Backend Analysis Skill logo

Backend Analysis Skill

Community
jiushiwon
backend-analysis-skill

后端项目静态分析技能。不运行项目,直接扫描源码,为 Java(Spring Boot/Spring Cloud)、Go(Gin/Echo)、Python(FastAPI/Django/Flask)、Node.js(Express/NestJS) 项目产出 4 份报告:① 接口报告(全部 API 清单:方法/路径/入参/出参/鉴权)② 技术报告(语言/框架版本、中间件如 Redis/MQ/ES、第三方 API 如短信/支付/推送、架构组件如拦截器/全局异常/全局配置/路由注册)③ 数据库报告(表结构/ORM/索引/迁移脚本)④ 业务逻辑报告(模块划分/核心流程/定时任务/外部集成)。当用户要求"分析后端项目"、"梳理后端接口"、"盘点技术栈"、"出数据库文档"、"接手老项目"、"读懂后端代码"、"backend analysis" 时调用。

Overview

Publisherjiushiwon
Repositorywg-skills
Skill namebackend-analysis-skill
Stars
123
Forks
38
Bundled files
5
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jiushiwon on GitHub. Read the source before you install it.

Installation

Install the Backend Analysis Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/backend/backend-analysis-skill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jiushiwon/wg-skills.git /tmp/wg-skills
mkdir -p .claude/skills
cp -r /tmp/wg-skills/vibeCoding/backend/backend-analysis-skill .claude/skills/backend-analysis-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Backend Analysis Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Backend Analysis Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Backend Analysis Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Backend Analysis Skill — 后端项目全景分析

本技能对已有后端项目做静态扫描(不编译、不运行),一次产出 4 份报告,用于接手老项目、技术盘点、交接文档、重构前摸底。

适用场景与边界

  • 适用:接手陌生项目、盘点技术栈与接口、补交接文档、重构/迁移前摸底
  • 不做:不修改目标项目代码、不运行业务、不替代运行时接口文档(Knife4j/Swagger)
  • 与其他技能的区别:
    • deploy-detect-skill 为部署生成画像(轻量),本技能为理解项目产出 4 份完整报告
    • frontend-code-doctor 审查前端代码质量,本技能盘点后端项目
    • backend-generate-skill 是从零生成后端,本技能是分析已有后端

工作流程

Step 0 识别技术栈 → Step 1 接口扫描 → Step 2 技术扫描 → Step 3 数据库扫描 → Step 4 业务梳理 → Step 5 汇总总览

默认 4 份报告全出;用户指定单份时(如"只出接口报告")只跑对应 Step。

Step 0:技术栈识别(必先执行)

读取构建文件判断语言与框架,规则详见 references/detection-rules.md:

  • pom.xml / build.gradle(.kts) → Java
  • go.mod → Go
  • requirements.txt / pyproject.toml / Pipfile → Python
  • package.json → Node.js

识别结果(语言 + 框架 + 版本 + ORM)决定后续使用哪套扫描模式。多模块/多语言混合项目逐模块识别后分别套用。

Step 1:接口扫描 → 01-api-report.md

扫描模式详见 references/api-scan-patterns.md。要点:

  1. 先 Glob 定位控制器/路由文件,再 Grep 路由注解/注册语句
  2. 类级路由前缀 + 方法级路径拼接出完整 URL(如 @RequestMapping("/user") + @PostMapping("/login") → POST /user/login)
  3. 提取每个接口的:HTTP 方法、完整路径、处理函数、入参(DTO/Query)、出参类型、鉴权标记
  4. 识别全局路由配置(context-path、统一前缀 /api、版本前缀 /v1)
  5. 标注无鉴权接口、被注释/废弃的接口

Step 2:技术栈扫描 → 02-tech-report.md

扫描模式详见 references/tech-scan-patterns.md。覆盖 6 个维度:

维度内容
基础栈语言与运行时版本、框架版本、构建工具
依赖清单按 Web/ORM/缓存/MQ/工具/测试 分类
中间件Redis、Kafka/RabbitMQ/RocketMQ、ES、对象存储(OSS/S3/MinIO)
第三方 API短信、支付、推送、地图、OAuth/SSO、邮件、AI 服务(依赖 + 配置 key 双证据)
架构组件拦截器/过滤器/中间件、全局异常处理、AOP、全局配置加载、跨域配置、路由注册方式、定时任务
安全隐患硬编码密钥、拼接 SQL、DEBUG 开启、Actuator 暴露

密钥/密码类信息在报告中必须打码(如 AKIA****)。

Step 3:数据库扫描 → 03-database-report.md

扫描模式详见 references/database-scan-patterns.md。要点:

