Agent skill

Jeecg Codegen New

by jeecgboot in jeecgboot/skills

A skill your agent uses when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模块", "新增功能", "建表", "加字段", "加一个字段"…

Apache-2.0Auto-check passedDevelopment

Install Jeecg Codegen New

skills CLI
$ npx skills add jeecgboot/skills --skill jeecg-codegen-new -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeecgboot/skills jeecg-codegen-new --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeecgboot/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/jeecg-codegen-new .claude/skills/jeecg-codegen-new && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
jeecg-codegen-new
GitHub stars
239
Token cost
~2.4k tokens
SKILL.md length
581 words
Files
285 (incl. scripts, references)
Skills in repo
13
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模块", "新增功能", "建表", "加字段", "加一个字段"…

  • Works in 6 steps: 判断操作类型 → 收集参数(一次性问完) → 展示摘要 → …
  • User asks to generate JeecgBoot CRUD code
  • SKILL.md covers 核心原则, 主数据复用, 接口禁止猜测 and 模板覆盖范围, plus 8 more sections
  • Runs Java and Python scripts from its folder; calls mysql, python and mvn; needs COLUMN_KEY

What it does

Jeecg Codegen New is an agent skill from jeecgboot/skills. Use when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模块", "新增功能", "建表", "加字段", "加一个字段", "增加字段", "新增字段", "修改字段", "删除字段", "generate code", "new entity", "add field"

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 292 other files, including scripts and reference files (for example `references/context-schema.md`, `references/dict-matching.md` and `references/field-mapping.md`).

It sits in Development, covering Project scaffolding. It works with Vue.js and SQL. The repository describes itself as: JeecgBoot Skills — AI 驱动 · 一句话生成全套工件! 在 Claude Code 中,用一句话生成 代码 · 表单 · 流程 · 报表 · 图表 · 大屏 · 仪表盘。 覆盖 JeecgBoot 低代码平台 与 JimuReport 积木报表 两大产品的企业级开发全场景。 The licence is Apache-2.0.

When your agent uses it

  • User asks to generate JeecgBoot CRUD code
  • Create a new module
  • Add/modify fields on existing module

Example prompts

  • “generate code”
  • “new entity”
  • “add field”
  • “/jeecg-codegen-new”

Requirements

  • Python 3
  • A credential in COLUMN_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 判断操作类型
  2. 收集参数(一次性问完)
  3. 展示摘要
  4. 调用脚本
  5. 处理特殊需求(模板没覆盖的部分)
  6. 后续操作

What it can do on your machine

Read from SKILL.md and the folder at commit 12760b9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 3 files in scripts/ (Java and Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • mysql
    • python
    • mvn
    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • COLUMN_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Jeecg Codegen New loads about 2.4k tokens when it runs, and up to ~8.3k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 581 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from jeecgboot/skills at commit 12760b9, republished under its Apache-2.0 licence (© jeecgboot). 581 words, ~2,382 tokens.

Download SKILL.mdSave it as .claude/skills/jeecg-codegen-new/SKILL.md (or your agent's skills folder). This skill also uses 284 other files; get the full folder from GitHub.
name
jeecg-codegen-new
description
Use when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模块", "新增功能", "建表", "加字段", "加一个字段", "增加字段", "新增字段", "修改字段", "删除字段", "generate code", "new entity", "add field"
disable-model-invocation
true

JeecgBoot 代码生成器(Freemarker 驱动)

把用户的自然语言需求转成 Freemarker 上下文 JSON,交给 scripts/codegen.py 调用模板生成全套 CRUD(后端 Java + 前端 Vue3 + 菜单 SQL)。

核心原则

AI 不再从零写代码。 基础代码全部由 jeecg 官方 Freemarker 模板生成,AI 只做三件事:

  1. 拼参数 — 把用户需求映射成 ctx.json
  2. 调脚本 — 跑 scripts/codegen.py 让 Freemarker 出基础代码
  3. 改产物 — 用户提了模板不覆盖的特殊需求时,用 Edit 改已生成的代码

⛔ 禁止修改 templates/ 目录下任何模板文件。模板由 jeecg 官方维护,改了就脱离了升级路径。 ⛔ 禁止绕开脚本直接手写 Entity / Controller / data.ts 等基础文件。

