“development”的搜索结果

Coordinate multiple AI agents for research, development, testing, and system analysis. It guides role assignment, communication structures, parallel and sequential tasks, shared memory, progress monitoring, and recovery, bringing separate contributions into reports or coordinated development workflows.

中文简介正在准备中。当前显示英语简介。

• Gather research in parallel and compile a report
• Coordinate application design, implementation, and review
• Run unit, integration, security, and performance tests in parallel

Guide development in Apache Tika with project rules for Maven builds, module tests, code conventions, and checks before committing. Covers safe file handling, regression tests, and build pitfalls that can hide failures.

中文简介正在准备中。当前显示英语简介。

• Preparing an Apache Tika development session
• Building and testing selected modules
• Checking parser changes and regression tests

Carry out a written implementation plan in a separate session, reviewing it before starting and tracking each task through verification. The workflow pauses for blockers and hands completed work to a development branch finishing process.

中文简介正在准备中。当前显示英语简介。

• Executing a written implementation plan
• Tracking task progress and verification
• Reviewing gaps before implementation

[omh] LLM-powered feature to build: LLM app development: prepare a build handoff for an LLM-powered feature with a pinned provider boundary, schema-first outputs, versioned prompt files, grounded retrieval, and an eval suite as a shipped deliverable. Use when the user says: llm-app-dev, llm app development, llm application development, build an llm app, build an llm feature, llm feature development, build a rag pipeline, rag pipeline.

中文简介正在准备中。当前显示原文说明。

Configure Apollo.io local development workflow. Use when setting up development environment, testing API calls locally, or establishing team development practices. Trigger with phrases like "apollo local dev", "apollo development setup", "apollo dev environment", "apollo testing locally".

中文简介正在准备中。当前显示原文说明。

WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects (小程序开发、调试、预览、发布). Covers project structure and config (`project.config.json`, `appid`, `miniprogramRoot`, `tabBar`, routing/navigation, icon assets), WeChat Developer Tools Nightly workflows (`wechatide` CLI, WeChat IDE Skills/MCP), `miniprogram-ci` preview/upload, console/network debugging, message push (消息推送) and customer-service auto-reply (客服消息), mini program SEO / search indexing (小程序搜索优化、页面收录、搜索推广、mpcrawler), and CloudBase integration (`wx.cloud`, 腾讯云开发, 云开发) when explicitly used. Use when users create, develop, modify, debug, preview, deploy, publish, or promote WeChat Mini Programs. NOT for Web frontend (use web-development), pure backend services (use cloudrun-development / cloud-functions), or UI-design-only tasks (use ui-design).

中文简介正在准备中。当前显示原文说明。

Think and work like an expert Developmental Biologist. Use when a task calls for Developmental Biologist judgment. Reasons from stage, positional information, gene regulatory networks, and tissue mechanics through morphology-based staging (Carnegie/HH/Theiler/NF/hpf), French-flag morphogen logic, light-sheet 4D imaging, lineage tracing, and ARRIVE/MDAR/REMBI reporting while treating developmental delay, CRISPR F0 mosaicism, morpholino p53 toxicity, and conflated fate-versus-lineage claims as first-class failure modes.

中文简介正在准备中。当前显示原文说明。

Think and work like an expert Developmental Psychologist. Use when a task calls for Developmental Psychologist judgment. Reasons from developmental trajectories, measurement invariance, and familial-environmental context through age-normed instruments (Bayley, WPPSI/WISC, CBCL, MacArthur-Bates CDI), false-belief and violation-of-expectation paradigms, and lme4/lavaan growth models while treating verbal-demand confounding of theory of mind, informative attrition, adult-normed task misapplication, and parent-versus-direct-assessment divergence as first-class failure modes.

中文简介正在准备中。当前显示原文说明。

Avalonia Zafiro Development workflow skill. Use this skill when the user needs Mandatory skills, conventions, and behavioral rules for Avalonia UI development using the Zafiro toolkit and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

中文简介正在准备中。当前显示原文说明。

Drafts U.S. commercial real estate owner-developer agreements covering scope, entitlements, schedule, pricing (fixed, GMP, cost-plus), change orders, payment and retainage, insurance, indemnity, IP, confidentiality, termination, and disputes. Use when user mentions "development agreement", "owner-developer agreement", "project development contract", "real estate development", "GMP", "cost-plus", "milestones", or "change orders".

