← 返回 Skills 市场
Agent Control
作者
Alin Catalin
· GitHub ↗
· v0.1.0
· MIT-0
352
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-control
功能描述
Manage OpenClaw isolated agents from chat with short commands. Use when the user asks to create/list/switch/bind/delete agents, route channels to a specific...
使用说明 (SKILL.md)
Agent Control
Translate short chat commands into OpenClaw CLI agent operations.
Command grammar
Accept these commands (case-insensitive, trim extra spaces):
agent listagent create \x3Cname> [workspace=\x3Cpath>] [model=\x3Cid>]agent switch \x3Cname> [channel=\x3Cchannel[:accountId]>]agent bind \x3Cname> \x3Cchannel[:accountId]>agent unbind \x3Cname> \x3Cchannel[:accountId]>agent delete \x3Cname>agent identity \x3Cname> [display="..."] [emoji=🗡️] [avatar=\x3Cpath>]
If input is ambiguous, ask one focused question.
Execution mapping
Run these exact command patterns:
- List:
openclaw agents list
- Create:
openclaw agents add \x3Cname> --workspace \x3Cpath> --model \x3Cid>- Omit optional flags when missing.
- Default workspace when omitted:
~/clawd/agents/\x3Cname>.
- Switch (route this channel/account to an agent):
openclaw agents bind --agent \x3Cname> --bind \x3Cchannel[:accountId]>- If channel is omitted, infer from current surface when possible (e.g.
webchat).
- Bind / unbind:
openclaw agents bind --agent \x3Cname> --bind \x3Cbinding>openclaw agents unbind --agent \x3Cname> --bind \x3Cbinding>
- Delete:
- Require explicit confirmation in the same turn for destructive action.
- Then run:
openclaw agents delete \x3Cname>
- Identity:
openclaw agents set-identity --agent \x3Cname> [--name \x3Cdisplay>] [--emoji \x3Cemoji>] [--avatar \x3Cpath>]
Response style
After each operation, return:
- A one-line result (success/failure)
- The next useful command for the user
Keep it brief and practical.
Safety rules
- Treat
agent deleteas destructive: confirm before running. - Never run unrelated shell commands.
- If a command fails, show the error and one concrete fix.
scripts/
Use scripts/example.py as a deterministic helper wrapper for command parsing/execution when needed.
安全使用建议
This skill appears to do what it claims: it translates short chat commands into openclaw CLI operations and ships a small helper script that runs those CLI commands. Before installing, confirm you trust the local openclaw binary (the skill will invoke it), and ensure the agent prompts the user for explicit confirmation before performing deletions because the helper script will execute a delete when invoked. Note that the SKILL.md documents an "identity" command that the provided script does not implement — if you need that feature, ask the author for clarification or patch the helper. If you allow autonomous invocation, be comfortable with the agent being able to run your openclaw CLI on your behalf.
功能分析
Type: OpenClaw Skill
Name: agent-control
Version: 0.1.0
The skill provides a legitimate management interface for OpenClaw agents, allowing the agent to list, create, and delete agents via the 'openclaw' CLI. The implementation in 'scripts/example.py' uses safe subprocess execution patterns, and 'SKILL.md' includes explicit safety instructions such as requiring user confirmation for destructive actions.
能力评估
Purpose & Capability
Name/description map to the actions implemented: the SKILL.md maps short chat commands to OpenClaw CLI agent operations and the included helper script invokes the OpenClaw CLI. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md stays narrowly focused on running OpenClaw CLI commands and safety rules (confirm deletes, don't run unrelated shell commands). Two minor inconsistencies: (1) SKILL.md documents an "agent identity" command and avatar handling, but the included scripts/example.py does not implement an identity subcommand; (2) SKILL.md requires explicit confirmation before running destructive delete operations, but the helper script will run openclaw agents delete if invoked — the expectation is the agent must prompt before calling the script.
Install Mechanism
No install spec and no external downloads. This is instruction-only plus a small local helper script (no extracted archives or third-party packages). Lowest-risk install profile.
Credentials
No environment variables, credentials, or external endpoints are requested. The script uses the user's home directory for default workspaces (~/clawd/agents/<name>), which is reasonable for an agent-management tool.
Persistence & Privilege
always is false and the skill does not request persistent system-wide modifications. The helper script only invokes the OpenClaw CLI and prints structured results; it does not modify other skills or agent settings itself.
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 agent-control - 安装完成后，直接呼叫该 Skill 的名称或使用
/agent-control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
v0.1.0
Initial release
元数据
常见问题
Agent Control 是什么？
Manage OpenClaw isolated agents from chat with short commands. Use when the user asks to create/list/switch/bind/delete agents, route channels to a specific... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 352 次。
如何安装 Agent Control？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-control」即可一键安装，无需额外配置。
Agent Control 是免费的吗？
是的，Agent Control 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Agent Control 支持哪些平台？
Agent Control 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 Agent Control？
由 Alin Catalin（@alincatalin）开发并维护，当前版本 v0.1.0。
推荐 Skills