← 返回 Skills 市场
Agent Autonomy Kit
作者
ryancampbell
· GitHub ↗
· v1.0.0
19807
总下载
69
收藏
203
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-autonomy-kit
功能描述
Stop waiting for prompts. Keep working.
安全使用建议
Install only if you intentionally want scheduled, unattended agent activity. Before enabling cron jobs, define allowed task types, writable paths, external posting rules, spending or token limits, logging, and a simple way to disable the schedules. Avoid using it in sensitive or production workspaces until those controls are in place.
功能分析
Type: OpenClaw Skill
Name: agent-autonomy-kit
Version: 1.0.0
This skill bundle is classified as benign. It aims to enhance agent autonomy by setting up a task queue and enabling continuous operation. While it utilizes cron jobs for persistence (via `openclaw cron add` commands in `README.md` and `SKILL.md`) and instructs the agent to perform broad tasks like 'Do meaningful work' or 'Do research, writing, or analysis' (in `templates/HEARTBEAT.md` and cron messages), these capabilities are directly aligned with the stated purpose of making the agent proactive and productive. There is no evidence of intentional harmful behavior, data exfiltration, malicious execution, or prompt injection designed to subvert the agent for unauthorized actions.
能力评估
Purpose & Capability
Task queues, proactive heartbeats, memory updates, team coordination, and cron-triggered work match the stated autonomy purpose.
Instruction Scope
The instructions tell the agent to pick tasks, do work, update queues, log memory, add new tasks, and post team updates, but do not define allowed task categories, writable paths, approval gates, or stop conditions.
Install Mechanism
Installation is a documented git clone with markdown templates; no executable scripts were present. The README separately provides OpenClaw cron commands that create scheduled unattended runs.
Credentials
The skill is general-purpose and may run in repositories or workspaces with sensitive data, yet it encourages broad research, writing, analysis, file updates, and channel posting without environment-specific containment.
Persistence & Privilege
Cron examples for daily reports, morning kickoff, and overnight work create persistent unattended execution, including a prompt to spawn team members, without clear monitoring, kill-switch, reversal, or permission guidance.
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-autonomy-kit - 安装完成后，直接呼叫该 Skill 的名称或使用
/agent-autonomy-kit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
Initial release of Agent Autonomy Kit.
- Enables agents to work proactively without waiting for prompts.
- Introduces a task queue system and proactive "heartbeat" for continuous task execution.
- Supports scheduled operations with cron jobs for overnight work and daily reports.
- Aims to improve productivity by keeping agents working until limits are reached.
元数据
常见问题
Agent Autonomy Kit 是什么？
Stop waiting for prompts. Keep working. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 19807 次。
如何安装 Agent Autonomy Kit？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-autonomy-kit」即可一键安装，无需额外配置。
Agent Autonomy Kit 是免费的吗？
是的，Agent Autonomy Kit 完全免费（开源免费），可自由下载、安装和使用。
Agent Autonomy Kit 支持哪些平台？
Agent Autonomy Kit 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 Autonomy Kit？
由 ryancampbell（@ryancampbell）开发并维护，当前版本 v1.0.0。
推荐 Skills