diff --git a/docs/docs/cookbook/agents/data_analysis_agent.md b/docs/docs/cookbook/agents/data_analysis_agent.md
index 015291318..794e59a84 100644
--- a/docs/docs/cookbook/agents/data_analysis_agent.md
+++ b/docs/docs/cookbook/agents/data_analysis_agent.md
@@ -208,7 +208,9 @@ uv run dbgpt start webserver --config configs/dbgpt-local-glm.toml
打开浏览器并访问:`http://localhost:5670`
-
+
+
+
### 4.1 知识库接入
@@ -216,59 +218,81 @@ uv run dbgpt start webserver --config configs/dbgpt-local-glm.toml
点击“应用管理”,选择“知识库”
-
+
+
+
2. 创建知识库
-
+
+
+
3. 知识库配置
填写相关配置信息。
-
+
+
+
4. 知识库类型
此处选择文档。
-
+
+
+
5. 上传
此处上传提前准备好的`指标.txt`文档。
-
+
+
+
6. 分片
分片策略选择"separator",分隔符设置为"###"。
-
+
+
+
7. 成功创建知识库
-
+
+
+
### 4.2 创建数据库
1. 选择数据库
-
+
+
+
2. 添加数据源
-
+
+
+
3. 配置数据源
配置准备好的数据库连接信息。
-
+
+
+
4. 添加成功
-
+
+
+
@@ -278,49 +302,65 @@ uv run dbgpt start webserver --config configs/dbgpt-local-glm.toml
点击“创建应用”
-
+
+
+
2. 基础配置
选择“多智能体自动规划模式”,并输入应用名称和对应描述。
-
+
+
+
3. 加入`MetricInfoRetriever`
选取`MetricInfoRetriever`,并配置知识库资源。
-
+
+
+
4. 加入`DataScientist`
选取`DataScientist`,并配置数据库资源。
-
+
+
+
5. 加入`AnomalyDetector`
选取`AnomalyDetector`。
-
+
+
+
6. 加入`VolatilityAnalyzer`
选取`VolatilityAnalyzer`,并配置数据库资源。
-
+
+
+
7. 加入`ReportGenerator`
选取`ReportGenerator`。
-
+
+
+
8. 保存
点击“保存”。
-
+
+
+
### 4.4 使用
@@ -328,20 +368,28 @@ uv run dbgpt start webserver --config configs/dbgpt-local-glm.toml
点击“开始对话”。
-
+
+
+
2. 提问
在输入框中输入问题,如“请帮我分析订单数量2012年 年环比增长情况”,点击发送。
-
+
+
+
3. 回答
-
+
+
+
4. 报告生成
最终生成分析报告。
-
+
+
+
diff --git a/docs/docs/cookbook/agents/data_manus_application.md b/docs/docs/cookbook/agents/data_manus_application.md
index 040ed2b59..b7eb32995 100644
--- a/docs/docs/cookbook/agents/data_manus_application.md
+++ b/docs/docs/cookbook/agents/data_manus_application.md
@@ -53,11 +53,15 @@ Data_Manus多智能体应用具备对表格文件进行多表格协同分析的
**1.点击”应用管理“,选择上方菜单栏中的”数据库“**
-
+
+
+
**2.点击右侧”添加数据源“,在弹出的表单中配置自己的数据源信息**
-
+
+
+
@@ -65,27 +69,39 @@ Data_Manus多智能体应用具备对表格文件进行多表格协同分析的
**1.进入”应用管理“页面,点击”创建应用“**
-
+
+
+
**2.在弹出来的菜单栏中,选择”多智能体自动规划模式“,并配置”应用名称“、”描述“**
-
+
+
+
**3.进入智能体应用构建页面后,选择我们data_manus必要的三个Agent:”SearchNeedEvaluator“、”DataScientist“、”ExcelScientist“**
-
+
+
+
**4.其中”DataScientist“和”ExcelScientist“这两个智能体必须要绑定数据库资源,在下方选择已添加的数据源,配置完毕后点击右上角”更新“完成应用创建**
-
+
+
+
**5.回到”应用管理“页面,点击自己刚刚创建的多智能体应用的”开始对话“按钮进行对话了**
-
+
+
+
**6.在输入框中输入问题,点击发送即可开始对话了**
-
+
+
+
diff --git a/docs/docs/dbgpts/how-to-use-custom-skill.md b/docs/docs/dbgpts/how-to-use-custom-skill.md
new file mode 100644
index 000000000..53550be82
--- /dev/null
+++ b/docs/docs/dbgpts/how-to-use-custom-skill.md
@@ -0,0 +1,55 @@
+# Use Custom Skills
+
+DB-GPT supports three ways to use custom skills: create from scratch with the built-in `skill-creator`, upload a zip package, or import via a GitHub link.