主数据复用

涉及字典、角色、用户、部门时遵循"先查后建",使用 jeecg-system skill。详见 ../jeecg-system/SKILL.md。

接口禁止猜测

所有接口路径/参数必须来自用户提供、jeecg-system skill 文档、或经查询确认。猜测命中也算违规。


模板覆盖范围

不是所有"表类型 × 前端风格"的组合都有模板。先选表类型 → 决定可选的前端风格:

表类型模板 stylePath支持前端风格触发关键词
单表default/onevue3 vue3Native默认
树表default/treevue3 vue3Native分类/层级/树/上下级
一对多 — Tab-in-Modaltab/onetomanyvue3tab风格 / radio切换 / 标题栏切换
一对多 — 内嵌子表inner-table/onetomanyvue3内嵌子表 / 行展开 / expandedRowRender
一对多 — ERPerp/onetomanyvue3 vue3NativeERP风格 / 独立编辑
一对多 — JVxeTablejvxe/onetomanyvue3 vue3NativeJVxe / JVxeTable / 可编辑表格 / 行内编辑

不支持的组合: default/onetomany 无 vue3 模板,用户若要此布局改推荐 tab 或 inner-table。Vue 2 模板均不收录。详见 template-diff.md。


交互流程

Step 0 — 判断操作类型
  • 关键词 "加字段 / 删字段 / 改字段 / 给XX加" → 增量修改(跳到本文末"增量修改"章节)
  • 其他 → 全量生成
Step 1 — 收集参数(一次性问完)

⛔ **铁律:**Step 2 摘要被用户明确确认前,禁止调脚本、禁止落地任何文件、禁止执行任何 SQL。 "需求很清楚了""都用默认值""先生成再改" 都是合理化跳过确认的借口,全部无效。

向用户一次问全所有缺失项(已知项可填默认值并标注"如无异议保留"):

项默认值 / 提示
后端模块根<backend_root>(如 D:/jeecgboot/jeecg-module-system/jeecg-system-biz)
前端项目根<frontend_root>(如 D:/jeecgboot-vue3)
Flyway SQL 目录<backend>/jeecg-module-system/jeecg-system-start/src/main/resources/flyway/sql/mysql
bussiPackageorg.jeecg.modules
entityPackage由用户给(如 biz / edu)
entityName / tableName由用户给或推导(如 BizGoods / biz_goods)
描述(中文)用户业务名(如"商品管理")
表类型单表 / 树表 / 一对多
一对多风格仅一对多需要:tab / inner-table / erp
前端风格vue3 或 vue3Native(结合表类型用上表校验是否支持)
字段清单已有表 → 查 DDL 自动取;新建表 → 由用户描述
字典自动匹配默认是。开启后会查 sys_dict 自动套字典编码(见下方"字典匹配")
目标数据库名仅"已有表/字典查询/本地执行 SQL"时需要,必须由用户确认
Step 2 — 展示摘要

把构造好的 ctx.json 用表格展示给用户:

  • 表头:表名、实体名、风格、前端风格、字段数
  • 字段表:fieldName / fieldDbName / 注释 / fieldDbType / classType / 字典 / 必填 / 列表显示 / 表单显示 / 查询
  • 不要 dump 整个 JSON,太冗长

明确询问 "是否生成?" — 收到 "确认 / ok / 可以 / 没问题" 等表述后才进入 Step 3。

Step 3 — 调用脚本

调用前先把构造好的 JSON 写到临时目录(路径规则见下方"临时配置文件规则"),然后用绝对路径调脚本。

SKILL 路径定位: 脚本永远在 <SKILL_ROOT>/scripts/codegen.py。<SKILL_ROOT> 就是包含 SKILL.md 的那个目录,比如 C:\Users\moe\.claude\skills\jeecg-codegen-new 或 E:\Projects\BJGJ\jeecg-skills\jeecg-codegen-new——你能加载 SKILL.md 就能得出这个路径,不要再去 Read codegen.py 来确认任何东西,下面的 CLI 参考就是脚本的完整契约。

