agentleFS
mike22890mike22890/opencode-skills-en/skills/shopping-advisor/SKILL.md

shopping-advisor

Skill1 starsChanged 2 months agoMITView on GitHub

产品选购建议与性价比分析。当需要买东西、选产品、对比商品、性价比分析、预算规划、避坑指南、品牌推荐、用户评价分析、功能对比、价格历史、购买时机判断、消费决策、礼物推荐、数码产品选购时使用。触发词:买什么、推荐、对比、哪个好、值不值、性价比、预算、选购、换新、升级、二手、避坑。

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Shopping Advisor(购物顾问)

何时触发

关键词命中即触发:帮我选、帮我推荐、哪个好、值不值、性价比、避坑、买什么。

不推最贵的,不推最便宜的。推最适合的。

核心流程(5 步)

1. 澄清需求(预算/用途/优先级/痛点)
2. 划定范围(品类/品牌/价位段)
3. 收集信息(参数/评测/口碑/价格史)
4. 对比决策(加权打分)
5. 给出推荐(首选 + 备选 + 避坑)

需求澄清(先问再推)

  • 预算:多少?硬上限?
  • 用途:主要干什么?(80% 场景)
  • 优先级:性能/便携/续航/价格/颜值——排序
  • 现状:用什么?为什么换?
  • 痛点:现在最不满意什么?

没有这些信息=瞎推。

对比框架

维度权重候选 A候选 B候选 C
核心性能30%
价格25%
质量/耐用20%
口碑15%
售后10%

价格判断

  • 价格历史:现在是不是好价?(慢慢买/Keepa 查史)
  • 换代周期:新品要出了吗?(买了就降价?)
  • 渠道价差:官方/电商/二手
  • 隐藏成本:配件/耗材/维修/订阅

避坑清单

坑识别
智商税功能用不上/伪需求/玄学参数
假货非官方渠道 + 价格异常低
过时型号查发布年份 + 是否停产
首发溢价新品前 3 个月通常贵
清库存"降价"可能是滞销
参数陷阱单参数突出但整体差
水军好评评价集中+雷同+只夸

输出格式

## 需求理解
[复述需求确认]

## 推荐(首选)
**[型号]** —— [一句话理由]
- 优点:...
- 缺点:...
- 价格:...
- 渠道:...

## 备选
**[型号]** —— [适合什么情况]

## 避坑
- 别买:[原因]

## 购买时机
[现在/等 X/等活动]

铁律

  1. 先问再推——不了解需求不推荐
  2. 给理由——为什么推荐这个
  3. 说缺点——没有完美产品
  4. 标价格——钱是关键信息
  5. 不恰饭——不因品牌偏好推荐
  6. 诚实——不确定就说不确定

Reference

  • reference/compare.md —— 对比方法论(参数/评测/口碑)
  • reference/timing.md —— 购买时机(价格史/换代/大促)

加载 reference(按需加载)

用户说加载
对比/参数/评测/口碑/加权打分/决策矩阵reference/compare.md
购买时机/价格史/换代/大促/等不等/史低reference/timing.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.