菜单
Generate professional football analysis reports in PDF, Word, and Excel formats. Use when creating match analysis reports, data visualizations, or exporting prediction results. Includes professional charts and statistical analysis.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Comprehensive API testing including unit tests, integration tests, performance testing, and automated test pipelines. Use when testing REST endpoints, validating API responses, load testing, or setting up test automation.
Manage code quality for Football Prediction project using Make commands. Use when running quality checks, formatting code, running tests, or preparing for commits. Supports black, flake8, mypy, bandit, pytest, and coverage tools.
Collect football data from external APIs including FotMob L2 data, odds information, and real-time match statistics. Use when gathering match data, collecting historical statistics, or updating prediction datasets.
Design and optimize data pipelines for football prediction system. Use when building ETL processes, data transformations, or optimizing data flow between PostgreSQL, Redis, and external APIs.
Manage PostgreSQL database operations including migrations, query optimization, connection pooling, and data backup/restore. Use when handling database tasks, optimizing queries, or managing database connections.
Manage application deployment including Docker containers, production environments, and service orchestration. Use when deploying to production, managing Docker services, or handling deployment rollbacks.
| name | report-generation |
| description | Generate professional football analysis reports in PDF, Word, and Excel formats. Use when creating match analysis reports, data visualizations, or exporting prediction results. Includes professional charts and statistical analysis. |
专业的足球分析报告生成系统，支持多种格式的报告输出，包括PDF、Word、Excel等，为不同用户提供定制化的分析报告。
用途: 媒体、投资机构、球队战术分析 格式: PDF (8-10页) 包含内容:
用途: 数据分析师、量化交易、研究团队 格式: XLSX (多工作表) 包含工作表:
用途: 实时监控、决策支持、展示演示 格式: JSON + HTML 数据结构:
# PDF生成
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter, A4
# Word文档
from docx import Document
from docx.shared import Inches
# Excel处理
import openpyxl
from openpyxl.styles import Font, PatternFill
from openpyxl.chart import BarChart, Reference
# 图表可视化
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.graph_objects as go
def generate_pre_match_report(home_team: str, away_team: str) -> str:
# 1. 获取预测数据
prediction = get_match_prediction(home_team, away_team)
# 2. 收集分析数据
analysis_data = collect_analysis_data(home_team, away_team)
# 3. 生成可视化图表
charts = generate_charts(analysis_data)
# 4. 渲染PDF报告
report_path = render_pdf_report(prediction, analysis_data, charts)
return report_path
templates/
├── pre_match_report.html # Jinja2模板
├── styles.css # 样式定义
├── header_footer.html # 页眉页脚
└── charts/ # 图表模板
├── radar_chart.html
├── probability_chart.html
└── trend_analysis.html
EXCEL_TEMPLATE = {
'pre_match_analysis': {
'worksheets': [
{'name': '预测结果', 'columns': ['日期', '主队', '客队', '预测', '概率']},
{'name': '历史数据', 'columns': ['交锋记录', '胜负统计']},
{'name': '图表数据', 'chart_type': 'bar_chart'}
]
}
}
def create_strength_radar(home_stats, away_stats):
"""五维实力对比雷达图"""
categories = ['进攻', '防守', '中场', '体能', '战术']
fig = go.Figure()
fig.add_trace(go.Scatterpolar(
r=home_stats,
theta=categories,
fill='toself',
name=home_team
))
fig.add_trace(go.Scatterpolar(
r=away_stats,
theta=categories,
fill='toself',
name=away_team
))
return fig
def create_probability_chart(probabilities):
"""胜负概率分布柱状图"""
labels = ['主胜', '平局', '客胜']
values = [probabilities['home'], probabilities['draw'], probabilities['away']]
colors = ['#2E8B57', '#FFD700', '#DC143C']
fig = go.Figure(data=[
go.Bar(x=labels, y=values, marker_color=colors)
])
fig.update_layout(
title='比赛结果概率分布',
yaxis_title='概率 (%)'
)
return fig
def create_trend_chart(team_name, matches_history):
"""球队近期表现趋势"""
dates = [match['date'] for match in matches_history]
results = [match['result'] for match in matches_history]
fig = go.Figure()
fig.add_trace(go.Scatter(
x=dates,
y=results,
mode='lines+markers',
name=team_name,
line=dict(color='blue', width=2)
))
return fig
# 使用CLI工具
python scripts/generate_report.py \
--home "Manchester United" \
--away "Arsenal" \
--type pre_match \
--format pdf \
--output reports/manu_vs_arsenal.pdf
python scripts/batch_reports.py \
--week "2024-W03" \
--league "Premier League" \
--format_all \
--output_dir weekly_reports/
import requests
# 请求报告生成
response = requests.post('/api/v2/reports', json={
'home_team': 'Manchester United',
'away_team': 'Arsenal',
'report_type': 'pre_match',
'format': 'pdf'
})
report_url = response.json()['report_url']
football-prediction: Football prediction systemfeature-engineering: Feature engineering for analysisdata-engineering: Data pipeline engineering