完整 CLI 参考
python <SKILL_ROOT>/scripts/codegen.py [OPTIONS]
参数必填默认取值说明
--style✅—default/one default/tree default/onetomany tab/onetomany inner-table/onetomany erp/onetomany模板风格,见"模板覆盖范围"表
--ctx✅—文件路径ctx.json 路径,必须在 {tempdir}/jeecg-codegen-new/<表名>_ctx.json
--frontend-style🟡vue3vue3 vue3Native必须与 --style 兼容,否则脚本拒绝(详见"模板覆盖范围"表)
--backend-root🟡—后端模块根比如 D:/jeecgboot/jeecg-module-system/jeecg-system-biz,脚本会自动拼 /src/main/java/<bussiPackage>/<entityPackage>/
--frontend-root🟡—前端项目根比如 D:/jeecgboot-vue3,脚本会自动拼 /src/views/<entityPackage>/
--mobile-root❌—uniapp 项目根不传则跳过 uniapp/uniapp3 产物——常规需求都不需要传
--flyway-dir🟡—Flyway SQL 目录菜单 SQL 落到这里;同名 SQL 自动去重
--out❌—任意目录调试用:渲染产物原样落到此目录,跳过分发。设了它就不需要 backend/frontend/flyway-root
--dry-run❌falseflag打印分发计划但不写文件

🟡 = 在没有 --out 的"正常模式"下,至少要传 --backend-root 或 --frontend-root 或 --flyway-dir 之一(任何没传的目录类型对应的产物都被跳过);正常代码生成场景三个都该传。

✅ = 任何模式都必填。

退出码 & 输出
  • 退出码 0 = 成功;其他都失败(参数非法、Java 编译失败、Freemarker 渲染异常)
  • 标准输出每行一个事件:[codegen] WROTE <绝对路径>、[codegen] WOULD WRITE ...(dry-run 时)、[codegen] running FtlRunner … 等
  • 失败时 stderr 含完整 Java 栈或 [codegen] xxx 错误信息
典型调用(复制后改 4 个值即可)
bash
python E:/Projects/BJGJ/jeecg-skills/jeecg-codegen-new/scripts/codegen.py \
  --style default/one \
  --ctx /c/Users/moe/AppData/Local/Temp/jeecg-codegen-new/biz_goods_ctx.json \
  --backend-root D:/jeecgboot/jeecg-module-system/jeecg-system-biz \
  --frontend-root D:/jeecgboot-vue3 \
  --frontend-style vue3 \
  --flyway-dir D:/jeecgboot/jeecg-module-system/jeecg-system-start/src/main/resources/flyway/sql/mysql
Show full SKILL.md (236 more words)Show less

临时配置文件规则(强制)

所有传给脚本的 --ctx <xxx.json> 必须写到 {系统临时目录}/jeecg-codegen-new/ 下,由操作系统自动清理;skill 与脚本均不主动删除该目录或文件。

python
import tempfile, os, json

SKILL_NAME = "jeecg-codegen-new"
skill_dir = os.path.join(tempfile.gettempdir(), SKILL_NAME)
os.makedirs(skill_dir, exist_ok=True)          # 确保目录存在,不主动检查

config_path = os.path.join(skill_dir, 'biz_goods_ctx.json')   # 示例文件名:<表名>_ctx.json
with open(config_path, 'w', encoding='utf-8') as f:
    json.dump(cfg, f, ensure_ascii=False, indent=2)

tempfile.gettempdir() 自动适配:Windows %TEMP%、Linux /tmp、macOS /var/folders/.../T(注意 macOS 并非 /tmp)。 文件名建议使用 <表名>_<步骤>.json(如 biz_goods_ctx.json / biz_goods_alter.json),无需重复技能前缀,因路径已包含技能名称,便于排错。

❌ 禁止:

  • 写到 <skill>/tmp/ 或当前工作目录(污染 skill / 用户项目)
  • 硬编码 /tmp、C:\Temp 或任何固定路径(不跨平台)
  • 每步完成后主动 rm / Remove-Item(操作系统会清理,属多余 tool call)
  • 主动 os.path.exists() 检查(其本身即为一次 tool call) (使用 os.makedirs(…, exist_ok=True) 满足需求,不算主动检查)

临时文件可能被操作系统异步清理,但仍遵循 乐观调用 + 报错补救:仅当脚本返回 FileNotFoundError 或 配置文件不存在 时,使用相同内容、在相同的 {系统临时目录}/jeecg-codegen-new/ 路径下重写(重写前仍需 os.makedirs(skill_dir, exist_ok=True) 确保目录存在),切勿更换路径或回退至 skill 目录。