  1. 从连接配置(spring.datasource.url / DATABASE_URL 等)判断数据库类型
  2. 按 ORM 扫描实体/模型文件,提取表名、字段、索引、关联关系
  3. 收集 SQL 与迁移文件(*.sql、Flyway db/migration、Liquibase changelog、Alembic/Prisma/Django migrations)
  4. 扫描缓存设计(Redis key 模式、@Cacheable)
  5. 连接串中的账号密码打码

Step 4:业务梳理 → 04-business-report.md

  1. 基于包/目录结构划分模块,给出每个模块职责
  2. 挑 2-5 条核心业务链路,从入口接口追到 Service 再到底层(DAO/外部调用),文字描述流程
  3. 列出定时任务(@Scheduled/cron/xxl-job)与异步任务(MQ 消费者、@Async)
  4. 列出对外集成点(调谁、被谁调)
  5. 允许用 mermaid 画 1-3 张核心流程图(非必须,复杂项目才画)
  6. 推测性结论必须标注"(推测)"

Step 5:汇总 → 00-overview.md

  • 项目画像(一段话:这是什么系统、用什么技术、规模多大)
  • 规模统计表(源文件数、接口数、表数、依赖数)
  • 4 份报告的链接 + 每份 3-5 条摘要
  • Top 风险/遗留点清单
  • 给接手人的建议阅读顺序

输出规范

  • 默认写入目标项目 docs/backend-analysis/(用户可指定其他路径):

    文件内容
    00-overview.md总览:项目画像 + 4 报告摘要 + 风险 Top
    01-api-report.md接口报告
    02-tech-report.md技术报告
    03-database-report.md数据库报告
    04-business-report.md业务逻辑报告
  • 报告模板详见 references/report-templates.md,必须按模板输出

  • 对话中只输出摘要 + 文件路径,不全文粘贴报告

  • 报告中的结论必须标注来源(path/to/file.java:42),便于核对

注意事项

  1. 排除目录:node_modules/、target/、dist/、build/、.git/、vendor/、__pycache__/、.idea/、.gradle/
  2. 大项目分批:先 Glob 看结构 → 按模块逐个深入,禁止一次性读取全量文件
  3. 只读原则:不修改、不运行目标项目任何代码与脚本
  4. 敏感信息打码:密钥、密码、Token、连接串账密一律 ****
  5. 证据优先:每条结论带来源文件;拿不准的标"(推测)",不编造。目录名/项目名不可信(xxx-back 可能是前端),技术栈以构建文件内容为唯一证据
  6. 鉴权扫描禁限量:Grep 设 head_limit 会漏文件导致误判无鉴权接口;鉴权相关扫描必须不限量,且每个"无鉴权"结论逐端点读函数签名确认
  7. 触发冲突处理:用户要"部署检测/部署画像"时转 deploy-detect-skill,要"生成后端"时转 backend-generate-skill

交付确认

报告生成后,在对话末尾输出:

✅ 后端分析完成,报告已写入 <项目>/docs/backend-analysis/:
- 00-overview.md(总览,建议先读)
- 01-api-report.md(接口 N 个)
- 02-tech-report.md(中间件 N 个 / 第三方 API N 个 / 安全隐患 N 处)
- 03-database-report.md(数据表 N 张)
- 04-business-report.md(模块 N 个 / 核心流程 N 条)

如需深入某个模块或补充运行时验证(如启动项目核对接口),请告诉我。

触发词

backend-analysis、Backend Analysis Skill — 后端项目全景分析

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Backend Analysis Skill AI skill do?

后端项目静态分析技能。不运行项目,直接扫描源码,为 Java(Spring Boot/Spring Cloud)、Go(Gin/Echo)、Python(FastAPI/Django/Flask)、Node.js(Express/NestJS) 项目产出 4 份报告:① 接口报告(全部 API 清单:方法/路径/入参/出参/鉴权)② 技术报告(语言/框架版本、中间件如 Redis/MQ/ES、第三方 API 如短信/支付/推送、架构组件如拦截器/全局异常/全局配置/路由注册)③ 数据库报告(表结构/ORM/索引/迁移脚本)④ 业务逻辑报告(模块划分/核心流程/定时任务/外部集成)。当用户要求"分析后端项目"、"梳理后端接口"、"盘点技术栈"、"出数据库文档"、"接手老项目"、"读懂后端代码"、"backend analysis" 时调用。

Why use Backend Analysis Skill on TypingMind?

Because you install it once and use it with any model. Backend Analysis Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Backend Analysis Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/backend/backend-analysis-skill. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Backend Analysis Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Backend Analysis Skill?

As many as you like. As long as a model supports skills, you can use Backend Analysis Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Backend Analysis Skill AI skill free?

Yes. It is published on GitHub by jiushiwon under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