Miroshark Matchday

${var} — Empty → the default three leagues (Premier League, Serie A, La Liga) for the upcoming matchday. A comma-separated subset (pl,seriea) runs fewer sims. Any other text is treated as ONE custom simulation scenario run as-is.

Every Friday, run one paid MiroShark simulation per major league for the weekend's matchday, then turn each simulation into a video. A sim ingests a scenario, spins up ~20–30 agent personas, runs 10 rounds of simulated social debate plus a prediction market, and publishes a shareable report. Each run costs a flat $1.00 USDC via x402 on Base (gasless for the payer — EIP-3009, no ETH needed).

Spend cap: $4 USDC per run of this skill. Three sims = $3; at most one retry of one failed launch = $4. Never exceed it. A launch that failed AFTER payment settled is reported, never re-paid.

Wallet detection

Payment goes through the operator's Finance District agent wallet (see skills/finance-district-mcp/SKILL.md for the full auth story). Tools surface as mcp__finance-district__* — discover them from the server; don't assume a fixed list.

• No mcp__finance-district__* tool callable → not connected. Notify once pointing the operator at dashboard → MCP → Connect Finance District, log FD_NOT_CONNECTED, and exit.
• Tools return 401 / invalid-token → notify the operator to re-connect once, log FD_AUTH_STALE, and exit.
• Balance below $3 USDC → notify with the current balance, log MIROSHARK_INSUFFICIENT_FUNDS, and exit. No silent partial batches — a smaller run is what ${var} is for.

Steps

1. Build one matchday prompt per league

For each league in scope:

1. WebSearch the league's upcoming matchday — the fixtures played this weekend. Get the matchday number, 3–5 marquee fixtures, and one live storyline (title race, derby, injury, manager under pressure). Never write fixtures from memory of the season; verify by search every time.
2. Write a scenario prompt (4–4000 chars): matchday number, the key fixtures, the storyline, and the voices that should argue about it (ultras, club directors, betting analysts, journalists).
3. Pin the market with prediction_market: ONE binary question about a concrete outcome resolvable at the end of the matchday (e.g. "Will X be ranked above Y at the conclusion of Matchday N?"). A pinned sharp question beats letting the sim invent a vague one.
4. Optional free sanity check: POST https://x402.miroshark.xyz/suggest with the topic shows how MiroShark itself would phrase it. Use it to tighten your prompt, not replace it.

If ${var} is a custom scenario, run just that one.

2. Launch the sims (paid)

Launch all in-scope sims back-to-back — each accepted POST returns immediately with a run_id, so they simulate in parallel server-side (~10 min each):

• Endpoint: POST https://x402.miroshark.xyz/run with JSON body {"prompt": "<scenario>", "prediction_market": {...}}.
• Pay via the wallet's x402 flow (the endpoint prices at $1.00 USDC on Base; the wallet handles the 402 → sign → retry dance within its server-side caps).
• If MIROSHARK_AFFILIATE is set, add "affiliate": "<that address>" to the body — MiroShark shares 50% of net profit per referred run with that address.
• From each response capture run_id, status_url, and the payment reference the wallet reports.
• A launch that errors BEFORE payment settles may be retried once (within the cap). One that errors after settlement gets its run_id/payment reference recorded for the final report instead.

3. Wait for completion

Poll each https://x402.miroshark.xyz/status/<run_id> every ~90 seconds. Stages: ingest → ontology → graph_build → create → prepare → simulate → report; done when report completes. Timeout per sim: 25 minutes — on timeout keep the run_id in the final report (the sim may still finish; the report stays fetchable later) and continue with the sims that made it.

From each completed run capture the sim_id — the share link is https://x402.miroshark.xyz/share/<sim_id>.