Automated summary
Frames backend development as a six-phase workflow, from requirement clarification through security hardening, testing and final review.
Strengths
- Explicit phase breakdown with JSON output artifacts at each step (requirements, architecture)
- Implementation guided from the inside out: Repository → Service → Handler
- Dedicated security phase covering authn, authz, input validation, injection defense, rate limiting and CORS/CSP
- Precise test pyramid with error paths prioritized over success paths
- Structured final review of concurrency, performance (N+1, indexes, pagination), observability and OpenAPI docs
Limitations
- Very broad description and triggers: the skill fires for nearly any server-side task, which can add noise
- Heavily code-oriented with no real automated checks; each phase relies on the agent's discipline
- Written in Chinese and the external references list is truncated, making the advertised extras hard to verify
Use when starting or restructuring a backend service and you want a repeatable framework covering design, security, testing and review.
Avoid for a one-line fix or a narrow framework question, where the full six-phase walkthrough is overkill.
Security analysis
CautionThe skill is a legitimate backend-development workflow and contains no malicious, obfuscated, exfiltration, or safety-disabling instructions. However, its broad tool permissions and deployment/CI-CD scope mean an agent could execute commands and modify files, so it warrants caution rather than being treated as purely read-only.
- •Declared tools include Bash, Write, Edit, and WebFetch, allowing command execution and file modification during backend scaffolding/deployment.
- •Workflow covers deployment, Docker/CI-CD, and writing server code, so it can legitimately execute or alter project infrastructure.
- •No explicit guardrails are provided around secrets handling, destructive shell commands, or human approval before deployment.
Examples
Build a REST API for a task management app in FastAPI with PostgreSQL — design the schema, lay out the endpoints and implement JWT authentication.Review my Express backend for security gaps: input validation, rate limiting, authorization on admin routes and sensitive data leakage in logs.Write unit and integration tests for my NestJS service layer and repository methods, covering error paths and boundary cases.name: backend-dev description: | This skill should be used when the user asks to "build a backend API", "design a database schema", "implement authentication", "create a REST endpoint", "develop a microservice", "set up server-side logic", "write API routes", "design system architecture", "implement business logic", "connect to database", "set up middleware", "configure ORM", "write server tests", "deploy backend service", or discusses backend-related tasks including API design, database design, authentication/authorization, server architecture, middleware, error handling, logging, performance optimization, or backend testing. Also triggered by technology-specific requests mentioning "Express", "FastAPI", "Spring Boot", "Django", "Rails", "Gin", "Fiber", "NestJS", "GraphQL", "gRPC", "WebSocket", "PostgreSQL", "MongoDB", "Redis", "JWT", "OAuth", "OpenAPI", "Swagger", "Docker compose backend", or "CI/CD pipeline".
【中文触发场景】
- "写后端接口"、"开发API"、"设计数据库"、"实现登录"
- "搭建后端服务"、"写服务器代码"、"实现业务逻辑"
- "数据库设计"、"表结构设计"、"API文档"
- "后端架构设计"、"微服务拆分"、"接口规范"
- "权限系统"、"中间件"、"错误处理"、"日志"
- "后端测试"、"单元测试"、"集成测试"
- "部署后端"、"Docker化"、"CI/CD配置" allowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, TaskCreate, TaskUpdate, TaskList
Backend Development Professional Workflow
专业后端开发工作流 —— 从需求到部署,结构化、可追溯、可审查。
核心原则
- 防御性编程 —— 所有外部输入不可信,边界条件显式处理
- 关注点分离 —— 分层架构(Handler → Service → Repository),每层只做一件事
- 显式优于隐式 —— 依赖注入、配置外部化、错误显式传播
- 渐进式交付 —— 先可运行,再优化;先核心路径,再边缘场景
工作流总览
Phase 0: 需求澄清与约束定义 ──→ 明确边界、性能目标、部署环境
↓
Phase 1: 架构设计 ──→ 分层/模块/数据流/技术选型 & 决策记录
↓
Phase 2: 核心实现(增量) ──→ Repository → Service → Handler 由内向外
↓