+
+## Option 1: Create with skill-creator
+
+`skill-creator` is the built-in meta-skill in DB-GPT, designed to help you create business-specific custom skills. Simply describe your requirements in a conversation, and `skill-creator` handles the entire process from design to packaging.
+
+### Steps
+
+1. Select the `skill-creator` skill in the DB-GPT chat interface.
+2. Describe the skill you want to create in natural language, for example: "Create a data analysis skill that reads CSV files and generates visual reports."
+3. `skill-creator` will automatically:
+ - Analyze your requirements and plan the skill structure
+ - Generate `SKILL.md` (including metadata and execution instructions)
+ - Create necessary scripts, reference docs, and asset files
+ - Validate and package into a distributable `.skill` file
+
+
+
+For more details on `skill-creator`, see the [skill-creator documentation](./built-in-skills/skill-creator.md).
+
+## Option 2: Upload a Zip Package
+
+If you already have a packaged skill (`.zip` or `.skill` file), you can upload it directly through the DB-GPT Web UI.
+
+### Steps
+
+1. Navigate to the **Skills** page in DB-GPT.
+
+
+
+2. Click the upload button and select your local `.zip` or `.skill` file.
+
+
+
+3. Once uploaded, the skill appears in the list and is ready to use in conversations.
+
+## Option 3: Import via GitHub Link
+
+DB-GPT supports importing skills directly from GitHub repositories — ideal for community or team-shared skills.
+
+### Steps
+
+1. Navigate to the **Skills** page in DB-GPT.
+2. Click the GitHub import button and paste the repository URL of the skill.
+
+
+
+3. The system automatically fetches the repository contents and completes the import. The skill is ready to use once imported.
+
+## Related reading
+
+- [skill-creator](./built-in-skills/skill-creator.md) — Learn about the full capabilities and resources of skill-creator
+- [Skills Overview](./introduction.md) — Understand skill definitions, structure, and how they work
diff --git a/docs/docs/dbgpts/how-to-use-skill.md b/docs/docs/dbgpts/how-to-use-skill.md
index 327bedf40..94c11bf52 100644
--- a/docs/docs/dbgpts/how-to-use-skill.md
+++ b/docs/docs/dbgpts/how-to-use-skill.md
@@ -31,6 +31,8 @@ The agent can:
3. generate charts and metrics
4. use `html_interpreter` to render the final report
+
+
### CSV / Excel analysis
The agent can:
@@ -40,6 +42,8 @@ The agent can:
3. use Python analysis to calculate metrics and visualize results
4. render the output as a report if needed
+
+
## Good practices
- use skills when the workflow should be repeatable
diff --git a/docs/docs/dbgpts/introduction.md b/docs/docs/dbgpts/introduction.md
index d27b3e08a..96a37ab6b 100644
--- a/docs/docs/dbgpts/introduction.md
+++ b/docs/docs/dbgpts/introduction.md
@@ -9,12 +9,11 @@ In DB-GPT, a skill is a reusable capability package that gives an agent a struct
Instead of relying only on free-form reasoning, a skill provides a stable execution pattern for a specific kind of work.
