← 返回 Skills 市场
Abby Autonomy
作者
earnabitmore365
· GitHub ↗
· v1.0.0
461
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install abby-autonomy
功能描述
使 Abby 能主动从任务队列获取并执行任务,自主管理任务状态,持续推进工作至完成或资源限制。
使用说明 (SKILL.md)
Abby Autonomy Skill
自主任务执行系统 - 让 从被动 Abby变主动
解决的问题
让 Abby 从"被动等待"变成"主动工作"!
当前问题:
- Heartbeat 只检查"有没有需要处理的"
- 空闲时说 "HEARTBEAT_OK"
- 等待爸爸指令才能工作
改进后:
- 主动从任务队列拿任务做
- 持续工作直到限制
- 自主推进任务
核心概念
1. 任务队列 (tasks/QUEUE.md)
# Task Queue
## Ready (可取用)
- [ ] 回测 RSI 策略
- [ ] 下载 BTC 数据
## In Progress (进行中)
- [x] @abby: 回测 MA 策略 (执行中, 剩余 5分钟)
## Done Today (今日完成)
- [x] 完成 MA 策略回测
## Blocked (阻塞)
- [ ] 等待爸爸确认
2. 状态追踪
Abby 记忆中记录当前任务状态:
{
"current_task": "回测 MA 策略",
"task_status": "running",
"estimated_completion": "20:15",
"progress": "50%",
"started_at": "20:05"
}
核心功能
1. 任务队列管理
| 功能 | 说明 |
|---|---|
| 读取队列 | 从文件读取任务列表 |
| 拿任务 | 取最高优先级任务 |
| 更新队列 | 标记完成/进行中/阻塞 |
| 记录进度 | 写回记忆 |
2. 状态检查
| 检查 | 说明 |
|---|---|
| 任务状态 | 有没有正在执行的任务? |
| 紧急事项 | 人类消息?系统错误? |
| 资源限制 | Token 快用完?时间到? |
3. 自主执行
| 步骤 | 说明 |
|---|---|
| 1. 检查 | 有紧急事项? |
| 2. 检查 | 有正在执行的任务? |
| 3. 读取 | 从队列拿任务 |
| 4. 执行 | 开始工作 |
| 5. 记录 | 标记状态 |
| 6. 等待 | 直到限制或完成 |
任务类型
自动任务
| 任务 | 说明 |
|---|---|
| 回测 | 运行策略回测 |
| 下载 | 下载历史数据 |
| 研究 | 分析市场数据 |
| 优化 | 优化交易参数 |
阻塞任务
| 状态 | 说明 |
|---|---|
| 等待爸爸确认 | 需要人工决策 |
| 等待系统资源 | 资源不足 |
| 等待外部数据 | API 不可用 |
使用方法
创建任务
# tasks/QUEUE.md
## Ready (可取用)
- [ ] 回测 RSI 策略 (优先级: 高)
- [ ] 下载 BTC 1h 数据 (优先级: 中)
Abby 心跳时
每3分钟:
1. 检查紧急事项
2. 检查当前任务状态
3. 如果空闲 → 拿任务做
4. 完成后更新队列
目录结构
abby-autonomy/
├── SKILL.md # 技能文档
├── tasks/
│ └── QUEUE.md # 任务队列模板
├── scripts/
│ ├── __init__.py
│ ├── queue.py # 队列管理
│ ├── status.py # 状态检查
│ ├── heartbeat.py # 主动心跳
│ └── executor.py # 任务执行
└── memory/
└── task_state.json # 任务状态
状态流转
Ready → In Progress → Done Today
↘ Blocked
In Progress → Done Today (完成)
→ Ready (暂停)
→ Blocked (阻塞)
重要概念
为什么需要这个?
-
❌ 被动 Heartbeat:说 "HEARTBEAT_OK" 浪费机会
-
❌ 没有任务队列:不知道该做什么
-
❌ 重复执行:同一个任务做多次
-
✅ 主动 Heartbeat:从队列拿任务
-
✅ 任务队列:永远有工作可做
-
✅ 状态追踪:避免重复执行
依赖
- long-term-memory skill (用于状态追踪)
- cron job (定时检查)
相关文档
创建于 2026-02-15
安全使用建议
This skill appears to implement a local task queue and autonomous heartbeat, which matches its description, but there are a few red flags you should consider before installing:
- The package references and attempts to import a 'long-term-memory' skill from the agent workspace (sys.path insertion). Verify that the long-term-memory skill exists and is trusted, because Abby will load and execute that code at runtime and may access its data.