Step 4 — 处理特殊需求(模板没覆盖的部分)

用户的需求经常超出模板能力(比如"商品名要带前缀生成""价格变更后自动算总价""列表行加复制按钮"),这时:

  1. 先跑脚本生成基础代码
  2. 再用 Read 读出对应文件、用 Edit 做精细修改
  3. 不要改 templates/,永远改产物

常见的特殊需求与改动位置参考 references/post-edit-recipes.md。

Step 5 — 后续操作
  • Flyway SQL:脚本已落到 <flyway-dir>/V<date>_1__menu_insert_<entity>.sql,重启后端时 Flyway 自动执行;如果用户要求立即生效,按"本地自动执行 SQL"流程做(见下方)。
  • 重启后端:提示用户 mvn spring-boot:run -pl jeecg-module-system/jeecg-system-start
  • 前端热更新:pnpm dev 自动热更,无需重启
  • 菜单可见:默认授权 admin,登录系统直接可见

字段语义推导

新建表时,AI 需要把用户描述的字段(如"价格"、"备注")映射到合适的 classType / fieldDbType / fieldType。映射表见 references/field-mapping.md。

已有表场景下,从 DDL 直接读类型,不依赖语义推导。

已有表反向生成

用户给了表名 → 必须先查数据库取 DDL 再构造 ctx:

bash
# 询问用户目标数据库名后,一条命令拿全部信息
mysql --no-defaults --default-character-set=utf8mb4 -h127.0.0.1 -P3306 -uroot -proot {dbname} \
  -e "SHOW CREATE TABLE 表名\G" \
  -e "SELECT COLUMN_NAME, COLUMN_TYPE, IS_NULLABLE, COLUMN_DEFAULT, COLUMN_COMMENT, COLUMN_KEY, EXTRA FROM information_schema.COLUMNS WHERE TABLE_SCHEMA='{dbname}' AND TABLE_NAME='表名' ORDER BY ORDINAL_POSITION"

⛔ 执行任何 SQL 前必须先询问用户目标数据库名,不要从 application-dev.yml 自动取——用户本机可能多库并存。

字典自动匹配

用户开启后,先查全部字典:

bash
mysql ... -e "
SELECT d.dict_code, d.dict_name,
       GROUP_CONCAT(i.item_text, '=', i.item_value ORDER BY i.sort_order SEPARATOR ', ') AS items
FROM sys_dict d LEFT JOIN sys_dict_item i ON d.id = i.dict_id AND i.status = 1
WHERE d.del_flag = 0 GROUP BY d.dict_code, d.dict_name ORDER BY d.dict_code"

匹配优先级:用户明确指定 > 字段名等于 dict_code > 注释关键词命中 dict_name > 不匹配。

匹配后在 ctx 的 column 上设置 classType: "list" + dictField: "<dict_code>",模板会自动展开成 @Dict + JDictSelectTag + dataIndex: "fieldName_dictText" 等完整代码。

更详细见 references/dict-matching.md。

本地自动执行菜单 SQL(仅 127.0.0.1 / localhost)

用户确认目标数据库后:

bash
# 1. 检查主菜单是否已存在(避免重复插入)
mysql ... -e "SELECT id FROM sys_permission WHERE name='<描述>' AND parent_id IS NULL"
# 2. 不存在则执行
mysql ... < <flyway_sql_file_path>

执行失败时只提示,不中断流程——Flyway 文件已落地,下次重启会自动执行。


增量修改(加 / 删 / 改字段)

所有"模板已生成的代码 + 用户后续小调整"都走 Edit,不重新跑脚本。

Step A — 定位文件
bash
# Entity
find <backend_root>/src/main/java -name "<EntityName>.java"
# 前端 data.ts
find <frontend_root>/src/views -name "<EntityName>__data.ts"