-> The originally shared image source is no longer reachable. This page now uses a working DB-GPT skills screenshot from the current project README. If you want the exact screenshot from your attachment, send me a usable file path or re-upload it and I will swap it to a local asset.
## Skill definition
diff --git a/docs/docs/installation/index.md b/docs/docs/installation/index.md
index c255995ab..974478596 100644
--- a/docs/docs/installation/index.md
+++ b/docs/docs/installation/index.md
@@ -1,23 +1,23 @@
---
sidebar_position: 0
-title: Install
+title: Install Overview
summary: "Choose the fastest way to install DB-GPT: quick install, CLI install, or source install"
read_when:
- You want to decide which installation path fits your environment
- You want the shortest route to a working DB-GPT setup
---
-# Install
+# Install Overview
DB-GPT offers three recommended installation paths. Pick the one that matches how you want to run and manage the project.
## Choose an installation path
-| Method | Best for | What you get |
-|---|---|---|
-| [Quick Install](/docs/installation/quick-install) | Fastest first run on macOS / Linux | One-line installer, generated profile config, ready-to-start webserver |
-| [CLI Install](/docs/getting-started/cli-quickstart) | Users who prefer installing from PyPI | `dbgpt` CLI, interactive setup wizard, profile management |
-| [Source Install](/docs/getting-started/deploy/source-code) | Developers and custom deployments | Full repo checkout, editable configs, maximum flexibility |
+| Method | Best for | Scenario | What you get |
+|:-------|:---------|:---------|:-------------|
+| [Quick Install](/docs/installation/quick-install) | Fastest first run on macOS / Linux | Quick launch the latest DB-GPT from source with automated environment setup and dependency installation | Quick install and start the latest source project with optional advanced config |
+| [CLI Install](/docs/getting-started/cli-quickstart) | Users who prefer installing from PyPI | One-click start and try a stable DB-GPT release without worrying about project structure or config details | One-line installer, interactive setup wizard, profile management |
+| [Source Install](/docs/getting-started/deploy/source-code) | Developers and custom deployments | You need to modify source code, debug internals, or integrate DB-GPT into a custom deployment pipeline | Full repo checkout, editable configs, maximum flexibility |
## Recommended path
diff --git a/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/how-to-use-custom-skill.md b/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/how-to-use-custom-skill.md
new file mode 100644
index 000000000..2dddb843b
--- /dev/null
+++ b/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/how-to-use-custom-skill.md
@@ -0,0 +1,55 @@
+# 使用自定义 Skill
+
+DB-GPT 支持三种方式使用自定义 skill:使用内置的 `skill-creator` 从零创建、上传 zip 包导入、通过 GitHub 链接导入。
+
+## 方式一:使用 skill-creator 创建
+
+`skill-creator` 是 DB-GPT 内置的 meta-skill(元技能),专门用于帮助你创建业务定制化的 skill。你只需在对话中描述需求,`skill-creator` 会自动完成从设计、编写到打包的全部流程。
+
+### 操作步骤
+
+1. 在 DB-GPT 对话界面中,选择 `skill-creator` 技能。
+2. 用自然语言描述你想要创建的 skill,例如:"帮我创建一个数据分析 skill,能够读取 CSV 文件并生成可视化报表"。