Phase 3: 安全加固 ──→ 认证/授权/输入校验/注入防护/速率限制
↓
Phase 4: 测试覆盖 ──→ 单元 → 集成 → 契约测试(含边界与异常)
↓
Phase 5: 审查与改进 ──→ 自审查清单 → 性能评估 → 文档收尾
每个阶段的 prompt 模板在 prompts/ 目录中,按需引用。
阶段详细说明
Phase 0: 需求澄清与约束定义
执行 prompts/phase0-clarify.md 中的提问框架,收齐以下信息:
| 维度 | 必须明确的点 | |------|-------------| | 上下文 | 业务场景、用户群体、预期流量 (QPS) | | 技术栈 | 语言/框架/数据库/运行时版本 | | 约束 | 部署方式(容器/Serverless/VM)、团队规模、时间线 | | 接口风格 | REST / GraphQL / gRPC / WebSocket / 混合 | | 数据要求 | 一致性级别、数据量级、是否需要事务 | | 非功能要求 | P99延时、可用性 SLA、审计合规 |
输出文件:.backend-dev/phase0-requirements.json
Phase 1: 架构设计
执行 prompts/phase1-arch.md,输出以下工件:
- 分层架构图 —— Handler / Service / Repository / 中间件栈
- 模块划分 —— 每个模块的职责、边界、依赖方向
- 数据模型 —— 核心 Entity 定义、表关系(ER)、索引策略
- 接口契约草案 —— 端点路径、请求/响应结构、状态码
- 技术选型决策记录 (ADR) —— 每次选型附理由和替代方案
- 风险与缓解 —— 识别数据热点、单点瓶颈、降级策略
输出文件:.backend-dev/phase1-architecture.json
Phase 2: 核心实现
按 Repository → Service → Handler 由内向外顺序,逐层实现:
Request → [Middleware] → Handler → Service → Repository → DB
│
↓
外部服务 / 缓存 / 消息队列
每条实现遵循:
- 先定义接口(interface/trait/type),再实现
- 显式错误类型 —— 定义领域错误码,不在运行时拼字符串
- 完备的日志 —— 每个外部调用的入口和出口都记录结构化日志
- 幂等性考虑 —— 写操作的幂等键(idempotency key)设计
Phase 3: 安全加固
执行 prompts/phase3-security.md 中的安全检查清单,逐项验证:
- 认证策略(JWT / Session / OAuth / API Key)
- 授权模型(RBAC / ABAC / ACL)
- 输入校验(结构化校验库 + 白名单策略)
- 注入防护(参数化查询 / ORM / 输出编码)
- 速率限制与防滥用
- 敏感数据(加密存储、响应脱敏、日志脱敏)
- CORS / CSP / HTTPS 强制
Phase 4: 测试覆盖
执行 prompts/phase4-testing.md,按金字塔模型覆盖:
╱╲ 手动探索测试
╱ ╲ E2E 测试 (关键用户路径)
╱ ╲ 集成测试 (模块间契约)
╱______╲ 单元测试 (核心逻辑 + 边界)
每条测试准则:
- 每个 Repository 方法对应一个集成测试
- 每个 Service 公共方法对应单元测试(mock 依赖层)
- 每条 Handler 路径(成功/鉴权失败/参数错误/404)各一个测试
- 错误路径优先级 ≥ 成功路径
Phase 5: 审查与改进
执行 prompts/phase5-review.md,逐项审查:
- 正确性审查 —— 并发竞态、事务边界、状态机状态遗漏
- 性能审查 —— N+1 查询、缺少索引、未使用连接池、未分页
- 可观测性 —— 结构化日志、指标埋点、健康检查端点、追踪上下文传播
- 文档补全 —— API 文档 (OpenAPI)、README 运行说明、环境变量清单
交叉引用清单
references/api-design.md—— REST / GraphQL / gRPC 设计规范与对比references/db-best-practices.md—— 表设计、索引策略、迁移、连接池references/error-handling.md—— 错误类型体系、结构化错误响应、全局异常处理references/security-baseline.md—— 安全基线检查表(OWASP Top 10 映射)references/struct-export.md—— 阶段间结构化数据传递格式定义
输出规范
所有中间产出统一存放于 .backend-dev/ 目录,按阶段命名:
.backend-dev/
├── phase0-requirements.json # 需求与约束
├── phase1-architecture.json # 架构设计方案
├── phase2-impl-record.md # 实现过程记录
├── phase3-security-report.md # 安全审查报告
├── phase4-test-report.md # 测试覆盖报告
├── phase5-review-report.md # 最终审查报告
└── adr/ # 架构决策记录(每项决策一个 markdown)
├── 001-use-postgresql.md
└── 002-adopt-repository-pattern.md
注意事项
- 增量交付 —— 不要一次性生成所有代码。每次围绕一个功能点的完整分层实现(Handler → Service → Repository),提交后继续下一个
- 不重复造轮子 —— 优先使用框架内建机制和社区稳定库,仅在确有必要时自定义
- 兼容性优先 —— 接口变更时保持向后兼容(字段添加不删除、可选参数扩展)
- 不假设运行环境 —— 所有路径引用使用相对路径,配置使用环境变量 + 默认值
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/backend-development-professional-workflow-mryiqgar/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/backend-development-professional-workflow-mryiqgar' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/backend-development-professional-workflow-mryiqgar/download' --output '.skill-downloads/backend-development-professional-workflow-mryiqgar/SKILL.md.part' && mv '.skill-downloads/backend-development-professional-workflow-mryiqgar/SKILL.md.part' '.skill-downloads/backend-development-professional-workflow-mryiqgar/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Write, Edit, Bash, Glob, Grep, WebFetch, TaskCreate, TaskUpdate, TaskList
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/backend-development-professional-workflow-mryiqgar/SKILL.md' && test -s '.skill-downloads/backend-development-professional-workflow-mryiqgar/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/backend-dev' && cp -R '.skill-downloads/backend-development-professional-workflow-mryiqgar' '.claude/skills/backend-dev'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/backend-development-professional-workflow-mryiqgar'openskills read 'backend-development-professional-workflow-mryiqgar'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/backend-development-professional-workflow-mryiqgar/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.