← Back to Skills Marketplace
添加飞书机器人
by
1054570699
· GitHub ↗
· v1.0.0
· MIT-0
93
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install fsagent-creator
Description
快速创建、删除和管理飞书机器人，支持配置App ID、App Secret及模型，自动更新相关配置和目录结构。
README (SKILL.md)
Agent Creator 技能
快速创建、删除、管理 OpenClaw agent 实例。
触发条件
用户要求创建新机器人、新 agent、新助手、删除 agent、查看 agent 列表时激活此技能。
可用脚本
| 脚本 | 功能 |
|---|---|
list-agents.sh |
查看当前所有 agent |
create-agent.sh |
创建新 agent |
delete-agent.sh |
删除 agent |
创建 Agent
参数
./create-agent.sh \x3Cagent-id> \x3Cagent-name> \x3Capp-id> \x3Capp-secret> [model] [description]
| 参数 | 必填 | 说明 | 示例 |
|---|---|---|---|
| agent-id | ✅ | 唯一标识符（英文小写） | xiaoming |
| agent-name | ✅ | 显示名称 | 小明 |
| app-id | ✅ | 飞书 App ID | cli_xxx |
| app-secret | ✅ | 飞书 App Secret | xxx |
| model | ❌ | 使用的模型（默认 glm-5） | qwen3.5-plus |
| description | ❌ | 人设描述 | 客服助手 |
示例
# 创建一个客服机器人
./create-agent.sh xiaokefu 小客服 cli_a94xxx mysecret123 glm-5 "客服助手，帮助用户解答问题"
# 使用默认模型创建
./create-agent.sh xiaowang 小王 cli_a94xxx mysecret123
创建后步骤
- 执行
openclaw gateway restart重载配置 - 在飞书开放平台配置事件订阅地址
- 在群里 @ 新机器人测试
删除 Agent
./delete-agent.sh \x3Cagent-id>
⚠️ 注意：main agent 不能被删除
查看列表
./list-agents.sh
配置文件位置
- 主配置:
/home/admin/.openclaw/openclaw.json - Agent 目录:
/home/admin/.openclaw/agents/{agent-id}/ - Workspace:
/home/admin/.openclaw/workspace-{agent-id}/
创建时自动完成
- ✅ 创建 agent 目录结构 (
agents/{id}/agent/,agents/{id}/sessions/) - ✅ 创建 workspace 目录和默认文件 (AGENTS.md, SOUL.md, USER.md 等)
- ✅ 更新 openclaw.json:
- 添加到
agents.list - 添加飞书账号到
channels.feishu.accounts - 添加绑定到
bindings - 添加到
tools.agentToAgent.allow
- 添加到
- ✅ 复制 models.json 配置
注意事项
- 飞书机器人需要先在飞书开放平台创建应用
- 需要配置飞书事件订阅地址（通常为 Gateway 地址）
- 创建/删除后需要重启 Gateway 才能生效
Usage Guidance
This skill appears to implement agent creation/listing/deletion as described, but check these before using it:
- Ensure 'node' is installed on the target system (scripts call node) or the scripts will fail. The skill metadata does not declare this dependency.
- Backup /home/admin/.openclaw/openclaw.json before running the scripts; they overwrite portions of the config without validation or backups and could corrupt your config if the file structure differs.
- Be aware App Secret values you supply are written in plaintext into openclaw.json. If you need secrecy, verify how your OpenClaw deployment handles secrets or modify the script to store secrets securely.
- Inspect the hard-coded binding peer id (oc_b34e7d612305f015d0a9a061fef1dec3) and the 'dashscope-coding/' model prefix added by the script — confirm these are intended for your environment. If not, edit the script to avoid auto-binding to an external/unknown peer or to use a configurable value.
- Prefer running this first in a staging/non-production environment to confirm behavior and to avoid accidentally exposing credentials or binding agents to unintended groups.