+3. `skill-creator` 会自动完成以下工作:
+ - 分析需求并规划 skill 结构
+ - 生成 `SKILL.md`(包含元数据和执行指令)
+ - 创建所需的脚本、参考文档和资源文件
+ - 校验并打包为可分发的 `.skill` 文件
+
+
+
+更多关于 `skill-creator` 的详细用法,请参阅 [skill-creator 文档](./built-in-skills/skill-creator.md)。
+
+## 方式二:上传 Zip 包
+
+如果你已经有一个打包好的 skill(`.zip` 或 `.skill` 文件),可以直接在 DB-GPT 的 Web UI 中上传。
+
+### 操作步骤
+
+1. 进入 DB-GPT 的 **Skills** 页面。
+
+
+
+2. 点击上传按钮,选择本地的 `.zip` 或 `.skill` 文件上传。
+
+
+
+3. 上传完成后,skill 会自动出现在列表中,即可在对话中使用。
+
+## 方式三:通过 GitHub 链接导入
+
+DB-GPT 支持直接从 GitHub 仓库导入 skill,适合使用社区或团队共享的 skill。
+
+### 操作步骤
+
+1. 进入 DB-GPT 的 **Skills** 页面。
+2. 点击 GitHub 导入按钮,粘贴 skill 所在的 GitHub 仓库链接。
+
+
+
+3. 系统会自动拉取仓库内容并完成导入,导入成功后即可使用。
+
+## 相关阅读
+
+- [skill-creator](./built-in-skills/skill-creator.md) — 了解 skill-creator 的完整能力和资源
+- [Skills 总览](./introduction.md) — 了解 skill 的定义、结构和工作原理
diff --git a/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/how-to-use-skill.md b/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/how-to-use-skill.md
index 5fee693ea..cf5c49b09 100644
--- a/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/how-to-use-skill.md
+++ b/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/how-to-use-skill.md
@@ -31,6 +31,8 @@
3. 生成图表与指标结果
4. 使用 `html_interpreter` 渲染最终报告
+
+
### CSV / Excel 分析
智能体可以:
@@ -40,6 +42,9 @@
3. 使用 Python 分析计算指标并可视化结果
4. 如果需要,再将结果渲染为报告
+
+
+
## 最佳实践
- 当工作流需要可重复时,优先使用 skill
diff --git a/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/introduction.md b/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/introduction.md
index 48cace2bb..163e61b3e 100644
--- a/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/introduction.md
+++ b/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/dbgpts/introduction.md
@@ -9,13 +9,11 @@
相比只依赖自由推理,skill 为特定类型的工作提供了更稳定、更可重复的执行模式。
-> 原始分享的图片地址已经失效。当前页面改为使用项目 README 中可正常访问的 DB-GPT skills 截图。如果你希望替换成你之前附件里的原始图片,请提供可用文件路径或重新上传,我可以改成仓库本地资源。
-
## Skill 的定义
结合 Agent Skills 的定义,可以把 skill 理解为:
diff --git a/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/installation/index.md b/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/installation/index.md
index e6249ad5e..9325b3ae9 100644
--- a/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/installation/index.md
+++ b/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/installation/index.md
@@ -1,23 +1,23 @@
---
sidebar_position: 0
-title: 安装
+title: 安装概览
summary: "选择最适合你的 DB-GPT 安装方式:快速安装、CLI 安装或源码安装"
read_when:
- 你想判断哪种安装路径最适合当前环境
- 你希望以最短路径完成可用的 DB-GPT 安装
---
-# 安装
+# 安装概览
DB-GPT 提供三种推荐安装方式。你可以根据自己的使用方式和环境选择最合适的路径。
## 选择安装方式
-| 方式 | 适合人群 | 你会得到什么 |
-|---|---|---|
-| [快速安装](/docs/installation/quick-install) | 希望在 macOS / Linux 上最快完成首次启动的用户 | 一行安装脚本、自动生成的 provider 配置、可直接启动的 webserver |
-| [CLI 安装](/docs/getting-started/cli-quickstart) | 希望通过 PyPI 安装并使用命令行的用户 | `dbgpt` CLI、交互式向导、profile 管理能力 |
-| [源码安装](/docs/getting-started/deploy/source-code) | 开发者或需要自定义部署的用户 | 完整仓库、可编辑配置、最大灵活性 |
+| 方式 | 适合人群 | 场景 | 你会得到什么 |
+|:-----|:---------|:-----|:---------------------------------------------|
+| [快速安装](/docs/installation/quick-install) | 希望在 macOS / Linux 上最快完成首次启动的用户 | 从源码快速启动最新版 DB-GPT,自动完成环境配置和依赖安装 | 通过脚本快速安装并启动最新的源项目,还可选择进行高级配置(基于源码快速体验) |