需要读:Entity.java / *__data.ts / *List.vue / *Modal.vue / *Form.vue(vue3Native)。

Step B — 推导新字段属性

参考 references/field-mapping.md。

Step C — 展示摘要 → 等用户确认 → 执行 Edit

加字段:在所有相关文件追加;删字段:精确删除;改字段:定位修改。 ALTER TABLE 写到新的 Flyway SQL(版本号递增)。

不要因为"加一个字段"就重新跑全量代码生成,会覆盖用户对生成结果的手工修改。


文件夹与脚本

路径说明
templates/jeecg 官方 Freemarker 模板(只读)
lib/freemarker.jar + fastjson2.jar
scripts/codegen.py主入口(Python3)
scripts/FtlRunner.javaJava 渲染器(首次运行自动 javac)
scripts/.cache/编译产物 + 临时 ctx
references/field-mapping.md字段语义 → Freemarker 字段映射
references/context-schema.mdctx.json 完整 schema
references/post-edit-recipes.md模板没覆盖的特殊需求改动位置
references/dict-matching.md字典匹配规则与 ctx 映射
references/template-diff.mdSKILL 模板与后端源目录的差异记录及原因

依赖:java(JDK 8+)+ python3(3.9+,类型注解用了 PEP 585 语法)。脚本会自动探测 javac 版本:JDK 8 用 -source 8 -target 8,JDK 9+ 用 --release 8,最终编译产物始终为 Java 8 字节码(major=52)。

© jeecgboot, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 284 other files (scripts, references) in jeecg-codegen-new of jeecgboot/skills.

  • SKILL.md
  • lib/fastjson2.jar
  • lib/freemarker-2.3.32.jar
  • references/context-schema.md
  • references/dict-matching.md
  • references/field-mapping.md
  • references/post-edit-recipes.md
  • references/template-diff.md
  • scripts/.cache/.gitignore
  • scripts/FtlRunner.java
  • scripts/codegen.py
  • templates/common/blob.ftl
  • templates/common/form/native/vue3NativeComponents.ftl
  • … and 272 more

Open the folder on GitHubat commit 12760b9

Compare with similar skills

Jeecg Codegen New next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Jeecg Codegen New compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jeecg Codegen New this skilljeecgboot/skills239—~2.4kAutomated safety check: PassApache-2.0
Code Nest Project Specxiaou61/Code-Nest770—~1.3kAutomated safety check: PassMIT
Mock CodegenChenyCHENYU/Robot_Admin1k—~1.2kAutomated safety check: PassMIT
Page CodegenChenyCHENYU/Robot_Admin1k—~3.5kAutomated safety check: PassMIT
Add Componentindielayer/ui222—~293Automated safety check: PassMIT
Cabloy Frontend Scaffoldcabloy/cabloy982—~4.1kAutomated safety check: PassMIT

Similar skills

  • Code Nest Project Spec

    xiaou61/Code-Nest

    Code-Nest 多模块全栈项目协作规范与落点导航。Use when modifying this repository for feature development, bug fixing, refactor, API change, SQL migration, or frontend-backend联调 so changes land in the correct module…

    770 GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Mock Codegen

    ChenyCHENYU/Robot_Admin

    A skill your agent uses when: generating mock data for development without a backend.

    1k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Page Codegen

    ChenyCHENYU/Robot_Admin

    A skill your agent uses when: generating Vue 3 page code from either a page-spec JSON or a natural language description.

    1k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Add Component

    indielayer/ui

    Add a new Vue component to @indielayer/ui with themes, tests, docs, and registry exports.

    222 GitHub stars~293 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • A skill your agent uses whenever the user wants the Zova frontend path in this Cabloy repo: create or extend pages, components, api or model beans, route/query/params work, metadata refresh…

    982 GitHub stars~4.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Fe Tools Template Recommender

    MichealWayne/fe-tools

    Recommend the most suitable project template or initialization path from fe-tools project-templates based on product, framework, runtime, and delivery constraints.

    207 GitHub stars~1k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from jeecgboot/skills

All 13 skills in this repo
  • Jeecg System

    jeecgboot/skills

    JeecgBoot 系统主数据查询与管理。Use when user asks to query/create/manage system master data, or says "查询角色", "查询用户", "查询部门", "查询字典", "创建字典", "创建角色", "查岗位", "查职务", "查租户", "查数据源", "查定时任务", "系统主数据", "query…

    239 GitHub stars~3.2k tokensUpdated 21 days ago
    Auto-check passed
  • Jeecg Bpmn

    jeecgboot/skills

    A skill your agent uses when user asks to create/generate/edit/modify a BPM workflow, design a Flowable BPMN process, or says "创建流程", "生成流程", "新建流程", "设计流程", "画流程", "审批流程", "工作流", "BPM", "BPMN"…

