MoonshotAI · stdrc · Jan 20, 2026 · Jan 20, 2026 · Jan 20, 2026 · Jan 20, 2026
diff --git a/.agents/skills/gen-changelog/SKILL.md b/.agents/skills/gen-changelog/SKILL.md
@@ -1,8 +1,6 @@
 ---
 name: gen-changelog
-description: Generate changelog entries for code changes. Use when user wants to add changelog entries, update CHANGELOG.md, or document changes made in the current branch compared to main.
+description: Generate changelog entries for code changes.
 ---
 
-# Generate Changelog
-
 根据当前分支相对于 main 分支的修改，在根目录 CHANGELOG.md 或相应 package/sdk 等目录的 CHANGELOG.md 文件中添加更新日志条目，遵循现有的格式和风格。
diff --git a/.agents/skills/gen-docs/SKILL.md b/.agents/skills/gen-docs/SKILL.md
@@ -1,10 +1,8 @@
 ---
 name: gen-docs
-description: Update Kimi CLI user documentation. Use when user wants to update docs, sync documentation with code changes, or ensure docs reflect recent commits and changelog updates.
+description: Update Kimi CLI user documentation.
 ---
 
-# Generate/Update Documentation
-
 现在我们正在为当前项目 Kimi CLI 编写和维护用户文档，文档内容在 docs 目录下，docs/AGENTS.md 中有对文档的说明。
 
 我们现在对代码库有了一些修改，请你参考最近的 git commit、staged changes、changelog.md 等的内容，根据 AGENTS.md 中的信息，必要时找到实际的代码全文，确保理解了所有变更对产品用户体验的真实改变，然后逐页、逐段地检查和更新文档内容。

diff --git a/.agents/skills/pr/SKILL.md b/.agents/skills/pr/SKILL.md
diff --git a/.agents/skills/pull-request/SKILL.md b/.agents/skills/pull-request/SKILL.md
@@ -0,0 +1,14 @@
+---
+name: pull-request
+description: Create and submit a GitHub Pull Request.
+type: flow
+---
+
+```mermaid
+flowchart TB
+    A(["BEGIN"]) --> B["当前分支有没有 dirty change？"]
+    B -- 有 --> D(["END"])
+    B -- 没有 --> n1["确保当前分支是一个不同于 main 的独立分支"]
+    n1 --> n2["根据当前分支相对于 main 分支的修改，push 并提交一个 PR（利用 gh 命令），用英文编写 PR 标题和 description，描述所做的更改。PR title 要符合先前的 commit message 规范（PR title 就是 squash merge 之后的 commit message）。"]
+    n2 --> D
+```
diff --git a/.agents/skills/release/SKILL.md b/.agents/skills/release/SKILL.md
@@ -1,26 +1,25 @@
 ---
 name: release
-description: Execute the release workflow for Kimi CLI packages. Use when user wants to release a new version, bump version numbers, create release PRs, or prepare packages for publishing.
+description: Execute the release workflow for Kimi CLI packages.
+type: flow
 ---
 
-# Release Workflow
-
-1. 首先从 AGENTS.md 和 .github/workflows/release*.yml 中理解本项目的发版自动化流程。
-2. 检查每个 packages、sdks 和根目录的包是否在上次发版（根据 tag 确认）后有变更。
-   - 注意 `packages/kimi-code` 是薄包装包，需要与根包 `kimi-cli` 同步版本。
-3. 如果有变更，对于每个变更的包，跟我确认新的版本号（遵循语义化版本规范），并更新相应的：
-   - pyproject.toml
-   - CHANGELOG.md（要保留 Unreleased 标题）
-   - 中英文档的 breaking-changes.md 文件中的版本号
-   - 若变更的是根包版本，同时同步更新：
-     - `packages/kimi-code/pyproject.toml` 的 `version`
-     - `packages/kimi-code/pyproject.toml` 的 `dependencies` 中 `kimi-cli==<version>`
-4. 运行 `uv sync`。
-5. 运行 gen-docs skill 中的指示以确保文档是最新的。
-6. 开一个新的分支叫 `bump-<package>-<new-version>`，提交所有更改并推送到远程仓库。
-   - 如果一次有多个包需要发版，可以合并在一个分支升级版本号，分支名适当编写即可。
-7. 用 gh 命令开一个 Pull Request，描述所做的更改。
-8. 持续检查这个 PR 的状态，直到被合并。
-9. 合并后，切到 main 分支，拉取最新的更改。
-10. 提示我最终发布 tag 所需的 git tag 命令，我会自行 tag + push tags。
-    - 说明：单个数字 tag 会同时发布 `kimi-cli` 与 `kimi-code`。
+```mermaid
+flowchart TB
+    A(["BEGIN"]) --> B["从 AGENTS.md 和 .github/workflows/release*.yml 中理解本项目的发版自动化流程"]
+    B --> C["检查每个 packages、sdks 和根目录的包是否在上次发版（根据 tag 确认）后有变更。注意 packages/kimi-code 是薄包装包，需要与根包 kimi-cli 同步版本。"]
+    C --> D{"有变更的包？"}
+    D -- 没有 --> Z(["END"])
+    D -- 有 --> E["对于每个变更的包，跟用户确认新的版本号（遵循语义化版本规范）"]
+    E --> F["更新相应的 pyproject.toml、CHANGELOG.md（保留 Unreleased 标题）、中英文档的 breaking-changes.md 文件中的版本号"]
+    F --> G{"变更的是根包版本？"}
+    G -- 是 --> H["同步更新 packages/kimi-code/pyproject.toml 的 version 和 dependencies 中 kimi-cli==&lt;version&gt;"]
+    H --> I["运行 uv sync"]
+    G -- 否 --> I
+    I --> J["运行 gen-docs skill 中的指示以确保文档是最新的"]
+    J --> K["开一个新分支 bump-&lt;package&gt;-&lt;new-version&gt;（多个包可合并在一个分支，分支名适当编写）"]
+    K --> L["提交所有更改，推送到远程仓库，并用 gh 命令开一个 Pull Request，描述所做的更改"]
+    L --> N["持续检查这个 PR 的状态，直到被合并"]
+    N --> O["合并后，切到 main 分支，拉取最新的更改，并提示用户最终发布 tag 所需的 git tag 命令（用户会自行 tag + push tags）。说明：单个数字 tag 会同时发布 kimi-cli 与 kimi-code。"]
+    O --> Z
+```
diff --git a/.agents/skills/translate-docs/SKILL.md b/.agents/skills/translate-docs/SKILL.md
@@ -1,10 +1,8 @@
 ---
 name: translate-docs
-description: Translate and sync bilingual documentation. Use when user wants to translate docs between Chinese and English, sync translations, or ensure bilingual documentation consistency.
+description: Translate and sync bilingual documentation.
 ---
 
-# Translate Documentation
-
 现在我们正在为当前项目 Kimi CLI 编写和维护用户文档，文档内容在 docs 目录下，docs/AGENTS.md 中有对文档的说明。
 
 中文文档和英文 changelog 已经确保是正确符合预期的，现在请你逐页、逐段地翻译文档内容，确保中英双语保持同步。

diff --git a/AGENTS.md b/AGENTS.md
@@ -58,8 +58,8 @@ shell UI, ACP server mode for IDE integrations, and MCP tool loading.
   and slash command autocomplete; it is the default interactive experience.
 - **Slash commands**: Soul-level commands live in `src/kimi_cli/soul/slash.py`; shell-level
   commands live in `src/kimi_cli/ui/shell/slash.py`. The shell UI exposes both and dispatches
-  based on the registry. Skills are registered as soul-level commands; running
-  `/skill:<skill-name>` loads the skill's `SKILL.md` as a user prompt.
+  based on the registry. Standard skills register `/skill:<skill-name>` and load `SKILL.md`
+  as a user prompt; flow skills register `/flow:<skill-name>` and execute the embedded flow.
 
 ## Major modules and interfaces
 

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -11,6 +11,10 @@ Only write entries that are worth mentioning to users.
 
 ## Unreleased
 
+- Skills: Add flow skill type with embedded Agent Flow (Mermaid/D2) in SKILL.md, invoked via `/flow:<skill-name>` commands
+- CLI: Remove `--prompt-flow` option; use flow skills instead
+- Core: Replace `/begin` command with `/flow:<skill-name>` commands for flow skills
+
 ## 0.80 (2026-01-20)
 
 - Wire: Add `initialize` method for exchanging client/server info, external tools registration and slash commands advertisement

diff --git a/docs/en/customization/skills.md b/docs/en/customization/skills.md
@@ -189,3 +189,59 @@ For regular conversations, the Agent will automatically decide whether to read s
 :::
 
