com um clique
xiaoshen-transactions-analysis
分析和总结小申的消费习惯和消费倾向,基于交易记录数据生成分类统计和占比分析。
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Menu
分析和总结小申的消费习惯和消费倾向,基于交易记录数据生成分类统计和占比分析。
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Multi search engine integration with 4 engines: Google, DuckDuckGo, Brave Search, and WolframAlpha. Supports advanced search operators, time filters, and knowledge queries. No API keys required.
Generate and edit images with gpt-image-2 through a unified Python raw-HTTP CLI. Use when Codex needs OpenAI-compatible image generation, image-to-image editing, /v1/images/generations, /v1/images/edits, optional /v1/responses image_generation tool support, fixed in-script API key/base URL defaults, retry handling, and reproducible request/response JSON artifacts.
Generate images through the custom OpenAI-compatible Responses endpoint at https://codex.ciii.club/v1/responses using top-level model gpt-5.4 and the image_generation tool with gpt-image-2. Use when Codex needs a deterministic Python CLI workflow, explicit request and response JSON artifacts, or the user explicitly asks to use this endpoint/API path instead of the built-in image tool.
Generate images through the custom OpenAI-compatible Responses endpoint at https://codex.ciii.club/v1/responses using top-level model gpt-5.4 and the image_generation tool with gpt-image-2. Prefer the bundled OpenAI SDK workflow for deterministic Python CLI generation with explicit request and response JSON artifacts; fall back to the raw HTTP script only when the SDK path is unavailable or the user explicitly asks for it instead of the built-in image tool.
UI/UX design intelligence. 67 styles, 96 palettes, 57 font pairings, 25 charts, 13 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
Guide for creating effective skills. Use when users want to create a new skill, update an existing skill, or ask "help me create a skill", "make a skill for...", "I want to build a skill". This skill guides users through an interactive SOP process with step-by-step questions.
| name | xiaoshen-transactions-analysis |
| description | 分析和总结小申的消费习惯和消费倾向,基于交易记录数据生成分类统计和占比分析。 |
| tags | ["finance","analysis","transactions","consumption"] |
| version | 1.0.0 |
| author | CodeBuddy |
| allowed-tools | null |
| disable | false |
此SKILL用于分析和总结小申的消费习惯和消费倾向,基于交易记录数据生成分类统计和占比分析。
该SKILL通过调用MCP服务获取指定周期内的消费数据,对消费进行分类统计,并输出基于百分比的汇总结果,可渲染为表格形式。
get_transactions_by_user MCP服务获取消费记录yyyy)或按月(yyyy-mm)查询get_transactions_by_user
获取指定用户的消费记录数据
| 参数名 | 类型 | 说明 | 示例值 |
|---|---|---|---|
user_id | string | 用户ID | "user123" |
period | string | 查询周期,支持年或年月格式 | "2025" 或 "2025-01" |
MCP服务返回交易记录数组,每条记录包含以下字段:
[
{
"account_id": 2,
"amount": "14.00",
"date": "2025-12-31",
"desc": "专二",
"from_account_id": null,
"id": 11203,
"item": "咖啡",
"opposite_trans_id": null,
"to_account_id": null,
"type": -1
},
{
"account_id": 1,
"amount": "34.93",
"date": "2025-12-31",
"desc": "都城",
"from_account_id": null,
"id": 11204,
"item": "餐饮",
"opposite_trans_id": null,
"to_account_id": null,
"type": -1
}
]
item: 消费项目类别,用于分类统计amount: 交易金额(字符串格式)date: 交易日期desc: 交易描述type: 交易类型(负数表示支出)account_id: 账户ID检查是否已获取必要的MCP参数:
user_id: 用户标识period: 查询周期当用户未提供足够的MCP参数时,按以下优先级询问:
优先级1: user_id
优先级2: period
询问示例:
item 字段分组输出包含以下内容的汇总报告:
=== 消费汇总分析(2025-01)===
消费类别 | 金额(元) | 占比
--------------|----------|--------
餐饮 | 34.93 | 71.4%
咖啡 | 14.00 | 28.6%
总支出: 48.93 元
记录数: 2 条
amount 字段为字符串格式,需转换为数值进行计算yyyy 和 yyyy-mm 两种周期格式可在实现中添加: