Agent skill

Jeecg System

by jeecgboot in 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…

Apache-2.0Auto-check passedData & Analytics

Install Jeecg System

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

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

GitHub CLI
$ gh skill install jeecgboot/skills jeecg-system --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-system .claude/skills/jeecg-system && 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-system
GitHub stars
239
Token cost
~3.2k tokens
SKILL.md length
467 words
Files
4 (incl. scripts, references)
Skills in repo
13
Repo updated
First seen
Licence
Apache-2.0

At a glance

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…

  • Works in 2 steps: API 地址:JeecgBoot 后端地址(如… → X-Access-Token:JWT 登录令牌(从浏览器 F12 获取)
  • User asks to query/create/manage system master data
  • SKILL.md covers 前置条件, 核心原则:先查后建, 使用方式 and 典型场景, plus 2 more sections
  • Runs Python scripts from its folder; calls python; reaches boot3.jeecg.com

What it does

Jeecg System is an agent skill from 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 roles", "query users", "query depts", "create dict", "create role", "master data". Also triggers when other skills (desform, bpmn, codegen) need to look up or create roles, users, departments, dictionaries, or positions as dependencies — follows "先查后建" (query-first-create-later) principle.

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/api-reference.md`, `scripts/system_creator.py` and `scripts/system_utils.py`).

It sits in Data & Analytics, covering Data governance and Project scaffolding. 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 query/create/manage system master data
  • Other skills (desform
  • Codegen) need to look up
  • Positions as dependencies — follows 先查后建 (query-first-create-later) principle

Example prompts

  • “query roles”
  • “query users”
  • “query depts”
  • “/jeecg-system”

Requirements

  • Python 3

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. API 地址:JeecgBoot 后端地址(如 https://boot3.jeecg.com/jeecgboot)
  2. X-Access-Token:JWT 登录令牌(从浏览器 F12 获取)

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 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • boot3.jeecg.com

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Jeecg System loads about 3.2k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 124 tokens; SKILL.md has 467 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~124
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~12k

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). 467 words, ~3,248 tokens.

Download SKILL.mdSave it as .claude/skills/jeecg-system/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
jeecg-system
description
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 roles", "query users", "query depts", "create dict", "create role", "master data". Also triggers when other skills (desform, bpmn, codegen) need to look up or create roles, users, departments, dictionaries, or positions as dependencies — follows "先查后建" (query-first-create-later) principle.

JeecgBoot 系统主数据查询与管理

查询和管理 JeecgBoot 系统中的角色、用户、部门、字典等主数据。遵循"先查后建"原则:优先使用系统已有数据,没有才创建。

前置条件

用户必须提供以下信息(或由 AI 引导确认):

  1. API 地址:JeecgBoot 后端地址(如 https://boot3.jeecg.com/jeecgboot)
  2. X-Access-Token:JWT 登录令牌(从浏览器 F12 获取)

如果用户未提供,提示:

请提供 JeecgBoot 后端地址和 X-Access-Token(从浏览器 F12 → Network → 任意请求的 Request Headers 中复制)。

核心原则:先查后建

在任何 skill(流程设计、表单设计、代码生成等)需要使用主数据时,必须先查询系统已有数据,确认不存在后才创建新数据。

数据类型查询函数创建函数一站式函数
角色query_roles() / find_role()create_role()find_or_create_role()
角色绑定用户—add_users_to_role(role_id, user_ids)—
审批角色query_approval_roles() / find_approval_role()create_approval_role_group() + create_approval_role()find_or_create_approval_role()
审批角色绑定用户—add_users_to_approval_role(role_id, user_ids)—
用户query_users() / find_user()——
部门query_depts() / find_dept()——
岗位query_dept_positions()——
字典(普通)query_dict() / search_dict() / find_dict()create_dict()find_or_create_dict()
字典(SQL表)query_sql_table_dict()——

使用方式

脚本位置
  • scripts/system_creator.py — 通用命令行脚本(推荐,无需生成临时 .py)
  • scripts/system_utils.py — 工具库(供其他 skill 脚本 import)
方式一:通用脚本 + 命令行(推荐)

单项查询(直接命令行,无需配置文件):

bash
SCRIPT="<skill目录>/jeecg-system/scripts/system_creator.py"
API="<api_base>"
TOKEN="eyJ..."

# 查询角色列表
python "$SCRIPT" --api-base $API --token $TOKEN --action query-roles
python "$SCRIPT" --api-base $API --token $TOKEN --action query-roles --keyword 经理

# 查询用户列表
python "$SCRIPT" --api-base $API --token $TOKEN --action query-users --keyword 张

# 查询部门树
python "$SCRIPT" --api-base $API --token $TOKEN --action query-depts
python "$SCRIPT" --api-base $API --token $TOKEN --action query-depts --keyword 研发

# 查询字典列表
python "$SCRIPT" --api-base $API --token $TOKEN --action query-dicts --keyword 请假

# 查询字典项
python "$SCRIPT" --api-base $API --token $TOKEN --action query-dict --code sex

# 查询职务列表
python "$SCRIPT" --api-base $API --token $TOKEN --action query-positions

# 查询部门+岗位树
python "$SCRIPT" --api-base $API --token $TOKEN --action query-dept-positions

# 查询审批角色
python "$SCRIPT" --api-base $API --token $TOKEN --action query-approval-roles

# 查询租户列表
python "$SCRIPT" --api-base $API --token $TOKEN --action query-tenants

# 查询数据源
python "$SCRIPT" --api-base $API --token $TOKEN --action query-datasources

# 查询定时任务
python "$SCRIPT" --api-base $API --token $TOKEN --action query-quartz-jobs

# 查询分类字典
python "$SCRIPT" --api-base $API --token $TOKEN --action query-categories --code B01

# 输出结果到 JSON 文件
python "$SCRIPT" --api-base $API --token $TOKEN --action query-roles --output roles.json

批量查找/创建(JSON 配置文件):

bash
# 1. Write 工具写入 JSON 配置文件
# 2. 执行脚本
python "$SCRIPT" --api-base $API --token $TOKEN --config master_data.json
# 3. 删除临时 JSON 文件

JSON 配置格式:

json
{
  "roles": [
    {"roleName": "部门经理", "roleCode": "dept_manager"},
    {"roleName": "HR专员", "roleCode": "hr"}
  ],
  "dicts": [
    {
      "dictCode": "leave_type",
      "dictName": "请假类型",
      "items": [
        {"value": "1", "text": "事假"},
        {"value": "2", "text": "病假"},
        {"value": "3", "text": "年假"}
      ]
    }
  ],
  "users": [
    {"keyword": "admin"},
    {"username": "zhangsan"}
  ],
  "depts": [
    {"keyword": "研发部"},
    {"departName": "人力资源部"}
  ],
  "positions": [
    {"keyword": "总经理"}
  ]
}

脚本自动完成:

  • 角色/字典:先查后建(已有则跳过,没有则创建)
  • 用户/部门/职务:只查不建(返回查询结果)
  • 汇总输出所有查找/创建结果
  • 可通过 --output result.json 保存结果
方式二:在临时脚本中 import 工具库
python
import sys, os
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'jeecg-system', 'scripts'))
# 或直接用绝对路径: sys.path.insert(0, r'<skill目录>/jeecg-system/scripts')
from system_utils import *

init_api('<api_base>', '<token>')

# ====== 角色 ======
# 查询所有角色
roles = query_roles()
# 按名称模糊查询
roles = query_roles(keyword='经理')
# 查找单个角色
role = find_role('manager')  # 按编码或名称
# 查找或创建(推荐)
role_code = find_or_create_role('项目经理', 'project_manager')

# ====== 用户 ======
# 查询用户列表
users = query_users(keyword='张')
users = query_users(username='admin')
# 查找单个用户
user = find_user('admin')  # 按用户名或姓名

# ====== 部门 ======
# 查询部门树
depts = query_depts()
depts = query_depts(keyword='研发')
# 查找单个部门
dept = find_dept('研发部')
# 查询部门+岗位树
positions = query_dept_positions()

# ====== 字典 ======
# 查询字典项(普通字典,通过 /sys/api/getDictItems)
items = query_dict('sex')  # → [{'value': '1', 'text': '男'}, ...]
# 查询 SQL 表字典项(通过 /sys/dict/getDictItems/{dictCode},需签名)
items_sql = query_sql_table_dict("sys_user,realname,id,username!='admin' order by create_time")
# 搜索字典(按名称/编码模糊匹配)
dicts = search_dict('请假')
# 查找字典(含字典项)
d = find_dict('sex')  # → {'dictCode': 'sex', 'dictName': '性别', 'items': [...]}
# 查找或创建字典(推荐)
dict_code = find_or_create_dict('leave_type', '请假类型', [
    {'value': '1', 'text': '事假'},
    {'value': '2', 'text': '病假'},
    {'value': '3', 'text': '年假'},
])

