nutmeg-compute SKILL.md skillA

nutmeg-compute from withqwerty/nutmeg is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add withqwerty/nutmeg/nutmeg-compute@git:20261008.9a530e2

Pins git:20261008.9a530e2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
withqwerty/nutmeg
Path
skills/compute/SKILL.md
Versions recorded
7
Latest version
git:20261008.9a530e2, committed Oct 8, 2026
First version recorded
Mar 25, 2026
Size
7,686 bytes
Repository stars
55
License
none declared

Calculate derived football metrics and models. Use when the user wants to compute xG, xGOT, PPDA, passing networks, expected threat, possession value, pressing intensity, or any derived football statistic from raw data.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Compute

Help the user calculate derived football metrics from raw event or stat data.

## Accuracy

Read and follow `${CLAUDE_PLUGIN_ROOT}/docs/accuracy-guardrail.md` before answering any question about provider-specific facts (IDs, endpoints, schemas, coordinates, rate limits). Always use `search_docs` — never guess from training data.
## First: check profile

Read `.nutmeg.user.md`. If it doesn't exist, continue with sensible defaults (Python and pandas, intermediate level) and suggest running `/nutmeg` setup at the end.

## Metric reference

Before computing a metric that has a football-docs metric card (`list_metrics` shows them: xG, npxG, xA, xG
assisted, PPDA, progressive passes and carries, xT, VAEP, field tilt, pass completion), read it with
`get_metric("<card>")`:
- Pick one variant and name its ID (for example `ppda.statsbomb-hudl`) in the code, the output and any chart. Values
  from different variants are not comparable.
- If the variant has reference code with test values on StatsBomb open data, check your implementation against them.
- In a research project, the plan choice rests on the card: `--rests-type metric --rests-ref <variant-id>`.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add withqwerty/nutmeg/nutmeg-compute@sha256:e584be396fbdcf29

The line at the top of this page pins the label git:20261008.9a530e2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ps4zsjiboba2uexg.svg)](https://markdownregistry.com/a/art_ps4zsjiboba2uexg)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 7 versions of this file, between Mar 25, 2026 and Oct 8, 2026, about one every 33 days.

versioncommittedcommitsizeaudit
git:20261008.9a530e2 latest2026-10-08 9a530e2 7,686 BA view · diff
git:20261004.5b6c70e2026-10-04 5b6c70e 6,805 BA view · diff
git:20260930.e84c2bd2026-09-30 e84c2bd 6,562 BA view · diff
git:20260329.b4a4e772026-03-29 b4a4e77 5,508 BA view · diff
git:20260327.afcf7442026-03-27 afcf744 5,513 BA view · diff
git:20260325.07b51412026-03-25 07b5141 5,281 BA view · diff
git:20260325.1f864412026-03-25 1f86441 5,274 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7686 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

withqwerty/nutmeg · 55 stars · license none declared · pushed 2026-10-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ps4zsjiboba2uexg
GET https://markdownregistry.com/api/v1/resolve?ref=withqwerty/nutmeg/nutmeg-compute
GET https://markdownregistry.com/api/v1/blob/e584be396fbdcf29aefff30d39aee0739a6ffe8ef027956375efb8ebdccef6a1

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from withqwerty/nutmeg

CLAUDE.md CLAUDE.md file
withqwerty/nutmeg · CLAUDE.md
git:20261011.b131b98 · audit A · 55 stars
nutmeg-acquire SKILL.md skill
withqwerty/nutmeg · skills/acquire/SKILL.md · Get football data: fetch, scrape or download from StatsBomb, Opta, FBref, Understat, SportMonks, Wyscout, Kaggle or any…
git:20261013.4ef97fb · audit A · 55 stars
nutmeg-analyse SKILL.md skill
withqwerty/nutmeg · skills/analyse/SKILL.md · Explore and interpret football data, and judge players or teams from stats: rankings, 'who is the best', 'is he a poor…
git:20261010.3c7d5af · audit A · 55 stars
nutmeg-brainstorm SKILL.md skill
withqwerty/nutmeg · skills/brainstorm/SKILL.md · Ideas for football data visualisations: chart types and designs for match reports, player profiles, dashboards and…
git:20261010.da11349 · audit A · 55 stars
nutmeg-heal SKILL.md skill
withqwerty/nutmeg · skills/heal/SKILL.md · Fix broken football data scrapers and pipelines: failed requests, API errors, changed formats. Also drafts upstream…
git:20261010.da11349 · audit A · 55 stars
nutmeg-learn SKILL.md skill
withqwerty/nutmeg · skills/learn/SKILL.md · Explain football analytics concepts and provider documentation: what a metric means (xG, PPDA, xT), learning paths and…
git:20261010.da11349 · audit A · 55 stars
nutmeg SKILL.md skill
withqwerty/nutmeg · skills/nutmeg/SKILL.md · Football data analytics entry point. Use for any task with football data: xG, match or player stats, scouting, shot…
git:20261013.f45c247 · audit A · 55 stars
nutmeg-research SKILL.md skill
withqwerty/nutmeg · skills/research/SKILL.md · Run football analysis as a research project that shows its work: a question, a plan with reasons, a claim ledger tying…
git:20261010.da11349 · audit A · 55 stars
nutmeg-review SKILL.md skill
withqwerty/nutmeg · skills/review/SKILL.md · Review football data code and visualisations for correctness. Use after building a chart, data pipeline, or analysis…
git:20261008.9a530e2 · audit A · 55 stars
nutmeg-store SKILL.md skill
withqwerty/nutmeg · skills/store/SKILL.md · Store and publish football data: databases, file formats, cloud storage, project layout, and sharing outputs…
git:20261010.da11349 · audit A · 55 stars
nutmeg-wrangle SKILL.md skill
withqwerty/nutmeg · skills/wrangle/SKILL.md · Clean, filter, reshape, join and convert football data, including missing values and large datasets. Use for any data…
git:20261013.8f51874 · audit A · 55 stars

Every file in withqwerty/nutmeg

Browse by kind, by grade A, or by owner.