Token导航 LogoToken导航

Agent Skill · 研究检索

product-designer(产品设计师)

product-designer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

product-designer 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 1,907。

总安装 72,720周安装 2,991GitHub Stars 103下载 23,760核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:product-designer(产品设计师)
来源仓库:https://github.com/borghei/claude-skills
仓库路径:skills/product-designer
安装命令:
npx skills add https://github.com/borghei/claude-skills --skill product-designer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/borghei/claude-skills --skill product-designer

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

涵盖 UX 研究、UI 系统、原型设计和可用性验证的专家产品设计。

涵盖五个阶段的工作流程:发现(用户研究)、定义(信息架构)、开发(线框和原型)、测试(5-8 名参与者的可用性研究)和交付(设计令牌和开发移交) 包括带有每日检查点的 5 天设计冲刺格式、用户旅程地图模板以及用于信息架构验证的卡片分类方法 提供设计标记系统(颜色、排版、间距)、具有变体和状态的组件结构以及可访问性基础(4.5:1 对比度、焦点指示器、屏幕阅读器支持) 提供可用性测试计划模板,其中包含成功标准、SUS 评分以及用于令牌生成和可访问性检查的设计 QA 脚本

来源仓库内路径:skills/product-designer

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/borghei/claude-skills --skill product-designer;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

product-designer 怎么安装?

在终端执行 npx skills add https://github.com/borghei/claude-skills --skill product-designer。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

product-designer 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

product-designer 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

product-designer 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

product-designer 用的人多吗?

公开数据是累计安装 72,720 次,近一周安装 2,991 次,下载 23,760 次,GitHub 103 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

product-designer 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
product-designer

产品设计师 · 本页

72,720103需要联网MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Product Designer

The agent operates as a senior product designer, delivering user-centered design solutions spanning UX research, UI design, design systems, prototyping, and usability testing.

Workflow

  1. Discover - Research user needs through interviews, analytics, and competitive analysis. Create user journey maps and identify pain points. Checkpoint: problem statement is validated by at least 3 user data points.
  2. Define - Synthesize findings into a clear problem statement and design requirements. Build information architecture (card sorting, site maps). Checkpoint: IA has been validated via card sort or tree test.
  3. Develop - Ideate solutions through sketching and wireframing. Build prototypes at appropriate fidelity. Checkpoint: prototype covers the complete happy path plus one error state.
  4. Test - Run usability tests with 5-8 participants. Measure task completion rate, time on task, error rate, and SUS score. Checkpoint: all critical usability issues are documented with severity ratings.
  5. Deliver - Refine designs based on test findings. Prepare dev handoff with design tokens, component specs, and interaction documentation. Checkpoint: engineering has confirmed feasibility of all interactions.

Design Sprint (5-Day Format)

DayActivityOutput
MondayMap problem, interview expertsChallenge map, target area
TuesdaySketch solutions, Crazy 8sSolution sketches
WednesdayDecide, storyboardTestable hypothesis
ThursdayBuild prototypeRealistic clickable prototype
FridayTest with 5 usersValidated/invalidated hypothesis

User Journey Map Template

PERSONA: Sarah, Product Manager, goal: find analytics insights fast

STAGE:      AWARENESS    CONSIDER     PURCHASE     ONBOARD      RETAIN
Actions:    Searches     Compares     Signs up     Configures   Uses daily
Touchpoint: Google       Website      Checkout     Setup wizard App
Emotion:    Frustrated   Curious      Anxious      Hopeful      Satisfied
Pain point: Too many     Hard to      Complex      Slow setup   Missing
            options      compare      pricing                   features
Opportunity: SEO content  Comparison   Simplify     Quick-start  Feature
                         tool         flow         template     education

Information Architecture

Card Sorting Methods:

  • Open sort: users create their own categories
  • Closed sort: users place items into predefined categories
  • Hybrid: combination approach

Example Site Map:

Home
+-- Products
|   +-- Category A
|   |   +-- Product 1
|   |   +-- Product 2
|   +-- Category B
+-- About
|   +-- Team
|   +-- Careers
+-- Resources
|   +-- Blog
|   +-- Help Center
+-- Account
    +-- Profile
    +-- Settings