    239 GitHub stars~17k tokensUpdated 21 days ago
    Auto-check passed
  • Jeecg Onlreport

    jeecgboot/skills

    A skill your agent uses when user asks to create/edit/query Online reports, SQL reports, data reports, or says "创建报表", "生成报表", "新建报表", "查询报表", "online报表", "SQL报表", "数据报表", "统计报表", "create report"…

    239 GitHub stars~5.8k tokensUpdated 21 days ago
    Auto-check passed
  • Jimureport

    jeecgboot/skills

    积木报表生成器 — 自然语言描述报表需求或提供截图,自动生成积木报表(支持数据报表、打印报表、分组报表、循环报表、数据填报等全类型)。Use when user says "积木报表", "jmreport", "Excel报表", "数据填报", "可视化报表", "打印报表", "分组报表", "循环报表", "按照截图生成报表", "创建积木报表", "做一个可视化报表"…

    239 GitHub stars~13k tokensUpdated 21 days ago
    Auto-check passed
  • Jeecg Aiflow

    jeecgboot/skills

    JeecgBoot AI 编排流程(AIFlow)全生命周期管理——通过自然语言描述需求,自动创建、编辑、查询、删除、调试、发布 AI 编排流程。

    239 GitHub stars~4.1k tokensUpdated 21 days ago
    Auto-check passed
  • Jeecg Portal

    jeecgboot/skills

    JeecgBoot 门户(Portal)全生命周期管理——通过 API 自动创建、删除、配置门户,管理门户内的 14 种组件(轮播图、新闻动态、系统公告、流程中心、应用快捷入口、协同待办、我的计划、知识库、文本、iframe 等),动态查询数据源并填充组件内容,支持 Web 和 App 双端布局。

    239 GitHub stars~2k tokensUpdated 21 days ago
    Auto-check passed

Works with

Categories

Questions about Jeecg Codegen New

What does Jeecg Codegen New do?

A skill your agent uses when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模块", "新增功能", "建表", "加字段", "加一个字段"…. Jeecg Codegen New is an agent skill from jeecgboot/skills.

When should I use Jeecg Codegen New?

Jeecg Codegen New fits situations like: user asks to generate JeecgBoot CRUD code; create a new module; add/modify fields on existing module.

How do I install Jeecg Codegen New in Claude Code?

Run `npx skills add jeecgboot/skills --skill jeecg-codegen-new -a claude-code`. Or copy the skill folder (jeecg-codegen-new in jeecgboot/skills) into .claude/skills/jeecg-codegen-new in your project. Claude Code loads it when a task matches its description.

How do I install Jeecg Codegen New in Codex?

Run `npx skills add jeecgboot/skills --skill jeecg-codegen-new -a codex`. Or copy the skill folder (jeecg-codegen-new in jeecgboot/skills) into .agents/skills/jeecg-codegen-new in your project. Codex loads it when a task matches its description.

Can I use Jeecg Codegen New in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeecgboot/skills --skill jeecg-codegen-new -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jeecg-codegen-new, .gemini/skills/jeecg-codegen-new, .github/skills/jeecg-codegen-new and .opencode/skills/jeecg-codegen-new in your project.

What does Jeecg Codegen New need to run?

Going by SKILL.md and its folder, Jeecg Codegen New needs Java and Python for the scripts in its folder, the command-line tools its instructions call (mysql, python, mvn and pnpm) and credentials named COLUMN_KEY. Our summary lists: Python 3; A credential in COLUMN_KEY.

Does Jeecg Codegen New access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Jeecg Codegen New safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Jeecg Codegen New use?

Jeecg Codegen New is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Jeecg Codegen New use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.9k tokens, read only when the agent opens those files.

What are the alternatives to Jeecg Codegen New?

Skills that share tags, products or a category with Jeecg Codegen New: Code Nest Project Spec (xiaou61/Code-Nest, 770 stars), Mock Codegen (ChenyCHENYU/Robot_Admin, 1k stars), Page Codegen (ChenyCHENYU/Robot_Admin, 1k stars) and Add Component (indielayer/ui, 222 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jeecg Codegen New?

jeecgboot (a GitHub organization) maintains it in jeecgboot/skills, which has 239 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 17, 2026.

Source: jeecgboot/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.