Enable communication and file sharing between agents in a Sconsole environment.
Install
mkdir -p .claude/skills/sconsole-intercom && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11812" && unzip -o skill.zip -d .claude/skills/sconsole-intercom && rm skill.zipInstalls to .claude/skills/sconsole-intercom
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Sconsole Agent 间通信 — 通过共享卷发现、发送和接收消息Key capabilities
- →Discover other Sconsole agents
- →Send messages to a target agent
- →Check own agent's inbox for messages
- →Read specific message content
- →Clean up read messages from inbox
- →Upload files from agent container to host
How it works
The skill enables Sconsole agents to discover each other and exchange messages and files using a shared filesystem volume for registry and mailboxes.
Inputs & outputs
When to use sconsole-intercom
- →Discover other agents
- →Send message to another agent
- →Upload files to host
About this skill
Sconsole Agent 间通信 (Intercom)
使 Sconsole 项目内部署的 agent 可以通过共享卷 (/agent/volume) 互相发现和通信。
工作原理
┌─────────────────────────────────────────────┐
│ 宿主机: Sconsole/container_volume/ │
│ ├── registry/ ← agent 注册信息 │
│ │ ├── 36.json ← agent #36 的元数据 │
│ │ └── 37.json ← agent #37 的元数据 │
│ └── mailbox/ ← 消息信箱 │
│ ├── 36/inbox/ ← #36 的收件箱 │
│ └── 37/inbox/ ← #37 的收件箱 │
│ ↓ 容器挂载为 /agent/volume │
└─────────────────────────────────────────────┘
所有 agent 容器共享同一个目录,通过文件系统进行发现和消息传递。
可用命令
发现其他 agent
python3 /agent/skills/sconsole-intercom/scripts/discover.py
列出当前注册的所有 agent(排除自身),输出 JSON。
发送消息
python3 /agent/skills/sconsole-intercom/scripts/message.py send <target_id> "<content>"
向指定 agent 发送消息。消息写入目标的收件箱。
检查收件箱
python3 /agent/skills/sconsole-intercom/scripts/message.py check
查看自己的收件箱,列出所有未读消息。
读取消息
python3 /agent/skills/sconsole-intercom/scripts/message.py read <message_id>
读取指定消息的完整内容。
清理已读消息
python3 /agent/skills/sconsole-intercom/scripts/message.py clean
清空自己的收件箱。
上传文件到宿主机
python3 /agent/skills/sconsole-intercom/scripts/upload.py <workspace_id> <file_path> [filename]
将 agent 容器内的文件上传到宿主机工作空间目录,上传后的文件可通过 Sconsole 前端浏览器下载,或由其他 agent 访问。
参数说明:
<workspace_id>— 工作空间 ID(即 instance_id)<file_path>— 容器内的文件绝对路径[filename]— 可选,自定义上传后的文件名,默认使用原文件名
上传目标: 文件保存在宿主机 ~/.sconsole/agent_upload/<workspace_id>/ 目录下。
工作原理:
- 读取容器内指定文件
- 通过 multipart/form-data POST 到 Sconsole 服务端的
/api/workspaces/{id}/upload端点 - 服务端保存到宿主机目录
- Sconsole 前端工作空间页面可通过「📁 文件」按钮浏览和下载
示例:
# 将分析结果上传到工作空间 60
python3 /agent/skills/sconsole-intercom/scripts/upload.py 60 /tmp/analysis_result.json
# 上传并自定义文件名
python3 /agent/skills/sconsole-intercom/scripts/upload.py 60 /tmp/output.csv results_20260604.csv
注意: 需确保 Sconsole 服务端可从容器内访问。默认通过
SCONSOLE_SERVER环境变量确定地址,备用为http://host.containers.internal:58091。
使用示例
# Agent A (instance_id=36) 发现其他 agent
$ python3 discover.py
[{"instance_id": 37, "model_name": "deepseek-v4-pro", "registered_at": "..."}]
# Agent A 向 Agent B 发送消息
$ python3 message.py send 37 "请帮我分析 /agent/volume/data.csv"
# Agent B 检查收件箱
$ python3 message.py check
[{"id": "msg_001", "from": 36, "content": "请帮我分析 /agent/volume/data.csv", ...}]
# Agent B 回复 (通过发送消息给 Agent A)
$ python3 message.py send 36 "分析完成,结果在 /agent/volume/result.json"
通信协议
每条消息是一个 JSON 文件,格式:
{
"id": "msg_1717000000_abc123",
"from": 36,
"to": 37,
"content": "消息内容",
"timestamp": "2026-05-29T12:00:00",
"reply_to": null
}
注册机制
Agent 启动时自动将元数据写入 /agent/volume/registry/{instance_id}.json:
{
"instance_id": 36,
"api_key": "ecb350...",
"api_port": 18000,
"model_name": "deepseek-v4-pro",
"registered_at": "2026-05-29T12:00:00"
}
Agent 停止时应清理自己的注册信息(容器销毁时自动随共享卷持久化,可手动清理)。
When not to use it
- →Communicating with agents not deployed within the Sconsole project
- →When agent communication does not need to be persistent via shared volume
- →When Sconsole server is not accessible from the container
Limitations
- →Requires agents to be deployed within the Sconsole project
- →Communication relies on a shared volume (`/agent/volume`)
- →Sconsole server must be accessible from the container for file uploads
How it compares
This communication method uses a shared filesystem for agent discovery and messaging, providing a direct file-based inter-agent communication channel within the Sconsole environment.
Compared to similar skills
sconsole-intercom side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| sconsole-intercom (this skill) | 0 | 2mo | Review | Intermediate |
| crewai | 4 | 6mo | No flags | Advanced |
| autonomous-agent-patterns | 4 | 6mo | Review | Intermediate |
| computer-use-agents | 10 | 6mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
crewai
davila7
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.
autonomous-agent-patterns
davila7
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.
computer-use-agents
davila7
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.
voice-ai-engine-development
sickn33
Build real-time conversational AI voice engines using async worker pipelines, streaming transcription, LLM agents, and TTS synthesis with interrupt handling and multi-provider support
crewai-developer
smallnest
Comprehensive CrewAI framework guide for building collaborative AI agent teams and structured workflows. Use when developing multi-agent systems with CrewAI, creating autonomous AI crews, orchestrating flows, implementing agents with roles and tools, or building production-ready AI automation. Essential for developers building intelligent agent systems, task automation, and complex AI workflows.
hummingbot
2025Emma
Hummingbot trading bot framework - automated trading strategies, market making, arbitrage, connectors for crypto exchanges. Use when working with algorithmic trading, crypto trading bots, or exchange integrations.