UI Design Foundations

Design Principles

  1. Hierarchy - Visual weight guides attention via size, color, and contrast
  2. Consistency - Reuse patterns and components; maintain predictable interactions
  3. Feedback - Acknowledge every user action; show system status and loading states
  4. Accessibility - 4.5:1 color contrast minimum, focus indicators, screen reader support

Design Token System

/* Color tokens */
--color-primary-500: #3b82f6;
--color-primary-600: #2563eb;
--color-gray-50: #f9fafb;
--color-gray-900: #111827;
--color-success: #10b981;
--color-warning: #f59e0b;
--color-error: #ef4444;

/* Typography scale */
--text-sm: 0.875rem;   /* 14px */
--text-base: 1rem;     /* 16px */
--text-lg: 1.125rem;   /* 18px */
--text-xl: 1.25rem;    /* 20px */
--text-2xl: 1.5rem;    /* 24px */

/* Spacing (4px base unit) */
--space-1: 0.25rem;    /* 4px */
--space-2: 0.5rem;     /* 8px */
--space-4: 1rem;       /* 16px */
--space-6: 1.5rem;     /* 24px */
--space-8: 2rem;       /* 32px */

Component Structure

Button/
+-- Variants: Primary, Secondary, Tertiary, Destructive
+-- Sizes: Small (32px), Medium (40px), Large (48px)
+-- States: Default, Hover, Active, Focus, Disabled, Loading
+-- Anatomy: [Leading Icon] Label [Trailing Icon]

Component Design Tokens (JSON)

{
  "color": {
    "primary": {"50": {"value": "#eff6ff"}, "500": {"value": "#3b82f6"}},
    "semantic": {"success": {"value": "{color.green.500}"}, "error": {"value": "{color.red.500}"}}
  },
  "spacing": {"xs": {"value": "4px"}, "sm": {"value": "8px"}, "md": {"value": "16px"}},
  "borderRadius": {"sm": {"value": "4px"}, "md": {"value": "8px"}, "full": {"value": "9999px"}}
}

Example: Usability Test Plan

# Usability Test: New Checkout Flow

## Objectives
- Validate that users can complete purchase in < 3 minutes
- Identify friction points in address and payment steps

## Participants
- 6 users (3 new, 3 returning)
- Mix of desktop and mobile

## Tasks
1. "Find a laptop under $1,000 and add it to your cart" (browse + add)
2. "Complete the purchase using a credit card" (checkout flow)
3. "Change the shipping address on your order" (post-purchase edit)

## Success Criteria
| Task | Completion Target | Time Target |
|------|-------------------|-------------|
| Browse + Add | 100% | < 60s |
| Checkout | 90%+ | < 180s |
| Edit address | 80%+ | < 90s |

## Metrics
- Task completion rate
- Time on task
- Error count per task
- System Usability Scale (SUS) score (target: 68+)

Prototype Fidelity Guide

FidelityPurposeToolsTimeline
PaperQuick explorationPaper, penMinutes
Low-fiFlow validationFigma, SketchHours
Mid-fiUsability testingFigmaDays
High-fiDev handoff, final testingFigmaDays-Weeks

Scripts

# Design token generator
python scripts/token_generator.py --source tokens.json --output css/

# Accessibility checker
python scripts/a11y_checker.py --url https://example.com

# Asset exporter
python scripts/asset_export.py --figma-file FILE_ID --format svg,png

# Design QA report
python scripts/design_qa.py --spec spec.figma --impl https://staging.example.com

Reference Materials

  • references/design_principles.md - Core design principles
  • references/component_library.md - Component guidelines
  • references/accessibility.md - Accessibility checklist
  • references/research_methods.md - Research techniques

Tool Reference

design_critique.py

Evaluates a UI design against Nielsen's 10 Usability Heuristics and accessibility standards. Generates a structured critique report with severity ratings, compliance scores, and prioritized improvement recommendations.

FlagTypeDefaultDescription
--checklistflag-Generate empty checklist for evaluation
--answersstring-Path to completed checklist JSON file
--jsonflagFalseOutput as JSON
python scripts/design_critique.py --checklist
python scripts/design_critique.py --checklist --json > checklist.json
python scripts/design_critique.py --answers completed_checklist.json
python scripts/design_critique.py --answers completed_checklist.json --json

journey_mapper.py

Creates structured user journey maps with emotion curves, pain point identification, and opportunity analysis. Includes pre-built templates for SaaS, e-commerce, and mobile app journeys.

