About this skill

Problem

When comparing two national teams, a simple head-to-head list is often not enough. This skill is useful for data-driven match discussion: given two teams and a tournament stage, it generates a structured prediction that combines World Cup history, recent continental performance, squad market value, international caps, and elite-player depth.

How It Works

Data foundation: local files include data/matches.csv with 1,248 World Cup matches, data/team_stats_v2.json with 87 team profiles, data/head_to_head.json with 736 matchup records, plus data/continental/*.txt and data/transfermarkt/*.csv.gz for tournament and player-value data.
Model logic: it uses a weighted composite score around Power V2 Score, Continental Form, Squad Value, Experience, and Elite Players, with data/predict.py for predictions and data/analyze_v2.py for deeper breakdowns.
Output shape: results typically include each team’s Power V2, World Cup win rate, squad value, and elite-player count, continental titles or win rates, win/draw/loss probabilities, expected score, and the main factors driving the prediction.

Limits

This is a statistical discussion aid, not betting advice. Squad values are a Transfermarkt snapshot, club-tier scores are approximate, and knockout or group-stage matches remain highly uncertain. Any output should keep the disclaimer that predictions are for entertainment only.

Screenshots

Use Cases

Compare Power V2, squad value, and continental win rates for a World Cup group-stage matchup.
Rank strong teams such as England, France, and Brazil by Power V2 and identify key advantages.
Explain why squad value and Euro performance drive Spain's prediction against a lower-value team.
Use head-to-head and Transfermarkt data to explain the key factors behind a specific match prediction.

Best For

Sports editors writing match-day features who need team comparisons, probabilities, and key factors.
Data analysts building sports content who need to recompute Power V2 from local datasets.
Podcast hosts preparing World Cup special episodes who need squad value, titles, and prediction drivers.
Engineers building football dashboards who need to call `predict.py` and read `team_stats_v2.json`.

Related Skills

Text Classifier Pro

@user_26bdbd50/text-classifier-pro

Batch-classify pasted text or CSV rows with preset and custom templates, outputting structured labels and confidence scores for data organization and annotation workflows.

Data Analysis 2026.08.30 ↓ 598

Bazhuayu Global Public Opinion and Brand Reputation Analysis

@user_2d9d1ec9/bazhuayu001

Analyzes product VOC and brand reputation events across public news, community, and social pages, delivering Markdown, Excel, and optional HTML reports.

Data Analysis 2026.08.30 ↓ 600