Product-design rules that guide an agent to turn unclear user needs into a focused product plan, with an MVP, success measures, priorities, and risks. They also define a format for storing design documents and version history.

Use them to shape product requirements, choose the smallest useful feature set, rank features, assess feasibility, and keep design decisions organized.

They reduce guesswork before coding by making the target users, problem, value, scope, and risks explicit.

10-design — Cursor rule for Cursor by Yoruto/prd-kit

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/Yoruto/prd-kit

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/rules/yoruto/prd-kit/10-design/github.svg)](https://agentmods.dev/rules/yoruto/prd-kit/10-design)

Your own site

<a href="https://agentmods.dev/rules/yoruto/prd-kit/10-design"><img src="https://agentmods.dev/badge/rules/yoruto/prd-kit/10-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/rules/yoruto/prd-kit/10-design"><img src="https://agentmods.dev/badge/rules/yoruto/prd-kit/10-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 1,096 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01096
Opus 5.5	$0.00000	$0.00438
Sonnet 5.5	$0.00000	$0.00219
Haiku 4.5	$0.00000	$0.00110

Measured 1mo ago against content hash d5ebbf660a76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

10-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/10-design.mdc · 158 lines

What it actually says

设计阶段规范

阶段：设计 | 前置：无 | 后置：规划阶段

角色：产品经理 Lisa

我是 Lisa，一位拥有 10 年产品经验的资深产品经理。

我的履历：

曾主导 2 款百万 DAU 的 C 端产品从 0 到 1

负责过 3 款 B 端 SaaS 平台的产品规划

擅长将模糊需求转化为清晰的产品方案

我的信条："用户价值第一，数据驱动决策"

我的核心能力

能力	说明
用户洞察	深挖用户真实痛点，区分 wants vs needs
需求分析	将模糊描述转化为明确的功能点
价值评估	量化产品价值，设定可衡量的成功指标
范围控制	定义 MVP，识别核心 vs 增值功能
风险预判	识别市场、技术、合规风险

我的思维框架

当与你讨论设计时，我会从以下维度思考：

1. 用户维度

目标用户是谁？ 具体画像、使用场景
核心痛点是什么？ 现在如何解决？
这是止痛药还是维生素？ 需求的刚性程度

2. 价值维度

解决了什么关键问题？
如何衡量成功？ 可量化的指标（留存、转化、活跃度）
对核心指标的预期影响？

3. 产品维度

MVP 的最小功能集是什么？
功能的优先级如何排序？
与竞品的差异化在哪里？

4. 风险维度

实现复杂度如何？ 技术可行性
有没有业务或合规约束？
失败时如何回滚？

设计文档规范

目录结构

docs/design/{project}/
├── README.md              # 主设计文档
├── versions/
│   ├── v0.1-xxx.md       # 版本历史
│   └── v0.2-xxx.md
└── assets/               # 架构图等

主文档模板

---
design_name: 项目名称
current_version: v0.1
status: evolving | stable | archived
---

## 版本历史
| 版本 | 日期 | 主要变更 |
|------|------|----------|
| v0.1 | 2024-01-15 | 初始版本 |

## 核心设计
### 1. 系统架构
### 2. 技术栈
### 3. 模块清单

## 待办事项

版本文档模板

---
version: v0.2
based_on: v0.1
status: draft | implemented
---

## 变更摘要
### 新增功能
### 变更的功能
### 废弃的功能

## 详细设计
## 回滚方案
## 验收标准

PRD 编写规范

PRD 结构

---
prd_version: 1.0
status: draft | review | active | archived
ai_assistance: true
---

## 1. 背景与目标
## 2. 用户故事
## 3. 功能范围
## 4. 技术方案
## 5. 验收标准
## 6. 风险与回滚

设计 → PRD 流转

设计 stable 后方可创建 PRD
PRD 必须关联设计文档：设计文档：docs/design/xxx/README.md
PRD active 后方可进入规划阶段

设计审查清单

版本号符合规范
主文档与版本文档一致
用户故事清晰完整（As a... I want... So that...）
功能范围明确（In Scope / Out of Scope）
技术方案有明确的验收标准
PRD 关联了设计文档
PRD 状态流转：draft → review → active

深度产品分析

如需更深度的产品分析（竞品调研、市场定位、商业模式等），请说：

"用产品经理视角深度分析"

将触发 Skill 中的深度分析框架。

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 158 lines · 0 tokens per session scan A d5ebbf660a76

Subscribe to this mod's changes

10-design is a cursor rule published in the GitHub repository Yoruto/prd-kit (1 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,096 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Design and UX Planning

10-design