Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
machina-sports avatar

World Cup

  • 540 installs
  • 201 repo stars
  • Updated August 5, 2026
  • machina-sports/sports-skills

world-cup is a prompt-only agent skill that routes coding agents to hosted FIFA World Cup 2026 match intelligence combining official fixtures, squads, and Kalshi plus Polymarket prediction market data for developers buil

About

world-cup is a premium prompt-only skill in machina-sports/sports-skills that routes coding agents to the hosted World Cup Intelligence project for FIFA World Cup 2026. It fuses official match truth—fixtures, standings, squads, injuries, and player performance—with live prediction market data from Kalshi and Polymarket including prices, order books, movers, and cross-venue edges. Every entity carries a canonical Machina URN cross-walked across api-football, Sportradar, Opta, Entain, and ESPN so a market resolves to a fixture and two teams. Developers reach for world-cup when building sports apps, newsletters, or editorial workflows that need prematch briefs, move explanations, and fan pulse context without wiring five data vendors manually. The skill is read-only and premium, designed for agent prompts that need grounded match and market context in one call pattern.

  • Tournament structure, groups, knockout flow, and schedule framing
  • Team, player, and historical matchup context for articles
  • Live-event content angles for social and product surfaces
  • Sports data interpretation for standings and scenarios
  • Reusable prompts for match previews and recaps

World Cup by the numbers

  • 540 all-time installs (skills.sh)
  • +7 installs in the week ending Aug 2, 2026 (Skillselion tracking)
  • Ranked #433 of 2,064 Data Science & ML skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/machina-sports/sports-skills --skill world-cup

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs540
repo stars201
Last updatedAugust 5, 2026
Repositorymachina-sports/sports-skills

How do you integrate World Cup match and market data?

Generate World Cup match context, team stats, schedules, and fan-facing sports content for apps, newsletters, or editorial workflows.

Who is it for?

Developers building FIFA World Cup 2026 apps, dashboards, or editorial tools that need fused match and prediction-market intelligence.

Skip if: Developers who only need generic sports scores without prediction markets or Machina-hosted World Cup intelligence access.

When should I use this skill?

A developer asks for World Cup 2026 fixtures, team stats, prediction market edges, or fan-facing match context for a sports product.

What you get

Prematch briefs, fixture-linked market prices, squad injury context, and cross-vendor canonical entity URNs

  • prematch brief
  • market price context
  • fixture-linked team intelligence

By the numbers

  • Cross-walks match entities across 5 named providers: api-football, Sportradar, Opta, Entain, and ESPN
  • Integrates 2 prediction market venues: Kalshi and Polymarket

Files

SKILL.mdMarkdownGitHub ↗

World Cup 2026 Intelligence (Premium)

A hosted, read-only intelligence layer for the FIFA World Cup 2026. It joins three things that are normally separate — official match truth, live prediction-market state, and AI-grounded context — under one canonical id space, so an agent can go from a market to the fixture to the teams in a single hop and reason about why a price is moving.

This skill itself runs no code. Like the `machina` gateway it builds on, it shells out to machina-cli, selects the hosted World Cup Intelligence project, and the agent harness talks to that project's MCP server. Tenant routing, provider keys, rate limits, and caching all live server-side. You never call a raw HTTP API or hold a provider key.

Read-only intelligence — not advice. Every output is informational sports
market intelligence. Not betting, trading, financial, or investment advice.
This layer has no order-placement, trading, or portfolio endpoints. If the
user wants to act on a signal, that execution happens in their own agent, on
their own account and keys — never here.

Premium / billing

This is a paid, metered layer (Machina Credits — see your project's credit-cost classes). Free public data does not flow through here. Where your agent harness supports agent-native pay-per-call (x402), the MCP server advertises price per tool; otherwise calls draw from the project's credit balance. If a call returns a 402 / "payment required" / "insufficient credits" error, surface it to the user and stop — do not retry-loop.

Quick Start

# 1. Install the Machina CLI (one-time) — shared with the `machina` skill
pip install machina-cli
# or: curl -fsSL https://raw.githubusercontent.com/machina-sports/machina-cli/main/install.sh | bash

# 2. Authenticate
machina login                              # interactive (browser)
# machina login --api-key <project-api-key>  # non-interactive (CI/CD)

# 3. Select the World Cup Intelligence project (REQUIRED)
machina project list
machina project use <world-cup-project-id>

# 4. Connect the MCP server
#    `machina project use` (or `machina template install`) returns the MCP URL +
#    headers. Point your harness's MCP config at it (e.g. .claude/mcp.json for
#    Claude Code), then reload the harness so it re-reads the config.

CRITICAL: Before Any Premium Call

Verify, in order — fix the specific failing step, never loop on the same call:

  • machina-cli is installed — which machina / machina version.
  • Authenticated — machina auth whoami returns a user.
  • The World Cup Intelligence project is selected — machina project use <id>.
  • The harness is connected to that project's MCP server (tools are visible).