+| [CLI 安装](/docs/getting-started/cli-quickstart) | 希望通过 PyPI 安装并使用命令行的用户 | 一键启动并体验稳定版 DB-GPT,无需关心项目结构或配置细节 | 通过`dbgpt` CLI一键启动、交互式安装向导、配置文件管理(基于稳定版本快速体验) |
+| [源码安装](/docs/getting-started/deploy/source-code) | 开发者或需要自定义部署的用户 | 需要修改源码、调试内部逻辑,或将 DB-GPT 集成到自定义部署流程中 | 完整源码仓库、自定义高级配置、给予开发者最大灵活性(自定义配置和二次开发) |
## 推荐路径
diff --git a/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/overview.mdx b/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/overview.mdx
index de2ea6b28..4f1aceeb0 100644
--- a/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/overview.mdx
+++ b/docs/i18n/zh-CN/docusaurus-plugin-content-docs/current/overview.mdx
@@ -8,7 +8,7 @@ import CommandCopyCard from "@site/src/components/mdx/CommandCopyCard";
# DB-GPT
-
+
diff --git a/docs/sidebars.js b/docs/sidebars.js
index 06adc4bb5..4a56317b1 100755
--- a/docs/sidebars.js
+++ b/docs/sidebars.js
@@ -535,7 +535,7 @@ const sidebars = {
{
type: "category",
label: "Built-in Skills",
- collapsed: false,
+ collapsed: true,
collapsible: true,
items: [
{ type: "doc", id: "dbgpts/built-in-skills/overview", label: "Overview" },
@@ -547,6 +547,7 @@ const sidebars = {
],
},
{ type: "doc", id: "dbgpts/how-to-use-skill", label: "How to Use Skill" },
+ { type: "doc", id: "dbgpts/how-to-use-custom-skill", label: "Use Custom Skills" },
],
sidebarDatasources: [
@@ -872,6 +873,7 @@ module.exports = {
label: "Installation",
collapsed: true,
collapsible: true,
+ link: { type: "doc", id: "installation/index" },
items: sidebars.sidebarInstallation[0].items,
},
{
diff --git a/docs/src/css/custom.css b/docs/src/css/custom.css
index 3b44918b5..87b2c3971 100755
--- a/docs/src/css/custom.css
+++ b/docs/src/css/custom.css
@@ -51,7 +51,7 @@ html {
background:
radial-gradient(820px 520px at 8% -10%, rgba(255, 79, 64, 0.045), transparent 60%),
radial-gradient(900px 560px at 100% 0%, rgba(15, 107, 76, 0.04), transparent 60%),
- linear-gradient(180deg, #fbf4e7 0%, #fffaf0 34%, #fffdf8 100%);
+ color-mix(in srgb, var(--ifm-background-surface-color) 88%, transparent);
}
body {
@@ -98,7 +98,7 @@ html[data-theme='dark'] {
background:
radial-gradient(820px 520px at 10% -10%, rgba(255, 79, 64, 0.08), transparent 60%),
radial-gradient(920px 540px at 100% 0%, rgba(95, 223, 162, 0.05), transparent 62%),
- linear-gradient(180deg, #0b1a22 0%, #0a1720 36%, #0e231f 100%);
+ color-mix(in srgb, var(--ifm-background-surface-color) 88%, transparent);
}
/* GitHub */
diff --git a/docs/static/img/dbgpt_vision_zh.png b/docs/static/img/dbgpt_vision_zh.png
new file mode 100644
index 000000000..156b31934
Binary files /dev/null and b/docs/static/img/dbgpt_vision_zh.png differ
diff --git a/docs/static/img/skill/create_skill.jpg b/docs/static/img/skill/create_skill.jpg
new file mode 100644
index 000000000..a63ea32c9
Binary files /dev/null and b/docs/static/img/skill/create_skill.jpg differ
diff --git a/docs/static/img/skill/create_skill_zh.jpg b/docs/static/img/skill/create_skill_zh.jpg
new file mode 100644
index 000000000..9c7466e20
Binary files /dev/null and b/docs/static/img/skill/create_skill_zh.jpg differ
