calle

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

CALL-E For Cursor

适用于Cursor的CALL-E

Use this skill when the user wants Cursor to use CALL-E for setup checks, authentication recovery, phone call planning, planned call execution, or call status inspection.

This Cursor plugin is MCP-first. Prefer the Cursor MCP tools exposed by the bundled

calle

server whenever they are available:

```
plan_call
```
```
run_call
```
```
get_call_run
```

Use the CLI fallback only when Cursor MCP tools are unavailable or the user explicitly asks to verify CALL-E through the CLI.

当用户希望Cursor使用CALL-E进行设置检查、身份验证恢复、电话规划、已规划电话执行或通话状态检查时，可使用此技能。

此Cursor插件优先使用MCP。只要可用，优先使用捆绑的

calle

服务器提供的Cursor MCP工具：

```
plan_call
```
```
run_call
```
```
get_call_run
```

仅当Cursor MCP工具不可用，或用户明确要求通过CLI验证CALL-E时，才使用CLI作为备选方案。

When to use

使用场景

Use this skill for:

verifying CALL-E setup in Cursor
checking that the
```
calle
```
MCP server is connected
recovering from missing or expired CALL-E MCP authentication
planning a phone call
running a planned call after planning returns complete run credentials
checking a call run status
reporting the final call summary, details, and transcript when a call reaches a terminal status

Do not use this skill when the user only wants a call script, roleplay, simulated conversation, or general contact lookup that does not require CALL-E.

此技能适用于以下场景：

验证Cursor中的CALL-E设置
检查
```
calle
```
MCP服务器是否已连接
从CALL-E MCP身份验证缺失或过期的状态中恢复
规划电话通话
在规划返回完整运行凭据后执行已规划的通话
检查通话运行状态
当通话进入终端状态时，报告最终的通话摘要、详情和转录内容

当用户仅需要通话脚本、角色扮演、模拟对话或不需要CALL-E的常规联系人查询时，请勿使用此技能。

Safety and consent

安全与同意

Real phone calls may contact external people or businesses.
Always use plan_call before run_call.
Only call run_call when the user clearly intends to place the call.
Preserve plan_id and confirm_token exactly.
If the user asked only to verify setup or only to plan, do not run the call.
Do not guess phone numbers, country codes, language, region, plan_id, confirm_token, or run_id.
Do not expose OAuth tokens, bearer tokens, authorization codes, callback URLs, refresh tokens, or access tokens.
Do not configure CALL-E run_call for auto-run.

真实电话可能会联系外部人员或企业。
执行run_call前必须先使用plan_call。
仅当用户明确表示要拨打电话时，才调用run_call。
严格保留plan_id和confirm_token的原样。
如果用户仅要求验证设置或仅进行规划，请勿执行通话。
请勿猜测电话号码、国家代码、语言、地区、plan_id、confirm_token或run_id。
请勿泄露OAuth令牌、Bearer令牌、授权码、回调URL、刷新令牌或访问令牌。
请勿将CALL-E的run_call配置为自动运行。

MCP readiness

MCP就绪检查

Use this flow whenever this Cursor plugin is actively invoked for a CALL-E request. Run it before call planning, when setup is uncertain, when auth fails, or when the user asks to verify CALL-E setup:

Confirm the
```
calle
```
MCP server is connected.
Confirm that
```
plan_call
```
,
```
run_call
```
, and
```
get_call_run
```
are available.
If Cursor asks to authorize the
```
calle
```
MCP server, use Cursor's MCP authorization flow and continue after authorization completes.
Never ask the user for OAuth tokens, bearer tokens, authorization codes, callback URLs, refresh tokens, or access tokens.
If the MCP server cannot be connected or authorized, use the CLI fallback.

Setup verification must not place a real phone call. Use only tool discovery, authorization recovery, and

plan_call

when the user explicitly asks to plan.

