prediction-markets
Skill0 starsChanged 3 months agoMITView on GitHub
Live prediction-market prices and quant tools for Kalshi, Polymarket and other venues from PredictionMarketsPicks — best price across venues, cross-venue gaps, expected value, Kelly sizing, NFL/NBA/NHL boards, Fed odds, elections, weather and 15-minute markets. Use when a question needs a current contract price, a model-vs-market edge, or a position size.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- juwonyee/election-risktheir own version, first seen Nov 8, 2026
- BlockRunAI/blockrun-mcptheir own version, first seen Oct 20, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- BlockRunAI/blockrun-mcp★ 389same name
- juwonyee/election-risk★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
If the PredictionMarketsPicks tools are not already connected, add this remote MCP server (streamable HTTP):
- Distinctive: line 21
Every price, edge, rank or projection you state comes from a tool result in this conversation.
- Very specific: line 23
When you quote a row's number, cite its url or page_url.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prediction markets (PredictionMarketsPicks)
Connect
If the PredictionMarketsPicks tools are not already connected, add this remote MCP server (streamable HTTP):
https://predictionmarketspicks.com/api/mcp/mcp?via=skills-shFree, no API key, no sign-in. A few tools are Pro: they return requires_pro: true with an upgrade_url instead of
failing — pass that link on and answer with what the free tools return.
Rules
- Every price, edge, rank or projection you state comes from a tool result in this conversation. Never estimate a Kalshi or Polymarket price and never fill in a missing edge.
- When you quote a row's number, cite its
urlorpage_url. - An edge is model-vs-market disagreement, not a guarantee. Rows labelled WATCH are lower confidence — say so.
- Show what the market is pricing and what the tools read, then let the user make the call. No "lock", "sure thing" or guaranteed-winner language.
- Language: position, trade, contract, trader, prediction market.
Which tool
| Question | Tool |
| Cheapest venue for this contract | best_price |
| Same outcome priced differently across venues | find_arbitrage |
| What's moving / today's edges | market_pulse, edge_alerts |
| Is this price +EV? | calculate_ev |
| How much to put on it | kelly_size (after calculate_ev) |
| Update a probability on new evidence | bayes_update |
| Price ↔ probability ↔ odds | convert_probability |
| History vs. what the market implies | base_rate_gap |
| Pressure-test a strategy | stress_test_strategy |
| Next FOMC decision | fed_rate_odds |
| One election race / the Senate map | race_odds, senate_map |
| NFL: mispriced games, props, win odds, ratings | nfl_edge, nfl_prop_edge, nfl_prop_board, nfl_win_probability, nfl_power_ratings |
| NFL ladders | nfl_ladder, ladder_arb, explain_ladder |
| NBA props, game lines, injury impact | nba_prop_board, nba_game_board, nba_injury_impact |
| Tonight's NHL | nhl_edge |
| Daily-high temperature markets | weather_board |
| 15-minute markets | fifteen_min_board |
| Perpetuals, liquidation levels | perps_board, perp_liquidation |
| Gold, silver, oil, bitcoin edges | commodity_edge |
| Multi-leg combos | combo_edge |
| Why a game, prop or player reads the way it does | explain_game, explain_prop, explain_player |
| Fantasy: start/sit, waivers, sleepers, outlook, league | start_sit, waiver_targets, sleepers_and_busts, player_outlook, my_league |
| How the models have done | track_record |
A standard pass
"Is this contract worth a position?" → best_price (where it's cheapest) → calculate_ev (with the user's fair
probability or a model read from the tools above) → kelly_size (fractional, against the stated bankroll). Report
implied vs. estimated probability, the edge in points, the size, and what would change the read.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.