diff --git a/docs/static/img/skill/csv_data_analysis_skill.jpg b/docs/static/img/skill/csv_data_analysis_skill.jpg
new file mode 100644
index 000000000..adcf2e09d
Binary files /dev/null and b/docs/static/img/skill/csv_data_analysis_skill.jpg differ
diff --git a/docs/static/img/skill/csv_data_analysis_skill_zh.jpg b/docs/static/img/skill/csv_data_analysis_skill_zh.jpg
new file mode 100644
index 000000000..03a59d4e8
Binary files /dev/null and b/docs/static/img/skill/csv_data_analysis_skill_zh.jpg differ
diff --git a/docs/static/img/skill/financial_report_analysis_skill.jpg b/docs/static/img/skill/financial_report_analysis_skill.jpg
new file mode 100644
index 000000000..36687d9b6
Binary files /dev/null and b/docs/static/img/skill/financial_report_analysis_skill.jpg differ
diff --git a/docs/static/img/skill/import_github_skill_.png b/docs/static/img/skill/import_github_skill_.png
new file mode 100644
index 000000000..03b35e08b
Binary files /dev/null and b/docs/static/img/skill/import_github_skill_.png differ
diff --git a/docs/static/img/skill/import_github_skill_zh.png b/docs/static/img/skill/import_github_skill_zh.png
new file mode 100644
index 000000000..86ef0eeff
Binary files /dev/null and b/docs/static/img/skill/import_github_skill_zh.png differ
diff --git a/docs/static/img/skill/skill_list.png b/docs/static/img/skill/skill_list.png
new file mode 100644
index 000000000..25ae2c3f8
Binary files /dev/null and b/docs/static/img/skill/skill_list.png differ
diff --git a/docs/static/img/skill/skill_list_zh.png b/docs/static/img/skill/skill_list_zh.png
new file mode 100644
index 000000000..6719e76bc
Binary files /dev/null and b/docs/static/img/skill/skill_list_zh.png differ
diff --git a/docs/static/img/skill/upload_skill.png b/docs/static/img/skill/upload_skill.png
new file mode 100644
index 000000000..da39c62f2
Binary files /dev/null and b/docs/static/img/skill/upload_skill.png differ
diff --git a/docs/static/img/skill/upload_skill_zh.png b/docs/static/img/skill/upload_skill_zh.png
new file mode 100644
index 000000000..3c3afcb4f
Binary files /dev/null and b/docs/static/img/skill/upload_skill_zh.png differ
diff --git a/docs/static/img/skill/use_csv_data_skill.png b/docs/static/img/skill/use_csv_data_skill.png
new file mode 100644
index 000000000..a5be2221f
Binary files /dev/null and b/docs/static/img/skill/use_csv_data_skill.png differ
diff --git a/docs/static/img/skill/use_csv_data_skill_zh.png b/docs/static/img/skill/use_csv_data_skill_zh.png
new file mode 100644
index 000000000..ad1d341f4
Binary files /dev/null and b/docs/static/img/skill/use_csv_data_skill_zh.png differ
diff --git a/docs/static/img/skill/use_financial_report_analysis_skill.png b/docs/static/img/skill/use_financial_report_analysis_skill.png
new file mode 100644
index 000000000..70ff3aefd
Binary files /dev/null and b/docs/static/img/skill/use_financial_report_analysis_skill.png differ
diff --git a/docs/static/img/skill/use_financial_report_analysis_skill_zh.png b/docs/static/img/skill/use_financial_report_analysis_skill_zh.png
new file mode 100644
index 000000000..086123b03
Binary files /dev/null and b/docs/static/img/skill/use_financial_report_analysis_skill_zh.png differ