2233admin

Full Self Coding — AI skill for Claude Code

AI community

No prompts, no instructions, no plans, you have 100~1000 AI agent coding in parallel now, solving all possible problems and issues in your codebase.

How to install Full Self Coding

This entry records only its repository, not the path inside it, so there is no exact command to give. Open 2233admin/full-self-coding and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Full Self Coding does

No prompts, no instructions, no plans, you have 100~1000 AI agent coding in parallel now, solving all possible problems and issues in your codebase.

Alternatives in AI

Hindsight — State-of-the-art long-term memory for AI agents by Vectorize 6.7k ★
Welcome — AI Research Skills — You now have access to 86 production-ready skills covering the entire AI research lifecycle: literature survey 5.4k ★
Define — Definition phase - Clarify and scope problems with multi-AI consensus 2.8k ★

README

Full Self Coding (FSC)

🔗 **OpenClaw集成版** - 本分支基于原版FSC，集成OpenClaw实现生产级多节点集群部署

**原版**: https://github.com/NO-CHATBOT-REVOLUTION/full-self-coding

No prompts, no instructions, no plans, you have 100~1000 AI agent coding in parallel now, solving all possible problems and issues in your codebase.

🌟 Overview

Full Self Coding (FSC) is a sophisticated framework designed to automate software engineering tasks by integrating multiple AI agents (Claude Code, Gemini CLI) within Docker containers. It provides intelligent codebase analysis, task decomposition, automated code modification, and comprehensive reporting capabilities.

Key Features

🤖 Multi-Agent Support: Integration with Claude Code, Gemini CLI, and extensible agent architecture
📦 Containerized Execution: Secure, isolated Docker-based task execution
🔍 Intelligent Analysis: Automated codebase analysis and task identification
⚙️ Flexible Configuration: Hierarchical configuration system with environment variable support
📊 Comprehensive Reporting: Detailed execution reports with git diff tracking
🔄 Parallel Processing: Multi-container parallel task execution with resource management
🛡️ Robust Error Handling: Comprehensive error recovery and graceful degradation

OpenClaw集成版 vs 原版

特性	原版 FSC	OpenClaw集成版
部署方式	单机	多节点集群
任务调度	Docker本地	OpenClaw Gateway
Session管理	无	任务隔离Session
多节点路由	手动	自动Routing
内网互联	无	WireGuard VPN
规模	单机并行	跨服务器并行

本分支新增特性

✅ 多节点集群部署: 支持跨服务器部署
✅ OpenClaw Gateway: 统一任务调度中心
✅ Session隔离: 任务间上下文隔离
✅ 智能路由: 根据任务类型自动选择节点
✅ WireGuard内网: 主要跨服务器通信方式 (10.10.0.x)
✅ SSH隧道: 备用通道
✅ 自动部署脚本: 一键部署整个集群

自定义调度器 (类似渲染集群)

本分支还实现了类似渲染集群的自定义调度器：

功能	说明
错误分类器	自动分类任务错误类型，智能重试
Token流控	控制API调用，避免超额
时长预估	估算任务执行时间，优化资源分配
DAG依赖	支持任务依赖关系，拓扑排序调度
多节点协同	跨服务器任务分发与结果汇总