What you get

All tools are read-only. Group by job:

Identity & fixtures (official match truth)

ToolReturns
worldcup-resolveAny provider id or canonical URN → entity + all cross-provider ids
worldcup-get-scheduleFixtures, filter by date / team / status
worldcup-get-event-contextEnriched match context (event + grounded prematch research)
worldcup-get-standingsGroup tables
worldcup-get-squadsBoth teams' squads
worldcup-get-injuriesInjuries / suspensions
worldcup-get-player-performance-contextPlayer performance signals (official + provisional, kept separate)

Market intelligence (Kalshi + Polymarket, URN-linked)

ToolReturns
worldcup-search-marketsMarket search across venues, linked to fixtures/teams
worldcup-get-market-stateLive price + order-book depth + price history + trades
worldcup-market-moversBiggest price moves over a lookback window
worldcup-compare-market-sourcesCross-venue price comparison
worldcup-find-market-edgesInformational edge / arb candidates, with caveats (AI)
worldcup-explain-market-moveWhy a price moved, grounded + cited (AI)
worldcup-generate-market-briefGrounded market-intelligence brief for a fixture (AI)
worldcup-fan-sentiment-contextSocial / news pulse from live X + web (AI)

Conversational

  • world-cup-intelligence-agent — full read + market context.
  • world-cup-market-analyst-agent — market-focused analyst.

The intelligence loop

A typical agent flow — research only, no execution:

1. Find the market — worldcup-search-markets {"query":"Brazil","status":"open"}. 2. Anchor it to truth — each market carries event_urn + related_team_urns; worldcup-resolve (or worldcup-get-event-context) expands the fixture, squads, standings, injuries. 3. Read live stateworldcup-get-market-state for price, order-book depth, history, trades; worldcup-market-movers / worldcup-compare-market-sources for movement and cross-venue gaps. 4. Explain & briefworldcup-explain-market-move, worldcup-find-market-edges (informational only), worldcup-generate-market-brief, worldcup-fan-sentiment-context. 5. Hand off — return the signal + sources + freshness/liquidity/resolution caveats to the user. Stop there. Any trade is the user's own action elsewhere.

Identifiers

Every entity has a canonical machina URN, stable across providers:

  • event — urn:machina:sport:soccer:event:{home}-vs-{away}:{YYYYMMDD}:wor
  • team — urn:machina:sport:soccer:team:{slug}:{iso3}
  • player — urn:machina:sport:soccer:player:{slug}:{YYYYMMDD-dob}:{iso3}
  • competition — urn:machina:sport:soccer:competition:fifa-world-cup-2026:wor

iso3 is the lowercased ISO-3166 alpha-3 (UK home nations use FIFA codes eng/sco/wal). Every doc also carries a uniform provider_ids map (one id per provider).

Alternate key: reads accept the canonical event_urn or provider_event_id (the api-football fixture id, e.g. 1489417) — the latter is the simplest client handle. Markets are keyed {source}:{source_market_id} (e.g. kalshi:KXWCGAME-…, polymarket:2415458).

Freshness

  • Identity / fixtures — synced; teams/events stable, players refresh daily.
  • worldcup-search-markets — cached, refreshed every ~30 min; responses warn past 15 min.
  • worldcup-get-market-state — live from the source.
  • worldcup-market-movers — hourly snapshot series; needs ≥2 buckets to show movement.

Common Errors & Recovery

ErrorCauseRecovery
command not found: machinaCLI not installedpip install machina-cli
Not authenticated…No sessionmachina login
No project selected…Project not chosenmachina project listmachina project use <world-cup-id>
402 / payment required / insufficient creditsMetered call, no balanceTell the user; top up credits or enable x402. Do not retry-loop.
Tools not visible after project useHarness hasn't reloaded MCP configRestart / reload the harness so it re-reads the MCP config

Commands that DO NOT exist — never call these

  • ~~any place, order, trade, buy, sell, bet tool~~ — this layer is

read-only; no such tool exists. Execution is the user's own, elsewhere.

  • ~~raw requests / direct provider HTTP~~ — go through the MCP server; keys and

the correct searchLimit/nested filters live server-side.

  • ~~machina mcp start / machina mcp connect~~ — the MCP server runs on Machina

infra; the harness connects via its own MCP config.

Guardrails

  • Never present an output as betting/trading/financial advice.
  • Never use "guaranteed edge", "guaranteed profit", or "bet this" language —

edges/movers are informational candidates, not recommendations.

  • Always return source, freshness, and resolution/liquidity caveats with any

market output.

Related skills

FAQ

What data sources does world-cup combine?

world-cup combines official FIFA World Cup 2026 match data with Kalshi and Polymarket prediction markets. Entities are cross-walked across api-football, Sportradar, Opta, Entain, and ESPN using canonical Machina URNs.

Is world-cup a self-hosted API integration?

world-cup is a prompt-only premium skill that routes agents to Machina's hosted World Cup Intelligence project. Developers do not wire individual vendor APIs manually; the skill provides read-only fused match and market context.

Data Science & MLcontentdistributionlifecycle

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.