JadeYingWah

GPT Series Reasoning Style — AI skill for Claude Code

AI community

A delivery-discipline behavior layer for AI agents — turns “the agent says it's done” into “the agent proves it's done”: pre-implementation gate, one backbone + two collaboration forms, evidence-based.

How to install GPT Series Reasoning Style

This entry records only its repository, not the path inside it, so there is no exact command to give. Open JadeYingWah/gpt-series-reasoning-style and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What GPT Series Reasoning Style does

A delivery-discipline behavior layer for AI agents — turns “the agent says it's done” into “the agent proves it's done”: pre-implementation gate, one backbone + two collaboration forms, evidence-based review, real-environment acceptance. 把「Agent 说做完了」变成「Agent 证明做完了」的交付纪律行为层。

Alternatives in AI

  • Orkas — Open-source multi-agent AI desktop client — build and command your AI agent team through conversation 1.5k ★
  • Loushang — AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool 1.3k ★
  • SoloDawn — Catches and repairs AI hallucinations before delivery: three quality gates, 31 built-in rules, a self-healing 312 ★

README

GPT-Series Reasoning Style

**把"Agent 说做完了"变成"Agent 证明做完了"。** **Turn "the agent says it's done" into "the agent proves it's done".**

GPT-Series Reasoning Style · 交付纪律层

![Version](https://img.shields.io/badge/version-1.6.0-blue) ![License: MIT](https://img.shields.io/badge/license-MIT-green) ![Size](https://img.shields.io/badge/SKILL.md-3594%E5%AD%97%E8%8A%82%C2%B735%E8%A1%8C%E9%97%A8%E7%A6%81-orange) ![Experiments](https://img.shields.io/badge/A%2FB%20%E4%B8%8E%E5%AE%9E%E6%B5%8B-300%2B%20%E8%87%82%E6%AC%A1-success) ![Runtime](https://img.shields.io/badge/按需加载-纯文本-blueviolet) ![CI](https://github.com/JadeYingWah/gpt-series-reasoning-style/actions/workflows/ci.yml/badge.svg)


📖 目录 / Table of Contents

🇨🇳 中文版

🇬🇧 English