 Skills allow you to codify your team's best practices and project standards, ensuring the AI always follows consistent standards.
+
+## Flow skills
+
+Flow skills are a special skill type that embed an Agent Flow diagram in `SKILL.md`, used to define multi-step automated workflows. Unlike standard skills, flow skills are invoked via `/flow:<name>` commands and automatically execute multiple conversation turns following the flow diagram.
+
+**Creating a flow skill**
+
+To create a flow skill, set `type: flow` in the frontmatter and include a Mermaid or D2 code block in the content:
+
+````markdown
+---
+name: code-review
+description: Code review workflow
+type: flow
+---
+
+```mermaid
+flowchart TD
+A([BEGIN]) --> B[Analyze code changes, list all modified files and features]
+B --> C{Is code quality acceptable?}
+C -->|Yes| D[Generate code review report]
+C -->|No| E[List issues and propose improvements]
+E --> B
+D --> F([END])
+```
+````
+
+**Flow diagram format**
+
+Both Mermaid and D2 formats are supported:
+
+- **Mermaid**: Use ` ```mermaid ` code block, [Mermaid Playground](https://www.mermaidchart.com/play) can be used for editing and preview
+- **D2**: Use ` ```d2 ` code block, [D2 Playground](https://play.d2lang.com) can be used for editing and preview
+
+Flow diagrams must contain one `BEGIN` node and one `END` node. Regular node text is sent to the Agent as a prompt; decision nodes require the Agent to output `<choice>branch name</choice>` in the output to select the next step.
+
+**D2 format example**
+
+```
+BEGIN -> B -> C
+B: Analyze existing code, write design doc for XXX feature
+C: Review if design doc is detailed enough
+C -> B: No
+C -> D: Yes
+D: Start implementation
+D -> END
+```
+
+**Executing a flow skill**
+
+```sh
+# Execute in Kimi CLI
+/flow:code-review
+```
+
+After execution, the Agent will start from the `BEGIN` node and process each node according to the flow diagram definition until reaching the `END` node.
diff --git a/docs/en/reference/kimi-command.md b/docs/en/reference/kimi-command.md
@@ -77,57 +77,7 @@ When using `--prompt` (or `--command`), Kimi CLI exits after processing the quer
 
 [Ralph](https://ghuntley.com/ralph/) is a technique that puts an agent in a loop: the same prompt is fed again and again so the agent can keep iterating one big task.
 
-When `--max-ralph-iterations` is not `0`, Kimi CLI enters Ralph Loop mode and automatically loops through task execution based on an internal Prompt Flow, until the agent outputs `<choice>STOP</choice>` or the iteration limit is reached.
-
-::: info Note
-Ralph Loop is mutually exclusive with the `--prompt-flow` option and cannot be used together.
-:::
-
-## Prompt Flow
-
-| Option | Description |
-|--------|-------------|
-| `--prompt-flow PATH` | Load a D2 (`.d2`) or Mermaid (`.mmd`) flowchart file as a Prompt Flow |
-
-Prompt Flow is a prompt workflow description method based on flowcharts, where each node corresponds to one conversation turn. After loading, you can start the flow execution with the `/begin` slash command. Both D2 and Mermaid flowchart formats are supported. You can edit and preview D2 flowcharts at [D2 Playground](https://play.d2lang.com), and Mermaid flowcharts at [Mermaid Playground](https://www.mermaidchart.com/play).
-
-D2 flowchart example (`example.d2` file):
-
-```
-BEGIN -> B -> C
-B: Analyze existing code, write design doc for XXX feature in design.md
-C: Review design.md, is it detailed enough?
-C -> B: No
-C -> D: Yes
-D: Start implementation
-D -> END
-```
-
-Mermaid flowchart example (`example.mmd` file):
-
-```
-flowchart TD
-A([BEGIN]) --> B[Analyze existing code, write design doc for XXX feature in design.md]
-B --> C{Review design.md, is it detailed enough?}
-C -->|Yes| D[Start implementation]
-C -->|No| B
-D --> F([END])
-```
-
-```mermaid
-flowchart TD
-A([BEGIN]) --> B[Analyze existing code, write design doc for XXX feature in design.md]
-B --> C{Review design.md, is it detailed enough?}
-C -->|Yes| D[Start implementation]
-C -->|No| B
-D --> F([END])
-```
-
-During node processing, decision nodes require the agent to output `<choice>branch name</choice>` to select the next node.
-
-::: info Note
-`--prompt-flow` is mutually exclusive with Ralph Loop mode and cannot be used together.
-:::
+When `--max-ralph-iterations` is not `0`, Kimi CLI enters Ralph Loop mode and automatically loops through task execution until the agent outputs `<choice>STOP</choice>` or the iteration limit is reached.
 
 ## UI modes
 

diff --git a/docs/en/reference/slash-commands.md b/docs/en/reference/slash-commands.md
@@ -118,6 +118,17 @@ For example:
 
 You can append additional text after the command, which will be added to the skill prompt. See [Agent Skills](../customization/skills.md) for details.
 
+### `/flow:<name>`
+
+Execute a specific flow skill. Flow skills embed an Agent Flow diagram in `SKILL.md`. After execution, the Agent will start from the `BEGIN` node and process each node according to the flow diagram definition until reaching the `END` node.
+
+For example:
+
+- `/flow:code-review`: Execute code review workflow
+- `/flow:release`: Execute release workflow
+
+See [Agent Skills](../customization/skills.md#flow-skills) for details.
+
 ## Others
 
 ### `/init`
@@ -134,12 +145,6 @@ Toggle YOLO mode. When enabled, all operations are automatically approved and a
 YOLO mode skips all confirmations. Make sure you understand the potential risks.
 :::
 
-### `/begin`
-
-Start Prompt Flow execution.
-
-This command is only available when a flowchart has been loaded via `--prompt-flow`. After execution, the agent will start from the `BEGIN` node and process each node according to the flowchart definition until reaching the `END` node. See [`kimi` command](./kimi-command.md#prompt-flow) for details.
-
 ## Command completion
 
 After typing `/` in the input box, a list of available commands is automatically displayed. Continue typing to filter commands with fuzzy matching support, press Enter to select.

diff --git a/docs/en/release-notes/changelog.md b/docs/en/release-notes/changelog.md
@@ -4,6 +4,10 @@ This page documents the changes in each Kimi CLI release.
 
 ## Unreleased
 
+- Skills: Add flow skill type with embedded Agent Flow (Mermaid/D2) in SKILL.md, invoked via `/flow:<skill-name>` commands
+- CLI: Remove `--prompt-flow` option; use flow skills instead
+- Core: Replace `/begin` command with `/flow:<skill-name>` commands for flow skills
+
 ## 0.80 (2026-01-20)
 
 - Wire: Add `initialize` method for exchanging client/server info, external tools registration and slash commands advertisement

diff --git a/docs/zh/customization/skills.md b/docs/zh/customization/skills.md
@@ -189,3 +189,59 @@ description: Git 提交信息规范，使用 Conventional Commits 格式
 :::
 
 Skills 让你可以将团队的最佳实践和项目规范固化下来，确保 AI 始终遵循一致的标准。
+
+## Flow Skills
+
+Flow Skill 是一种特殊的 Skill 类型，它在 `SKILL.md` 中内嵌 Agent Flow 流程图，用于定义多步骤的自动化工作流。与普通 Skill 不同，Flow Skill 通过 `/flow:<name>` 命令调用，会按照流程图自动执行多个对话轮次。
+
+**创建 Flow Skill**
+
+创建 Flow Skill 需要在 Frontmatter 中设置 `type: flow`，并在内容中包含 Mermaid 或 D2 格式的流程图代码块：
+
+````markdown
+---
+name: code-review
+description: 代码审查工作流
+type: flow
+---
+
+```mermaid
+flowchart TD
+A([BEGIN]) --> B[分析代码变更，列出所有修改的文件和功能]
+B --> C{代码质量是否达标？}
+C -->|是| D[生成代码审查报告]
+C -->|否| E[列出问题并提出改进建议]
+E --> B
+D --> F([END])
+```
+````
+
+**流程图格式**
+
+支持 Mermaid 和 D2 两种格式：
+
+- **Mermaid**：使用 ` ```mermaid ` 代码块，[Mermaid Playground](https://www.mermaidchart.com/play) 可用于编辑和预览
+- **D2**：使用 ` ```d2 ` 代码块，[D2 Playground](https://play.d2lang.com) 可用于编辑和预览
+
+流程图必须包含一个 `BEGIN` 节点和一个 `END` 节点。普通节点的文本作为提示词发送给 Agent；分支节点需要 Agent 在输出中使用 `<choice>分支名</choice>` 选择下一步。
+
+**D2 格式示例**
+
+```
+BEGIN -> B -> C
+B: 分析现有代码，为 XXX 功能编写设计文档
+C: Review 设计文档是否足够详细
+C -> B: 否
+C -> D: 是
+D: 开始实现
+D -> END
+```
+
+**执行 Flow Skill**
+
+```sh
+# 在 Kimi CLI 中执行
+/flow:code-review
+```
+
+执行后，Agent 会从 `BEGIN` 节点开始，按照流程图定义依次处理每个节点，直到到达 `END` 节点。