football-match-report skill
A Python skill and package that turn a WhoScored match URL into a report with pass maps, shot maps, xG and player dashboards.
- 120 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- Scraping third-party sites may violate their terms of use.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/football-match-reportDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Scraping third-party sites may violate their terms of use.
This is third-party code. Review the repository files before installing.
What it does
The `football-match-report` package takes any WhoScored match URL. A headless Chromium scraper collects the event stream with coordinates: passes, tackles, carries. The FotMob match id is resolved from date and team names, supplying shots with xG and xGOT, momentum, official stats and team colors. An offline render then draws two 4x3 report pages: passing networks, shot map, defensive blocks, progressive passes, xT momentum, final-third entries, Zone 14 and more. Player dashboards follow, one 2x3 page per starter plus a merged `player_stats.csv`. The skill for Hermes agents describes the command order. No API keys or manual Selenium sessions are required.
Who it is for. Football analysts and data hobbyists who want a ready match report without assembling charts by hand.
Good fit when
- A post-match team report with a shot map and xG is needed.
- One player is analyzed: maps of his passes, shots and touches are needed.
- Match data is merged into `player_stats.csv` for further analysis.
- An agent receives a WhoScored link and runs the scrape and render chain itself.
Not a fit when
- Scraping sites is forbidden by their terms of use.
- Live data during a match is required.
- A licensed data source is needed for publication.
Example request
Take the match at this WhoScored link, collect data into `./data`, then render both team reports and the player dashboards.Limitations
Data comes from scraping WhoScored and FotMob, so layout changes on those sites break collection and each user must follow source terms. Scraping installs Chromium through Playwright, which downloads a browser. The skill is described for the Hermes agent and for Linux and macOS. Reports cover matches already played. Examples in the repository show the report format, not a guarantee of data completeness. The last commit dates from August 2026.
How to disable. Remove the skill folder from the agent directory and the project `uv` environment. Downloaded data sits in the `--out` and report folders and is deleted manually.
FAQ
Are API keys required?
No. Scraping goes through a headless browser, with no keys or manual sessions.
What reports are produced?
Two team report pages (`match_report_1`, `match_report_2`), a top-players dashboard and personal dashboards.
Where do xG and xGOT come from?
From FotMob: the match id is resolved from the date and team names.
Can a report be rebuilt offline?
Yes. The `render` and `players` commands work offline from data already downloaded.
Does it work on Windows?
The skill description lists Linux and macOS. The author does not claim Windows support.
Discussion
No questions or reviews yet.
Related
SkillsAn MCP server searching documentation of 31 football data providers: StatsBomb, Opta, Wyscout and more. Context7 for football.
Excel analysis skill that profiles a sheet, cleans it, reconciles totals against the sheet's own sums and then releases numbers.
MPSTATS skills
Claude Code Skills — MPSTATS
Official MPSTATS skills: Wildberries, Ozon and Yandex Market analytics plus product card visuals via the API
A skill set for math modeling contests: problem parsing, method selection, Python and MATLAB code, and paper writing
A data visualization skill for agents: turns data into polished interactive HTML charts and full reports with one visual language
Skill and CLI for tables: cleaning with recorded decisions, level-based statistics, a PDF report and a separate audit.
README in short
The repository is a clean Python package with a `football-match-report` command and an agent skill. The report layout follows the Post-Match-Report 2.0 blueprint.