- The SKILL.md and scripts mention an executor.py that is not included — the skill may be incomplete and could behave unexpectedly if you rely on it.
- There are minor code inconsistencies (duplicate imports/names) suggesting limited QA. Test in a controlled environment first (no sensitive data or credentials available), and inspect the long-term-memory skill code the bundle will import.
- If you allow the skill to run autonomously, consider limiting its permissions and monitoring file writes to tasks/ and memory/ directories.
If you want, I can list exact lines where the sys.path insertion and missing executor reference appear, or help craft a safer test plan for trying this skill in an isolated environment.
功能分析
Type: OpenClaw Skill
Name: abby-autonomy
Version: 1.0.0
The OpenClaw AgentSkills bundle 'abby-autonomy' is classified as benign. The skill's purpose is to enable autonomous task execution by managing a local task queue and state. All file operations are confined to the skill's designated `tasks/` and `memory/` directories. There is no evidence of data exfiltration, unauthorized command execution, network activity, or obfuscation. The `SKILL.md` provides instructions for the agent's internal operation but does not contain any prompt injection attempts to subvert the agent's core directives or perform malicious actions. The `scripts/heartbeat.py` contains a `TODO` for actual task execution, but its current implementation only simulates work, posing no immediate risk.
能力评估
Purpose & Capability
Name/description align with the included code (queue/heartbeat/status). The skill reads/writes a local tasks/QUEUE.md and memory/task_state.json, which fits the stated purpose. However: SKILL.md and scripts reference an executor.py that is not present in the bundle, and __init__.py imports 'complete_task' from both queue and status (name collision/inconsistency). These mismatches suggest incomplete or sloppy packaging.
Instruction Scope
SKILL.md and the scripts describe only local file-based queue management and periodic heartbeats, which is appropriate. But heartbeat.py inserts a path into sys.path to import code from workspace/skills/long-term-memory (outside the skill bundle). That means at runtime the skill will attempt to load another skill's code from the agent workspace — behavior not strictly documented beyond a dependency note. The urgent-check mentions 'Gateway' and human messages (TODO) but those checks are unimplemented. Overall the runtime instructions do not exfiltrate data, but the external import expands the runtime surface and could access other skill data.
Install Mechanism
No install specification and no remote downloads; the skill is provided as local code and operates on local files. This is low install risk.
Credentials
The skill requests no environment variables or credentials, and operates on local files only. The main proportionality concern is the explicit sys.path insertion to a 'long-term-memory' skill in the agent workspace — that gives the skill potential indirect access to whatever that other skill exposes (including any data it stores). The dependency on 'long-term-memory' is declared in SKILL.md, but users should verify that the referenced skill is trustworthy.
Persistence & Privilege
Flags show normal autonomy settings (always:false, user-invocable:true, model invocation allowed). The skill only writes to its own tasks/ and memory/ files; it does not request to modify other skills or global agent configuration. No 'always:true' privilege is requested.
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 abby-autonomy - 安装完成后,直接呼叫该 Skill 的名称或使用
/abby-autonomy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
Abby Autonomy Skill 1.0.0 – Empowering Abby to work proactively
- Transforms Abby from passive waiting ("HEARTBEAT_OK") to active, autonomous task execution.
- Implements a structured task queue system with clear states (Ready, In Progress, Done Today, Blocked).
- Abby now pulls new tasks, tracks progress in memory, and works until set limits or completion.
- Includes robust status checks for emergencies, resource limits, and ongoing tasks.
- Integrates with long-term memory and cron for state tracking and scheduled operation.
元数据
常见问题
Abby Autonomy 是什么?
使 Abby 能主动从任务队列获取并执行任务,自主管理任务状态,持续推进工作至完成或资源限制。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 461 次。
如何安装 Abby Autonomy?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install abby-autonomy」即可一键安装,无需额外配置。
Abby Autonomy 是免费的吗?
是的,Abby Autonomy 完全免费(开源免费),可自由下载、安装和使用。
Abby Autonomy 支持哪些平台?
Abby Autonomy 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 Abby Autonomy?
由 earnabitmore365(@earnabitmore365)开发并维护,当前版本 v1.0.0。
推荐 Skills