About this skill

Problem

Sports event details are scattered across schedules, previews, social posts, injury notes, and player pages. Engineers and fans who want a quick picture of “what is playing today, which matches matter, and how the teams compare” often have to assemble JSON, verify sources, and format notes manually. This skill turns public sports information into renderable HTML reports, focusing on fragmented information, unverifiable sources, and demo data being mistaken for live data.

How It Works

Rendering engine: analytics.py accepts structured match JSON and outputs HTML reports to the desktop, supporting daily, focus, and report modes.
Data collection: live.py pulls current fixtures from public schedule APIs and explicitly degrades to sample data on failure; when no paid key is configured, an agent can use WebSearch to fill in the day’s real schedule.
Quality gates: audit.py checks avatars, expert freshness, and consistency; --fix can normalize and deduplicate, and the exit code can block a pipeline.
Presentation: team/player cards, tactical comparison, radar panels, and source tiers appear in the report, with live / verified / sample badges to distinguish data freshness.

Boundaries

The skill only organizes, compares, and visualizes public sports information. It does not predict match outcomes or provide selection advice. Free data sources have coverage limits, so readers should check the top banner and per-match badges to confirm whether a row is live, agent-verified, or sample data.

Screenshots

Use Cases

Build a daily sports overview that turns public schedules, players, injuries, and weather into an HTML report with data-freshness badges.
Create a focus board that filters top matches by league tier, star players, and notable clubs, with player spotlight cards for deeper review.
Deep-dive a selected fixture using matchups, form, H2H, injuries, and weather to produce sourced, non-predictive insight panels.
Run audit.py before delivery to check avatars, expert freshness, and consistency, then re-collect data if checks fail.

Best For

Sports frontend engineers who want to turn public schedules, player status, and source notes into shareable HTML without hand-building templates.
Automation agent developers who want to chain live.py, analytics.py, and audit.py into a collection, rendering, and QA pipeline with explicit fallbacks.
Sports editors who need to tier multi-source event information as official, authoritative media, or unverified rumors while preserving source credibility.
Data-oriented fans who want daily match highlights, player spotlights, and context without result predictions or selection advice.