools, and retry loops. Produce readable reports, compare attempts, and configure automated checks for unusual or unhealthy runs.
中文简介正在准备中。当前显示英语简介。
Compare how proxies and backend servers interpret HTTP requests in a CTF sandbox. Use paired requests and logs to pinpoint differences in paths, headers, or message boundaries, then document a minimal reproduction of unintended routing.
中文简介正在准备中。当前显示英语简介。
Set up GitHub Copilot for a new project with instructions, reusable skills, and specialized agents tailored to its technology stack. Add a coding agent environment workflow when GitHub Actions is used, plus setup and customization guidance.
中文简介正在准备中。当前显示英语简介。
Create an AGENTS.md file that explains how coding agents should work in a project. Examine its structure and existing configuration, then document setup commands, development workflows, tests, coding conventions, builds, and contribution requirements.
中文简介正在准备中。当前显示英语简介。
Apply consistent coding practices across TypeScript, JavaScript, React, and Node.js projects. Get guidance on naming, types, error handling, API design, file organization, and tests to make code easier to read and maintain.
中文简介正在准备中。当前显示英语简介。
Design autonomous coding agents using implementation patterns for tool calls, permission checks, browser interaction, and saved task state. Code examples and checklists help structure agent behavior and workflows that include human approval.
中文简介正在准备中。当前显示英语简介。
Delegate development tasks to external coding agents such as Codex and Claude Code through command-line tools. Choose local or container execution, check setup, provide a self-contained task brief, and inspect important changes afterward.
中文简介正在准备中。当前显示英语简介。
Guides you through installing Wasp agent skills, which add Wasp knowledge and recommended practices to AI coding tools. It retrieves installation instructions and explains the steps for working with Wasp and Open SaaS.
中文简介正在准备中。当前显示英语简介。
Coordinate multiple coding agents through Superset in separate workspaces. Split work into bounded tasks, track dependencies and progress, send follow-ups, and collect structured results covering changed files, verification checks, blockers, and the order for combining work.
中文简介正在准备中。当前显示英语简介。
Turn a rough idea or an existing prompt into a ready-to-paste instruction for a specific AI tool. The skill clarifies the task, output format, constraints, and success criteria for writing, image generation, or coding agents.
中文简介正在准备中。当前显示英语简介。
Compare major AI coding tools and consult practical guidance on prompts, project instructions, debugging, workflows, and costs. Use the reference to choose suitable tools and identify why an AI-assisted coding task is stuck.
中文简介正在准备中。当前显示英语简介。
Analyze webpage screenshots to extract colors, typography, and component styles. Generate structured JSON describing reusable design rules and an AI coding prompt, or convert the results into brand styling for a presentation video.
中文简介正在准备中。当前显示英语简介。
Set up Git workflows for Gitee, Coding.net, 极狐 GitLab, and CNB with platform-specific connection and authentication examples. Choose branching rules, standardize Chinese commit messages, and adapt automated testing and deployment configurations to your team's workflow.
中文简介正在准备中。当前显示英语简介。