← 返回 Skills 市场
298
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install kiro-agent-chat
功能描述
Inter-agent communication via shared JSON file. Use when two or more OpenClaw instances need to exchange messages, coordinate, or pass information. Works acr...
使用说明 (SKILL.md)
Agent Chat
Two OpenClaw agents communicate through a shared JSON queue file.
Setup
Set the chat file path in TOOLS.md:
## Agent Chat
chat_file: ~/shared/agent-chat.json
Usage
Send Message
# Write to queue
SENDER="kiro-local" \
RECEIVER="kiro-vps" \
MESSAGE="Selam! Nasılsın?" \
python3 scripts/send_message.py ~/shared/agent-chat.json
Read My Messages
# Read messages sent to you
MY_NAME="kiro-local" \
python3 scripts/read_messages.py ~/shared/agent-chat.json
Delete Processed Messages
python3 scripts/delete_messages.py ~/shared/agent-chat.json 1772698493241,1772698493242
Flow
- Agent A writes message to shared file
- Agent B reads file, sees new message
- Agent B responds, writes to file
- Agent A reads response
Remote Usage (via SSH)
# From local, send to VPS agent
ssh -i ~/.ssh/openclaw.pem ubuntu@host "
SENDER='kiro-local' RECEIVER='kiro-vps' MESSAGE='Selam!' python3 /path/to/send_message.py /shared/agent-chat.json
"
Queue Format
{
"messages": [
{
"id": 1772698493241,
"sender": "kiro-local",
"receiver": "kiro-vps",
"message": "Selam!",
"timestamp": "2026-03-05T11:14:53.241676"
}
]
}
安全使用建议
This skill is a simple file-based message queue and appears internally consistent. Before installing, verify the chat file path and set strict filesystem permissions so only intended agents/users can read/write it (sensitive data should not be stored in plaintext there). Note the metadata does not list the environment variables the scripts use (SENDER, RECEIVER, MESSAGE, MY_NAME) — be careful not to expose secrets via those env vars or in the shared file. The remote SSH examples require you to use your private key; do not share that key. Also be aware the scripts perform plain read/write without locking, so concurrent writes may corrupt the file; if you need robust or secure messaging across hosts, consider using an authenticated messaging service or add file-locking/encryption.
功能分析
Type: OpenClaw Skill
Name: kiro-agent-chat
Version: 1.0.0
The skill bundle provides a straightforward mechanism for inter-agent communication using a shared JSON file. The Python scripts (send_message.py, read_messages.py, and delete_messages.py) perform basic file operations and environment variable processing aligned with the stated purpose, showing no signs of malicious intent, data exfiltration, or unauthorized execution.
能力评估
Purpose & Capability
Name/description match the included scripts and instructions. The three Python scripts implement writing, reading, and deleting messages in a shared JSON file and there are no unrelated binaries, cloud credentials, or unexpected external services requested.
Instruction Scope
SKILL.md stays within the chat-file use case but relies on environment variables (SENDER, RECEIVER, MESSAGE, MY_NAME) and editing TOOLS.md without declaring them in metadata. Remote usage examples show using ssh with a private key path (~/.ssh/openclaw.pem) — this is expected for SSH-based operation but requires the user to supply and protect their SSH keys. The instructions do not attempt to read arbitrary local files or send data to external endpoints beyond the shared file/SSH examples.
Install Mechanism
There is no external install or download step; the skill is instruction+included scripts only. All code is present in the package and nothing is pulled from third‑party URLs or installed from untrusted sources.
Credentials
No required environment variables are declared in the registry metadata, but the runtime expects SENDER, RECEIVER, MESSAGE and MY_NAME environment variables. These are not sensitive by themselves, but the README examples reference using a private SSH key for remote execution — users must protect that key and avoid embedding secrets in the shared JSON. The skill does not request unrelated credentials.
Persistence & Privilege
always is false, the skill does not request persistent elevated privileges, and it does not modify other skills' configurations or system-wide settings.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install kiro-agent-chat - 安装完成后,直接呼叫该 Skill 的名称或使用
/kiro-agent-chat触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
İlk versiyon
元数据
常见问题
Kiro Agent Chat 是什么?
Inter-agent communication via shared JSON file. Use when two or more OpenClaw instances need to exchange messages, coordinate, or pass information. Works acr... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 298 次。
如何安装 Kiro Agent Chat?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install kiro-agent-chat」即可一键安装,无需额外配置。
Kiro Agent Chat 是免费的吗?
是的,Kiro Agent Chat 完全免费(开源免费),可自由下载、安装和使用。
Kiro Agent Chat 支持哪些平台?
Kiro Agent Chat 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Kiro Agent Chat?
由 sonerbo(@sonerbo)开发并维护,当前版本 v1.0.0。
推荐 Skills