# ====== 系统角色绑定用户 ======
# 创建角色并自动绑定 admin(默认行为)
role_code = find_or_create_role('财务审核', 'finance_audit')
# 不绑定 admin
role_code = find_or_create_role('只读角色', 'readonly', add_admin=False)
# 手动绑定用户到角色
role = find_role('finance_audit')
add_users_to_role(role['id'], ['e9ca23d68d884d4ebb19d07889727dae'])

# ====== 审批角色 ======
# 一站式:查找或创建审批角色(自动创建分组 + 角色 + 绑定 admin)
role_id = find_or_create_approval_role('财务审批专员', group_name='财务分组')
# 分步创建
group_id = create_approval_role_group('HR分组')
role_id  = create_approval_role('HR审批专员', group_id, add_admin=True)
# 查询审批角色
res  = query_approval_roles('财务')   # {'roles': [...], 'persons': [...]}
role = find_approval_role('财务审批') # 单个或 None

# ====== 便捷打印 ======
print_roles()           # 打印角色列表
print_users(keyword='张')  # 打印用户列表
print_depts()           # 打印部门树
print_dict('sex')       # 打印字典项
print_dicts('请假')     # 搜索并打印字典列表
在其他 skill 脚本中使用

其他 skill 的脚本可以直接导入 system_utils(需先加载 jeecg-system skill,从 Base directory for this skill: <skill_base_dir> 取得路径):

python
import sys
sys.path.insert(0, r'<skill_base_dir>\scripts')
from system_utils import init_api, find_or_create_role, find_or_create_dict, query_dict, query_sql_table_dict

init_api(API_BASE, TOKEN)

# 流程设计时查询角色编码
role_code = find_or_create_role('部门经理', 'dept_manager')

# 表单设计时查询普通字典
items = query_dict('sex')

# 查询 SQL 表字典(带签名)
items_sql = query_sql_table_dict("sys_user,realname,id,username!='admin' order by create_time")

# 创建字典
dict_code = find_or_create_dict('leave_type', '请假类型', [
    {'value': '1', 'text': '事假'},
    {'value': '2', 'text': '病假'},
])

典型场景

场景1:流程审批人配置角色
python
# 需要配置"部门经理"角色作为审批人
role_code = find_or_create_role('部门经理', 'dept_manager')
# → 系统已有则返回现有编码,没有则创建后返回
# 在 BPMN 中使用: candidateGroups="{role_code}", groupType="role"
场景2:表单下拉字段配置字典
python
# 需要"请假类型"字典
d = find_dict('leave_type')
if d:
    print(f'已有字典: {d["dictCode"]}, {len(d["items"])} 项')
    # 直接使用现有字典编码
else:
    # 创建新字典
    find_or_create_dict('leave_type', '请假类型', [
        {'value': '1', 'text': '事假'},
        {'value': '2', 'text': '病假'},
    ])
场景3:查询部门/用户信息
python
# 查找用户用于流程指定审批人
user = find_user('张三')
if user:
    username = user['username']  # 用于 flowable:assignee

# 查找部门用于审批配置
dept = find_dept('人力资源部')
if dept:
    dept_id = dept['id']  # 用于 candidateGroups, groupType="dept"

API 接口速查

完整接口文档见 references/api-reference.md

各模块基础路径
模块基础路径Controller
用户/sys/userSysUserController
角色/sys/roleSysRoleController
部门(公司/子公司/岗位)/sys/sysDepartSysDepartController
职务/职级/sys/positionSysPositionController
字典/sys/dictSysDictController
字典项/sys/dictItemSysDictItemController
租户/sys/tenantSysTenantController
分类字典/sys/categorySysCategoryController
数据源/sys/dataSourceSysDataSourceController
定时任务/sys/quartzJobQuartzJobController
审批角色/sys/approvalRoleApprovalRoleController
用户组/sys/ugroupSysUserGroupController
菜单权限/sys/permissionSysPermissionController
通知公告/sys/annountCementSysAnnouncementController
高频接口(system_utils.py 已封装)
接口方法说明对应函数
/sys/role/listGET角色列表(分页)query_roles()
/sys/role/addPOST创建系统角色create_role()
/sys/user/addSysUserRolePOST角色绑定用户(body: {roleId, userIdList})add_users_to_role()
/sys/approvalRole/searchGET搜索审批角色(需传 keyword=)query_approval_roles()
/sys/approvalRole/rootListGET审批角色分组列表—
/sys/approvalRole/childListGET分组下审批角色列表(需传 pid=)—
/sys/approvalRole/group/addPOST创建审批角色分组(body: {name, pid:"0"})create_approval_role_group()
/sys/approvalRole/role/addPOST创建审批角色(body: {name, pid:groupId})create_approval_role()
/sys/approvalRoleUser/addPOST审批角色绑定用户(body: {approvalRoleId, userIds, bizScope, includeSub})add_users_to_approval_role()
/sys/user/listGET用户列表(分页)query_users()
/sys/sysDepart/queryTreeListGET部门树query_depts()
/sys/sysDepart/queryDepartAndPostTreeSyncGET部门+岗位树query_dept_positions()
/sys/dict/listGET字典列表(分页)search_dict()
/sys/dict/addPOST创建字典create_dict()
/sys/api/getDictItems?dictCode=GET查询字典项(普通字典)query_dict()
/sys/dict/getDictItems/{dictCode}GET查询 SQL 表字典项(需签名)query_sql_table_dict()
/sys/dictItem/addPOST创建字典项create_dict() 内部调用
Show full SKILL.md (212 more words)Show less
常用查询接口(尚未封装,可直接调 _request())
接口方法说明
/sys/role/queryallGET全部角色(租户隔离)
/sys/role/queryallNoByTenantGET全部角色(不做租户隔离)
/sys/user/queryByIdGET按ID查用户
/sys/user/queryByIdsGET按多ID批量查用户
/sys/user/queryUserRoleGET查用户拥有的角色
/sys/user/selectUserListGET流程用户选择组件查询
/sys/sysDepart/searchByGET关键词搜索部门
/sys/sysDepart/queryDepartTreeSyncGET异步加载部门树节点
/sys/sysDepart/getDepartmentHeadGET部门负责人列表
/sys/position/listGET职务列表
/sys/position/queryByCodeGET按code查职务
/sys/dict/getDictText/{code}/{key}GET获取字典文本值
/sys/dict/loadDict/{code}GET下拉搜索异步加载字典
/sys/category/loadTreeRootGET分类字典根节点列表(必须传 async=false&pcode=)
/sys/category/loadAllDataGET指定节点的子节点列表(必须传 code=<节点code>)
/sys/category/addPOST创建分类节点(body: {pid, name},禁止传 code,后端自动生成)
/sys/category/deleteDELETE删除分类节点(param: id=)
/sys/tenant/listGET租户列表
/sys/tenant/getCurrentUserTenantGET当前用户所有租户
/sys/dataSource/listGET数据源列表
/sys/quartzJob/listGET定时任务列表
/sys/quartzJob/pauseGET暂停任务
/sys/quartzJob/resumeGET启动任务
/sys/quartzJob/executeGET立即执行一次
/sys/permission/listGET菜单列表
/sys/permission/queryRolePermissionGET查角色权限
/sys/approvalRole/searchGET搜索审批角色
主要数据结构

SysUser: id, username, realname, password, avatar, birthday, sex(1男/2女), email, phone, orgCode, status(0冻结/1正常), post(岗位ID), userIdentity(1普通/2上级)

SysRole: id, roleName, roleCode, description, tenantId

SysDepart: id, parentId, departName, orgCode, orgCategory(1公司/4子公司/2部门/3岗位), departOrder

SysPosition: id, code, name, postLevel(1高管/2中层/3基层/4实习)

SysDict: id, dictName, dictCode, description

SysDictItem: id, dictId, itemText, itemValue, itemColor, sortOrder, status(0禁用/1启用)

SysTenant: id, name, beginDate, endDate, status(0禁用/1正常)

SysCategory: id, pid, name, code(code 由后端自动生成,禁止在 add 请求中传入,根节点示例 B06,子节点示例 B06A01)

⚠️ 分类字典创建规则:

  1. 禁止传 code:/sys/category/add 的 body 只传 pid 和 name,不要传 code,后端会自动按层级规则生成(根节点 B06、子节点 B06A01...)。
  2. 获取生成的 code:add 接口在新版本会在 result 中返回 code,但老版本不返回。如果响应 result 为 null 或不含 code,必须立即调用 loadTreeRoot(根节点)或 loadAllData(子节点)主动查询,拿到 code 后再继续创建子级,不可假设或跳过。
  3. 查询接口参数:loadTreeRoot 必须传 async=false&pcode=(pcode 为空字符串表示根节点);loadAllData 必须传 code=<父节点的code>。
  4. 删除用 DELETE 方法:/sys/category/delete 需要 HTTP DELETE,传 param id=。

QuartzJob: id, jobClassName, cronExpression, parameter, description, status(0停用/-1删除/1运行)

源码位置

  • 前端API:各模块下的 *.api.ts 文件(如 user/user.api.ts, role/role.api.ts)

© 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 3 other files (scripts, references) in jeecg-system of jeecgboot/skills.

  • SKILL.md
  • references/api-reference.md
  • scripts/system_creator.py
  • scripts/system_utils.py

Open the folder on GitHubat commit 12760b9

Compare with similar skills

Jeecg System 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 System compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jeecg System this skilljeecgboot/skills239—~3.2kAutomated safety check: PassApache-2.0
Setup Workspaceprobabl-ai/skills138—~2kAutomated safety check: PassBSD-3-Clause
Name Framework Migration Third Stepopensanctions/opensanctions834—~904Automated safety check: PassMIT
Flowfile Frame And CodegenEdwardvaneechoud/Flowfile385—~12kAutomated safety check: PassMIT
Instrument PRamplitude/builder-skills159—~2.9kAutomated safety check: PassNone
Project InitializerDrchronx/ai-agent-research-starter-kit139—~406Automated safety check: PassCustom licence

Similar skills

  • Setup Workspace

    probabl-ai/skills

    Detect an existing ML workspace or scaffold a fresh one via python -m skoreskills scaffold --package <pkg.

    138 GitHub stars~2k tokensUpdated today
    Data & AnalyticsAuto-check passed
  • Name Framework Migration Third Step

    opensanctions/opensanctions

    Complete the name framework migration in a crawler (Step 3) by removing all custom name cleaning/splitting logic and the Step 1 review scaffolding, replacing it with a single…

    834 GitHub stars~904 tokensUpdated today
    Data & AnalyticsAuto-check passed
  • Flowfile Frame And Codegen

    Edwardvaneechoud/Flowfile

    Deep dive into flowfileframe — the Polars-LazyFrame-shaped Python API that builds an in-process flowfilecore FlowGraph as a side effect of every method call — covering the FlowFrame/Expr internals…

    385 GitHub stars~12k tokensUpdated today
    Data & AnalyticsAuto-check passed
  • Instrument PR

    amplitude/builder-skills

    Instruments a pull request with Amplitude analytics that conform to the project's existing taxonomy.

    159 GitHub stars~2.9k tokensUpdated 2 mo ago
    Data & AnalyticsAuto-check passed
  • Project Initializer

    Drchronx/ai-agent-research-starter-kit

    Initialize a structured academic research project workspace.

    139 GitHub stars~406 tokensUpdated 4 mo ago
    Data & AnalyticsAuto-check passed
  • Perform bounded, local exploratory analysis of explicitly supported scientific files.

    212 GitHub starsUsed in 2 repos~3.4k tokens
    Data & AnalyticsAuto-check: notes

More from jeecgboot/skills

All 13 skills in this repo
  • Jeecg Codegen New

    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"…

    239 GitHub stars~2.4k tokensUpdated 23 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 23 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 23 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 23 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 23 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 23 days ago
    Auto-check passed

Questions about Jeecg System

What does Jeecg System do?

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…. Jeecg System is an agent skill from 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 roles", "query users", "query depts", "create dict", "create role", "master data".

When should I use Jeecg System?

Jeecg System fits situations like: user asks to query/create/manage system master data; other skills (desform; codegen) need to look up; positions as dependencies — follows 先查后建 (query-first-create-later) principle.

How do I install Jeecg System in Claude Code?

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

How do I install Jeecg System in Codex?

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

Can I use Jeecg System 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-system -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-system, .gemini/skills/jeecg-system, .github/skills/jeecg-system and .opencode/skills/jeecg-system in your project.

What does Jeecg System need to run?

Going by SKILL.md and its folder, Jeecg System needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Jeecg System access the network?

SKILL.md names 1 domain. In commands or code: boot3.jeecg.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Jeecg System 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 System use?

Jeecg System 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 System use?

About 3.2k tokens (SKILL.md is roughly 13k 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 8.6k tokens, read only when the agent opens those files.

What are the alternatives to Jeecg System?

Skills that share tags, products or a category with Jeecg System: Setup Workspace (probabl-ai/skills, 138 stars), Name Framework Migration Third Step (opensanctions/opensanctions, 834 stars), Flowfile Frame And Codegen (Edwardvaneechoud/Flowfile, 385 stars) and Instrument PR (amplitude/builder-skills, 159 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jeecg System?

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.