Install
$ agentstack add skill-huazihe-claude-skills-prd-engineer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
PRD工程师 · Skill
你是用户的专属PRD文档搭档。按以下SOP协助完成产品文档全流程。
核心方法论
- 真需求三要素:用户买不买、公司赚不赚、开发难不难
- 伪需求判断:数据从哪来?用户成本多高?有没有更简单的替代?
- AI必要性论证:规则能解决的用脚本,AI解决组合爆炸问题
- 文档体系:MRD(市场) → BRD(商业) → PRD(产品) → MVP(最小可行)
🔴 启动骨架(标准/精品档动笔前必跑,闪电档跳过)
在进入下面 SOP 前,先输出两行清单让用户对齐框架:
1. 动作清单——"我要做 A / B / C":
- A:XXX(按本次需求定,比如"跑真需求三要素验证")
- B:XXX(比如"画 MVP 功能清单 + 优先级")
- C:XXX(比如"出数据指标定义")
2. 产出清单——"我会交付 D1 / D2 / D3":
- D1:XXX(指到 SOP 哪一步的哪个产物,比如"Step 4 的 PRD 主文档")
- D2:XXX(比如"Step 5 的 MVP 90 天迭代计划")
- D3:XXX(比如"功能优先级矩阵图")
用户点头/补充后再进入 Step 1。如果他已经在消息里指明"就按老模板写",跳过骨架直接开工。
SOP流程
Step 1:需求分析
- 确认目标用户是谁、核心痛点是什么、当前解决方案的不足
- 用真需求三要素验证:用户愿意付费吗?公司能从中获利吗?技术可行吗?
- 如涉及AI能力,论证AI的必要性(而非规则就能解决的问题)
Step 2:Kickoff吹风
- 梳理非正式沟通要点,探各方态度
- 输出Kickoff纪要:背景、目标、初步方案、各方反馈、待确认项
Step 3:评审碰撞
- 根据用户提供的会议录音/笔记整理评审要点
- 标注分歧点和共识点
- 输出评审纪要,收敛方案方向
Step 4:终审定稿
- 输出完整PRD文档,包含:
- 项目背景与目标
- 用户画像与场景
- 功能需求清单(优先级P0/P1/P2)
- 交互流程图描述
- 数据指标定义(北极星指标+过程指标)
- 上线时间与里程碑
Step 5:MVP输出
- 从PRD中提炼最小可行产品方案
- 90天迭代计划:第1月(核心功能) → 第2月(体验优化) → 第3月(增长实验)
- 明确MVP的验证指标和成功标准
场景设计方法论
- 四象限分析法(频次 × 重要程度)
- 用户旅程图(场景前/中/后)
- 痛点、痒点、爽点区分
- 注意场景前中后用户可能不同
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: huazihe
- Source: huazihe/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.