中文简介正在准备中。当前显示原文说明。

Use this skill when an engineering team needs a secure development policy, or has one that does not match how code really ships, and asks "write our secure SDLC policy", "secure development policy from our CI", "document our code review and scanning for the audit", "what does our pipeline already enforce", "change management for engineers" or "secure coding policy for SOC 2 or CRA". Reads the repositories and pipeline definitions, inventories what is actually enforced (reviews, checks, scanners, deploy gates, dependency and secret controls), and writes a policy whose every "must" points to the place it is enforced, with gaps listed as decisions.

中文简介正在准备中。当前显示原文说明。

帮助配置和排查 Vite 项目，整理配置文件、环境变量、API 转发、插件与构建产物，调查开发服务器和依赖问题，并准备库的发布输出。

• 配置环境变量与开发 API 转发
• 排查开发服务器缓慢或更新失效
• 优化并检查生产构建产物

将产品需求和规划文档整理为可供开发使用的具体要求，明确业务规则、数据归属、服务间接口及待定事项，形成可交接的资料。

• 将产品需求文档转为开发要求
• 梳理跨服务功能的需求
• 记录评审中反复确认的前提

根据变更规模，为功能开发、缺陷修复等工作选择调研、规划、测试和审查阶段。这套相关技能共用的流程包含计划审批和提交前确认。

• 统一功能开发与缺陷修复流程
• 根据变更规模选择开发阶段
• 依据设计文档开发MVP

帮助团队选择适合开发方式和发布节奏的Git分支策略，统一提交记录与拉取请求说明，并梳理本地历史、合并冲突解决、版本标签和发布管理的操作步骤。

• 为新项目选择分支策略
• 统一提交信息和拉取请求说明
• 提交审查前整理本地历史

使用 Flox 将开发工具、数据库、版本及配置集中到文件中，建立可在 macOS 和 Linux 上复现的开发环境，并与团队共享或为智能体添加项目工具。

• 统一团队的开发环境
• 管理语言工具与系统依赖
• 在本地启动 PostgreSQL 和 Redis

将测试驱动开发用于功能新增和缺陷修复：先写测试并确认失败，再用最少代码使其通过，最后整理代码，逐项验证行为。

• 先写测试再添加功能
• 先复现缺陷再修复
• 保持测试通过并整理代码

将项目质量标准及其数值、理由和检查方法写入文档，并从差异中检查跳过测试、抑制警告或降低门槛的改动，维持智能体开发质量。

• 制定智能体开发的质量标准
• 选择覆盖率与性能目标
• 发现跳过测试或抑制警告

读取claude-mem中保存的开发历史，生成叙事报告，梳理设计演变、难题解决和工作模式，并提供时间统计及复用记忆所节省的词元估算。

• 回顾项目的开发历程
• 追溯设计决策及其影响
• 了解故障排查和工作模式

在Claude Code操作前后加入自动处理，执行代码格式化与验证、协调多个智能体，并保存工作记录，将进度和决策延续到下次会话。

• 自动执行编辑后的格式化与验证
• 在多个智能体之间共享进度
• 保存和恢复开发会话

将软件开发从需求整理、设计、先写测试的实现推进到审查和部署，并通过多个AI智能体分担任务、共享设计判断与调查结果。

• 规划并实现新功能
• 为现有代码改造补充测试
• 审查代码安全性与性能

按测试驱动开发流程推进Rust功能实现和缺陷修复：先确认测试失败，再编写最少代码使其通过，随后重构，并完成格式、静态分析和测试检查。

• 从测试开始添加Rust功能
• 用测试复现缺陷后修复
• 测试无效输入和错误路径

Automate checks, code formatting, agent coordination, and session records around Claude Code operations. Uses hooks, actions triggered before or after work, to preserve context and connect development tasks with shared memory.

中文简介正在准备中。当前显示英语简介。

• Automatically format and validate edited code
• Share progress across multiple agents
• Save and restore development sessions

Organize software development from requirements and design through testing, review, and deployment. Uses Claude Flow to coordinate specialized agents, share decisions across sessions, and guide implementation with tests written before code.

中文简介正在准备中。当前显示英语简介。

• Developing a feature from requirements through review
• Refactoring legacy code with supporting tests
• Investigating bugs and adding regression tests