ai-autonomy

Automate AI-driven development workflows with git-based state tracking and logging.

7|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/wsxwj123/opencode-skills-backup --skill ai-autonomy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-autonomy
Source: https://github.com/wsxwj123/opencode-skills-backup/tree/main/ai-autonomy
Command: npx skills add https://github.com/wsxwj123/opencode-skills-backup --skill ai-autonomy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires httpx, python-dotenv, and includes scripts (resource) and references (resource) components.

What problem does it solve?

AI 自主开发系统让团队能够在任意项目中为 AI 注入自治能力,实现持续开发、跨会话任务跟进与无人值守执行。

Core Features & Use Cases

核心特性包括两种工作模式:嵌入式模式(每个会话自动读取任务继续开发)和脚本循环模式(无人值守批量执行)。工作流包含初始化、任务分派、执行、验证、交接日志与版本控制等环节,支持自定义模板、任务工单、进度记录和多智能体协作。典型用例包括在新项目中注入自治能力,读取 feature_list.json 获取待办任务并自动推进开发;在需要长时间无人工干预时,使用 .autonomy/run_autonomy.py 进行循环驱动。

Quick Start

在任意项目文件夹中执行“初始化自治”以进入嵌入式模式,随后通过会话指令让 AI 继续工作,或运行 run_autonomy.py 启动全自动循环。

Frequently Asked Questions about ai-autonomy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up continuous AI-driven autonomous development workflows in my software project?▼

Continuous AI-driven autonomous development workflows are set up by initializing the autonomy system in your project directory, which creates task tracking files like feature_list.json to enable hands-free, multi-agent task execution.

Can I run AI agents for unattended batch execution of software tasks?▼

Yes, unattended batch execution of software tasks is supported through the script-loop mode. You execute the run_autonomy.py script to drive AI agents continuously without manual intervention across multiple development sessions.

How does AI agent state tracking work across different coding sessions?▼

AI agent state tracking across coding sessions works by using git-based state tracking alongside progress.txt and feature_list.json files, ensuring the workflow resumes correctly from the last completed task.

What is the difference between embedded mode and script-loop mode for AI automation?▼

Embedded mode automatically reads tasks to continue development within each active session, whereas script-loop mode drives unattended batch execution by running the run_autonomy.py script for fully autonomous loops.

Do I need Python dependencies like httpx to enable autonomous AI workflows?▼

Yes, Python dependencies including httpx and python-dotenv are required to enable autonomous AI workflows, providing the necessary environment configuration and HTTP communication capabilities for the multi-agent coordination.

What are the limitations of using git-based state tracking for multi-agent workflows?▼

Git-based state tracking for multi-agent workflows relies on structured files like feature_list.json and progress.txt for task assignment and validation, meaning improper logging or file conflicts can disrupt the orchestration of autonomous task execution.