每当此Cursor插件被主动调用处理CALL-E请求时，都需执行此流程。在通话规划前、设置存疑时、身份验证失败时，或用户要求验证CALL-E设置时，运行此流程：

确认
```
calle
```
MCP服务器已连接。
确认
```
plan_call
```
、
```
run_call
```
和
```
get_call_run
```
工具可用。
如果Cursor要求授权
```
calle
```
MCP服务器，使用Cursor的MCP授权流程，完成授权后再继续。
切勿向用户索要OAuth令牌、Bearer令牌、授权码、回调URL、刷新令牌或访问令牌。
如果无法连接或授权MCP服务器，使用CLI备选方案。

设置验证不得拨打真实电话。仅当用户明确要求进行规划时，才使用工具发现、授权恢复和

plan_call

。

MCP call flow

MCP通话流程

Use
```
plan_call
```
first. If the user has not provided enough explicit fields for
```
plan_call
```
, call it with
```
user_input
```
set to the latest user message verbatim so CALL-E can ask for missing details.
Read the returned
```
plan_id
```
and
```
confirm_token
```
.
If the user's request is to place a call, immediately use
```
run_call
```
with the exact
```
plan_id
```
and
```
confirm_token
```
returned by planning.
Do not ask for a second confirmation between
```
plan_call
```
and
```
run_call
```
.
Read the returned
```
run_id
```
. Preserve it exactly.
After
```
run_call
```
, wait 60 seconds before the first
```
get_call_run
```
request unless the call already returned a terminal status.
Keep using
```
get_call_run
```
with that exact
```
run_id
```
until the call reaches a terminal status or the user asks you to stop. Poll every 5 to 10 seconds after the first status check.
Use
```
get_call_run
```
only with a known
```
run_id
```
.

Terminal statuses include

COMPLETED

FAILED

NO_ANSWER

DECLINED

CANCELED

CANCELLED

VOICEMAIL

BUSY

, and

EXPIRED

For non-terminal statuses, reply with progress in this shape:

text

Phone call is in progress! Progress:
- <HH:MM:SS message>

Use one bullet per

activity

item, preserving the order returned by CALL-E. For each item, prefer the event

ts

formatted as

HH:MM:SS

plus

message

. If

ts

is missing, use the message by itself. If there is no activity, use

- Status: <status>

when a status exists; otherwise use

- Waiting for the next status update.

Do not include the final summary, details, or transcript until a terminal status is returned.

When the call reaches a terminal status, reply with the final call result, including these sections in this order:

text

[Status]
<status>

[Call Summary]
<post_summary or summary or message>

[Details]
Callee Number: <primary callee or Not available>
Duration: <duration or Not available>
Time: <start/end time or Not available>
Call id: <call_id or Not available>

[Transcript]
<transcript or Not available.>

If the user asked for extra final content, such as key takeaways or next steps, add it after

[Transcript]

under a short heading. Base all final sections only on the JSON returned by

run_call

get_call_run

; do not invent a transcript.

首先使用
```
plan_call
```
。如果用户未为
```
plan_call
```
提供足够的明确字段，调用时将
```
user_input
```
设置为用户最新消息的原文，以便CALL-E请求补充缺失的细节。
读取返回的
```
plan_id
```
和
```
confirm_token
```
。
如果用户的请求是拨打电话，立即使用规划返回的准确
```
plan_id
```
和
```
confirm_token
```
调用
```
run_call
```
。
在
```
plan_call
```
和
```
run_call
```
之间无需再次确认。
读取返回的
```
run_id
```
，严格保留其原样。
调用
```
run_call
```
后，等待60秒再发起第一次
```
get_call_run
```
请求，除非通话已返回终端状态。
持续使用准确的
```
run_id
```
调用
```
get_call_run
```
，直到通话进入终端状态或用户要求停止。第一次状态检查后，每5到10秒轮询一次。
仅使用已知的
```
run_id
```
调用
```
get_call_run
```
。

终端状态包括

COMPLETED

、

FAILED

、

NO_ANSWER

、

DECLINED

、

CANCELED

、

CANCELLED

、

VOICEMAIL

、

BUSY

和

EXPIRED

。

对于非终端状态，按以下格式回复进度：

text

Phone call is in progress! Progress:
- <HH:MM:SS message>

每个

activity

项使用一个项目符号，保留CALL-E返回的顺序。对于每个项，优先使用格式化为

HH:MM:SS

的事件

ts

加上

message

。如果缺少

ts

，仅使用message。如果没有活动内容，当存在状态时使用

- Status: <status>

；否则使用

- Waiting for the next status update.