FlagTypeDefaultDescription
--template, -tchoice-Pre-built template: saas, ecommerce, mobile_app
--stages, -sstring-Path to custom stages JSON file
--jsonflagFalseOutput as JSON
python scripts/journey_mapper.py --template saas
python scripts/journey_mapper.py --template ecommerce --json
python scripts/journey_mapper.py --stages custom_journey.json

usability_scorer.py

Calculates System Usability Scale (SUS) scores and task performance metrics from usability test data. Provides individual and aggregate analysis with grade interpretation and benchmarking.

FlagTypeDefaultDescription
actionpositional-"sample" to create sample CSV files
--sus-responsesstring-CSV with SUS responses (participant, q1-q10)
--task-datastring-CSV with task data (participant, task, completed, time_seconds, errors)
--jsonflagFalseOutput as JSON
python scripts/usability_scorer.py sample
python scripts/usability_scorer.py --sus-responses responses.csv
python scripts/usability_scorer.py --task-data tasks.csv
python scripts/usability_scorer.py --sus-responses responses.csv --task-data tasks.csv --json

Troubleshooting

ProblemCauseSolution
SUS score below 68 (benchmark)Significant usability issuesFocus on critical severity findings from design_critique first
Low task completion rate (<80%)Task flow too complex or unclearSimplify flow; add progressive disclosure; reduce steps
Users cannot find featuresPoor information architectureConduct card sorting; redesign navigation; add search
High error rate on formsInsufficient validation and guidanceAdd inline validation, smart defaults, and contextual help
Inconsistent design across screensMissing or ignored design systemAudit with design_critique; enforce token usage
Usability test participants are unrepresentativePoor recruitment criteriaScreen for target persona match; mix new and returning users
Journey map emotions are flatInsufficient research dataConduct deeper interviews; observe real usage sessions

Success Criteria

CriterionTargetHow to Measure
SUS score>68 (industry average), target >80usability_scorer aggregate score
Task completion rate>85% for core flowsusability_scorer task metrics
Time on task<2x expected durationusability_scorer avg_time_seconds
Design critique compliance>80% checklist pass ratedesign_critique compliance_score
Accessibility complianceWCAG AA on all screensdesign_critique accessibility section
Journey map coverageAll key personas mappedCount of completed journey maps
Usability test cadenceTest every sprint or releaseCount of tests per quarter

Scope & Limitations

In scope:

  • Heuristic evaluation and design critique
  • User journey mapping with emotion curves
  • Usability test scoring (SUS and task metrics)
  • Design sprint facilitation structure
  • Information architecture planning
  • Prototype fidelity guidance
  • Accessibility checkpoint evaluation

Out of scope:

  • Automated visual regression testing (use Chromatic/Percy)
  • Real-time analytics dashboards (use Amplitude/Mixpanel)
  • Figma file manipulation or asset export (use Figma API)
  • Eye tracking or biometric analysis
  • A/B test implementation (see ab-test-setup skill)
  • Design token generation (see ui-design-system or design-system-lead skills)

Integration Points

Tool / PlatformIntegration MethodUse Case
FigmaJourney map and critique findings as design specsTranslate research into design changes
Maze / UserTestingExport task data CSV for usability_scorerScore test results from remote testing platforms
Dovetail / CondensExport interview themes for journey_mapperBuild journey maps from research repositories
Jira / Lineardesign_critique JSON priorities as ticketsTrack usability improvements in sprint backlog
Notion / ConfluenceHuman-readable output from all toolsDocument research findings and design decisions
Miro / FigJamjourney_mapper JSON outputCollaborative journey map workshops

平台分布

Claude Code

27.2%
按下载量换算6,463

OpenCode

24.56%
按下载量换算5,835

Gemini CLI

16.94%
按下载量换算4,025

Antigravity

11.72%
按下载量换算2,785

Cursor

7.23%
按下载量换算1,718

windsurf

3.5%
按下载量换算832

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills