openchatcut

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

OpenChatCut

OpenChatCut is a local-first, agent-native video editor. This skill is the single external entry point; specialized editing guidance remains inside the running editor and is loaded on demand with

load_skill

OpenChatCut是一款本地优先、Agent原生的视频编辑器。本技能是唯一的外部入口；专业的编辑指导仍在运行中的编辑器内部，并通过

load_skill

按需加载。

Route the task

任务路由

Install, connect, or diagnose the MCP server: read
```
references/getting-started.md
```
.
Inspect or modify a project: read
```
references/editing-workflow.md
```
.
Recover from a failed tool call, stale session, or missing editor: read
```
references/known-errors.md
```
.

安装、连接或诊断MCP服务器：阅读
```
references/getting-started.md
```
。
查看或修改项目：阅读
```
references/editing-workflow.md
```
。
从失败的工具调用、过期会话或缺失编辑器中恢复：阅读
```
references/known-errors.md
```
。

Essentials

核心要点

Start OpenChatCut before connecting. The default MCP endpoint is
```
http://localhost:5199/api/external-mcp/mcp
```
.
Call
```
openchatcut_status
```
, then
```
list_projects
```
. Select a project only when the user names it or the current context identifies it.
Call
```
load_skill
```
before specialized work. It is read-only and requires neither
```
begin_edit_session
```
nor
```
editSessionId
```
; available names and support files come from the live MCP tool description. With progressive exposure enabled, this call reveals the skill's referenced tools and emits
```
tools/list_changed
```
; refresh the list before continuing.
Before project reads or edits, call
```
begin_edit_session
```
. Keep its
```
editSessionId
```
and pass it to every draft-safe editor tool.
Use
```
approvalMode: "manual"
```
unless the user explicitly asks for unattended application. In manual mode, the user approves the complete proposal in OpenChatCut. In auto mode,
```
review_edit_session
```
applies the complete draft.
Finish with
```
review_edit_session
```
. Report success only after
```
get_edit_session
```
returns
```
applied
```
.

连接前先启动OpenChatCut。默认MCP端点为
```
http://localhost:5199/api/external-mcp/mcp
```
。
先调用
```
openchatcut_status
```
，再调用
```
list_projects
```
。仅当用户指定项目名称或当前上下文明确项目时，才选择项目。
进行专业操作前调用
```
load_skill
```
。该操作为只读，无需
```
begin_edit_session
```
或
```
editSessionId
```
；可用名称和支持文件来自实时MCP工具描述。启用渐进式暴露后，此调用会展示技能引用的工具并触发
```
tools/list_changed
```
；继续操作前请刷新工具列表。
在读取或编辑项目前，调用
```
begin_edit_session
```
。保留其
```
editSessionId
```
并将其传递给所有支持草稿的编辑器工具。
除非用户明确要求无人值守执行，否则使用
```
approvalMode: "manual"
```
。手动模式下，用户需在OpenChatCut中批准完整提案；自动模式下，
```
review_edit_session
```
会应用完整草稿。
最后调用
```
review_edit_session
```
。仅当
```
get_edit_session
```
返回
```
applied
```
时，才报告操作成功。

Skill version

技能版本

2026-08-10.1

The OpenChatCut MCP server announces its required skill baseline. If the server baseline is newer, run:

bash

npx skills update openchatcut

Fallback command:

bash

npx skills add 0xsline/OpenChatCut --skill openchatcut

2026-08-10.1

OpenChatCut MCP服务器会公布其要求的技能基准版本。若服务器基准版本更新，请运行：

bash

npx skills update openchatcut

备用命令：

bash

npx skills add 0xsline/OpenChatCut --skill openchatcut