The problem

Standard tournament coverage relies on shallow statistics like goal counts, ignoring the tactical context and opponent quality. Fans and analysts often overreact to single viral performances while missing sustainable breakout patterns in deeper roles.

What it does

• Calculates dynamic 100-point performance ratings based on match impact, role difficulty, and opponent strength.
• Generates "Movement Maps" predicting how much a player's rating will rise or fall after their next match.
• Adjusts scoring logic for specific positions to ensure defenders and midfielders are evaluated fairly against attackers.
• Identifies "Trend Clusters" to separate sustainable elite performance from temporary statistical noise.
• Weights knockout stage performances more heavily than group stage matches to reflect tournament pressure.

Why this beats prompting it yourself

General AI prompts often suffer from attacker bias and treat all matches as equal. This skill utilizes a specialized weighting architecture that enforces positional fairness and movement constraints, preventing the "one-game wonder" rating inflation typical of standard LLM responses.

Use cases

• Tracking breakout stars and rising market value during the 2026 World Cup.
• Generating analytical player boards for sports media or scouting reports.
• Evaluating mid-tournament form versus historical baseline performance.

Known limitations

The engine requires specific tournament stages or player sets to function and will halt if the context is too vague to provide an analytical rating.