。在返回终端状态前，请勿包含最终摘要、详情或转录内容。

当通话进入终端状态时，回复最终的通话结果，按以下顺序包含这些部分：

text

[Status]
<status>

[Call Summary]
<post_summary or summary or message>

[Details]
Callee Number: <primary callee or Not available>
Duration: <duration or Not available>
Time: <start/end time or Not available>
Call id: <call_id or Not available>

[Transcript]
<transcript or Not available.>

如果用户要求额外的最终内容，如关键要点或后续步骤，在

[Transcript]

之后添加一个简短标题并附上内容。所有最终部分均需基于

run_call

或

get_call_run

返回的JSON，请勿编造转录内容。

CLI fallback

CLI备选方案

All CLI commands run from this Cursor plugin must include the CALL-E integration attribution environment:

bash

env CALLE_SOURCE=cursor CALLE_INTEGRATION=cursor_plugin CALLE_INTEGRATION_VERSION=0.1.0

Use the first command form that works.

Prefer the repository-local CLI when the current workspace contains it:

bash

env CALLE_SOURCE=cursor CALLE_INTEGRATION=cursor_plugin CALLE_INTEGRATION_VERSION=0.1.0 node packages/cli/bin/calle.js

If the repository-local CLI is unavailable, use the global command:

bash

env CALLE_SOURCE=cursor CALLE_INTEGRATION=cursor_plugin CALLE_INTEGRATION_VERSION=0.1.0 calle

If neither command works, use the pinned npm package through

npx

bash

env CALLE_SOURCE=cursor CALLE_INTEGRATION=cursor_plugin CALLE_INTEGRATION_VERSION=0.1.0 npx -y @call-e/cli@0.3.2

Only tell the user to install the CLI globally if

npx

is unavailable, network access is blocked, or the user explicitly wants a persistent global command.

Use CLI fallback readiness commands in this order:

Check CLI availability with
```
--help
```
.
Run
```
auth status
```
.
If
```
auth status
```
reports
```
usable: false
```
, run blocking
```
auth login
```
and keep that command running until it exits.
After login completes, run
```
mcp tools
```
.
Confirm that
```
plan_call
```
,
```
run_call
```
, and
```
get_call_run
```
are available.

If a CLI command returns

auth_required

, switch to the CLI fallback readiness flow, complete login, and then retry the original operation after login completes.

Use

references/commands.md

for exact CLI command examples, supported options, and JSON handling rules.

从此Cursor插件运行的所有CLI命令必须包含CALL-E集成归因环境变量：

bash

env CALLE_SOURCE=cursor CALLE_INTEGRATION=cursor_plugin CALLE_INTEGRATION_VERSION=0.1.0

使用第一个可用的命令格式。

如果当前工作区包含仓库本地CLI，优先使用它：

bash

env CALLE_SOURCE=cursor CALLE_INTEGRATION=cursor_plugin CALLE_INTEGRATION_VERSION=0.1.0 node packages/cli/bin/calle.js

如果仓库本地CLI不可用，使用全局命令：

bash

env CALLE_SOURCE=cursor CALLE_INTEGRATION=cursor_plugin CALLE_INTEGRATION_VERSION=0.1.0 calle

如果上述两个命令都不可用，通过

npx

使用固定版本的npm包：

bash

env CALLE_SOURCE=cursor CALLE_INTEGRATION=cursor_plugin CALLE_INTEGRATION_VERSION=0.1.0 npx -y @call-e/cli@0.3.2

仅当

npx

不可用、网络访问受限，或用户明确需要持久化的全局命令时，才告知用户全局安装CLI。

按以下顺序使用CLI备选方案的就绪检查命令：

使用
```
--help
```
检查CLI是否可用。
运行
```
auth status
```
。
如果
```
auth status
```
返回
```
usable: false
```
，运行阻塞式的
```
auth login
```
，并保持该命令运行直到退出。
登录完成后，运行
```
mcp tools
```
。
确认
```
plan_call
```
、
```
run_call
```
和
```
get_call_run
```
工具可用。

如果CLI命令返回

auth_required

，切换到CLI备选方案的就绪检查流程，完成登录后，再重试原操作。

如需准确的CLI命令示例、支持的选项和JSON处理规则，请参考

references/commands.md

。