Given these mismatches and the plaintext handling of secrets, proceed only after review and possible modifications; the issues look like sloppy engineering rather than clear malicious intent, hence 'suspicious'.
Capability Analysis
Type: OpenClaw Skill
Name: fsagent-creator
Version: 1.0.0
The skill bundle provides scripts for managing OpenClaw agents but contains a significant code injection vulnerability. In 'create-agent.sh' and 'delete-agent.sh', shell variables (such as agent-id and agent-name) are directly interpolated into a 'node -e' command string without sanitization. This allows an attacker to execute arbitrary JavaScript code by providing crafted input to the agent creation process. While the bundle's stated purpose of managing Feishu (Lark) agents appears legitimate and includes defensive instructions for sub-agents, the insecure handling of configuration updates poses a risk of local code execution.
Capability Assessment
Purpose & Capability
The scripts' actions (create agent directories, update /home/admin/.openclaw/openclaw.json, add 飞书 account entries) match the skill's stated purpose of managing 飞书/OpenClaw agents. Minor inconsistencies: the agent model is written as 'dashscope-coding/<model>' in the script while SKILL.md references plain model names (e.g., glm-5), and a hard-coded binding peer id ('oc_b34e7d612305f015d0a9a061fef1dec3') is added without explanation.
Instruction Scope
SKILL.md and scripts explicitly read and write the OpenClaw configuration and create workspace files—this is in-scope for agent creation. The scripts store app-secret values directly into openclaw.json and assume certain config structure (channels.feishu.accounts, agents.list, bindings, tools.agentToAgent.allow) exist; there is no validation or backup step. No external network endpoints are contacted by the scripts themselves.
Install Mechanism
There is no install spec (instruction-only), which lowers distribution risk. However, the bundled scripts invoke 'node' for JSON manipulation but the skill metadata and SKILL.md do not declare node as a required binary or dependency—this is a mismatch that may cause failures or unexpected behavior when run.
Credentials
The skill requests no environment variables and takes App ID/App Secret as runtime parameters (which is appropriate). However, it then writes those secrets in plaintext into /home/admin/.openclaw/openclaw.json. There is no declaration about where secrets are stored or whether they are encrypted, and no credentials unrelated to the purpose are requested.
Persistence & Privilege
The scripts modify system configuration (/home/admin/.openclaw/openclaw.json) and create directories under /home/admin/.openclaw — expected for this purpose. Concern: the skill injects a hard-coded binding that targets a specific peer id (oc_b34e7d6...), which effectively auto-binds new agents to that peer; this could be unwanted or a misconfiguration and should be reviewed. The skill does not request 'always: true' and does not autonomously persist beyond updating config and files.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install fsagent-creator - After installation, invoke the skill by name or use
/fsagent-creator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release with major workflow and tooling changes:
- Replaced Python-based agent creation and packaging with simple shell scripts: create-agent.sh, delete-agent.sh, and list-agents.sh.
- Removed prior asset templates and Python scripts for generating and bundling agent identity files.
- New workflow supports rapid creation, deletion, and listing of agents via command-line, with clear required/optional parameters.
- Agent setup now includes automated directory creation and configuration updates in openclaw.json.
- Documentation updated to reflect changed commands, configuration structure, and post-creation steps.
- Focus shifted from packaging agent personas for ClawHub to direct management of agent instances and workspace structure.
Metadata
Frequently Asked Questions
What is 添加飞书机器人?
快速创建、删除和管理飞书机器人，支持配置App ID、App Secret及模型，自动更新相关配置和目录结构。 It is an AI Agent Skill for Claude Code / OpenClaw, with 93 downloads so far.
How do I install 添加飞书机器人?
Run "/install fsagent-creator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 添加飞书机器人 free?
Yes, 添加飞书机器人 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 添加飞书机器人 support?
添加飞书机器人 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 添加飞书机器人?
It is built and maintained by 1054570699 (@1054570699); the current version is v1.0.0.
More Skills