product-pro

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

🚀 Skill: Product Pro (v1.1.0)

Executive Summary

执行摘要

The

product-pro

is the orchestrator of the product's vision, strategy, and "Magic Moments." In 2026, Product Management has evolved from managing deterministic backlogs to curating Probabilistic AI Loops. This skill focuses on building products that "Think," leveraging Agentic Workflows for rapid validation, and maintaining Strategic Integrity in a world of high-velocity AI development.

product-pro

是产品愿景、战略和「魔法时刻」的编排者。2026年，产品管理已经从管理确定性待办事项演进为搭建Probabilistic AI Loops。本技能聚焦于构建具备「思考」能力的产品，利用Agentic Workflows实现快速验证，以及在高速AI发展的环境下保持战略完整性。

📋 Table of Contents

AI产品理念
「禁止」清单（反模式）
科学假设生成
AI产品战略
快速Agentic原型设计
产品经理上下文工程
参考库

🏛️ AI Product Philosophies

🏛️ AI产品理念

Confidence over Certainty: Design for probabilistic outcomes. What happens at 70% confidence?
Magic Moments First: Focus on the core reasoning loop that provides 80% of the value.
Context is the Moat: The more your AI knows about the user's domain, the harder you are to replace.
Agentic Velocity: Use AI agents to build and test prototypes in days.
Ethical Guardianship: Ensure that AI decisions are transparent, biased-free, and secure.

置信度优于确定性：为概率性结果做设计，置信度为70%时的应对方案是什么？
魔法时刻优先：聚焦于贡献80%价值的核心推理循环。
上下文就是护城河：你的AI对用户领域了解越深，就越难被替代。
Agentic开发效率：使用AI Agent在数天内完成原型的构建与测试。
伦理守护：确保AI决策透明、无偏见且安全。

🚫 The "Do Not" List (Anti-Patterns)

🚫 「禁止」清单（反模式）

Anti-Pattern	Why it fails in 2026	Modern Alternative
Deterministic Roadmaps	AI features fail or pivot rapidly.	Use Experiment Loops.
Silent AI Failures	Destroys user trust instantly.	Use Graceful Uncertainty UI.
"AI for AI's Sake"	High cost, low business value.	Problem-First Integration.
Thin Context	Leads to hallucinations.	Context Engineering.
Ignoring Data Privacy	Legal and brand catastrophe.	Privacy-by-Design Architecture.

反模式	2026年失效原因	现代替代方案
确定性路线图	AI功能容易失效或快速转向	使用实验循环
静默AI故障	会瞬间摧毁用户信任	使用Graceful Uncertainty UI
「为了AI而AI」	成本高，商业价值低	问题优先的集成方案
上下文薄弱	会导致幻觉生成	上下文工程
忽视数据隐私	引发法律风险和品牌灾难	Privacy-by-Design Architecture

🧪 Scientific Hypothesis Generation

🧪 科学假设生成

We use a rigorous method to test AI improvements:

Observation: "Users are confused by Feature X."
Hypothesis: "If we add a Reasoning Agent to Feature X, then completion rate will rise 20%."
Experiment: Build a minimal agentic prototype.
Validation: Measure helpfulness and accuracy logs.

我们采用严谨的方法测试AI优化效果：

观察：「用户对X功能感到困惑。」
假设：「如果我们为X功能添加推理Agent，那么完成率将提升20%。」
实验：构建最小可用的agentic原型。
验证：统计有用性和准确率日志。

📖 Reference Library

📖 参考库

Detailed deep-dives into AI Product Excellence:

AI Product Strategy: Navigating the probabilistic era.
Rapid Prototyping: Building with agentic velocity.
Context Engineering: Curating truth for AI agents.
Hypothesis Criteria: Framework for rigorous testing.

Updated: January 22, 2026 - 20:30

AI产品最佳实践深度解析：

AI产品战略：概率时代的导航指南
快速原型设计：以agentic效率构建产品
上下文工程：为AI Agent梳理真实信息
假设校验标准：严谨测试的框架

更新时间：2026年1月22日 20:30