# kalshi-weather-markets

kalshi-weather-markets covers daily high/low temperature contracts on Kalshi: ticker structure, the forecast-to-P(YES) map, settlement rules, and weather-specific pitfalls.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 352 installs · ★ 582 repo stars
- Author: agiprolabs
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/agiprolabs/claude-trading-skills/tree/HEAD/skills/kalshi-weather-markets/SKILL.md
- Updated: 2026-09-03
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/kalshi-weather-markets

## What it does

The skill documents binary contracts on daily highs and lows for around 20 US cities. YES settles at $1.00, NO at $0.00. Two contract types are covered: brackets `B<center>` — a 2°F window with both ends inclusive — and thresholds `T<strike>`, one-sided binaries. The threshold direction (`greater` or `less`) is not encoded in the ticker; it has to come from the `strike_type` field in the API.

P(YES) is computed from a forecast distribution `N(μ, σ)` with a mandatory ±0.5 continuity correction. Skipping it biases every bracket: one project treated 2°F windows as half-open and produced a +1640% phantom backtest. The CLI/METAR gap matters too — the skill suggests fitting a per-city, per-season bias before pricing.

The settlement date lives in the ticker (`KXHIGHNY-26JUN21` settles 2026-06-21 LST), not in `close_time`, which rolls to the next UTC day. Settlement uses the NWS Climatological Report, midnight-to-midnight LST with no DST adjustment. Read each market's rulebook before scoring: source, station, and day window are per-contract terms.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add agiprolabs/claude-trading-skills --skill kalshi-weather-markets -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/kalshi-weather-markets/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/kalshi-weather-markets/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add agiprolabs/claude-trading-skills --skill kalshi-weather-markets -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/kalshi-weather-markets/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add agiprolabs/claude-trading-skills --skill kalshi-weather-markets -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/kalshi-weather-markets/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install agiprolabs/claude-trading-skills skills/kalshi-weather-markets
```

2. **Manually: put the files in place**
- File: `.github/skills/kalshi-weather-markets/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add agiprolabs/claude-trading-skills --skill kalshi-weather-markets -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/agiprolabs/claude-trading-skills --path skills/kalshi-weather-markets
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/kalshi-weather-markets/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add agiprolabs/claude-trading-skills --skill kalshi-weather-markets -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/agiprolabs/claude-trading-skills/tree/HEAD/skills/kalshi-weather-markets/SKILL.md

## When to use it
- map a temperature forecast to YES probability for a bracket
- avoid guessing greater vs less on threshold contracts
- apply the half-integer correction when pricing brackets
- correct for the METAR-to-CLI bias per city and season
- pull the settlement date from the ticker instead of close_time

## Example prompts
- Price bracket `B74.5` with forecast μ=75, σ=2.1
- What settlement date is encoded in `KXHIGHNY-26JUN21-B74.5`?
- How do I tell if threshold `T74` is greater or less?

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 7d7cc616e5dc70d1.

BEGIN THIRD-PARTY FILE 7d7cc616e5dc70d1
````text
---
name: kalshi-weather-markets
description: Daily temperature high/low bracket and threshold contracts on Kalshi — contract structure, forecast→P(YES) map, settlement rules, cross-venue divergences, and weather-specific pitfalls
---

# Kalshi Weather Markets — Daily Temperature High/Low

Kalshi lists daily high and low temperature options for ~20 US cities as binary contracts that settle YES ($1.00) or NO ($0.00). This skill covers the market structure, the forecast-to-probability map, exact settlement mechanics, and hard-won pitfalls. It builds on the exchange layer — for Kalshi API mechanics (host, auth, orders, order book, candlesticks) see the `kalshi-api` skill; for strategy, sizing, and backtesting see `prediction-market-strategy`.

## Contract Types

### Brackets — `B<center>`

A bracket ticker `B<center>` is a **2°F-wide, both-ends-inclusive** window.

- `B74.5` covers the **two integers {74, 75}°F**.
- YES iff the settled temperature is exactly 74 **or** 75.
- Brackets in one event are mutually exclusive and (with two open tail markets) collectively exhaustive.
- Their YES prices sum to the **overround** (fair = 1.0; > 1.0 = aggregate overpricing).

### Thresholds — `T<strike>`

A threshold ticker `T<strike>` is a one-sided binary.

- `greater` → YES iff `cli >= strike + 1`
- `less` → YES iff `cli <= strike - 1`
- **Critical:** `strike_type` (`"greater"` / `"less"`) is **not inferable from the ticker**. Read it from the API `strike_type` field every time.

### Ticker Format

```
KXHIGH<CITY>-<YYMONDD>-B<center>     # bracket high
KXLOW<CITY>-<YYMONDD>-T<strike>      # threshold low
```

**The date is encoded in the ticker, not derivable from `close_time`.**  
`KXHIGHNY-26JUN21` settles 2026-06-21 LST. `close_time` is next-day UTC (~00:59 ET). Joining on `close_time` off-by-ones every label — use the ticker date.

---

## Forecast → P(YES)

Given a forecast distribution `N(μ, σ)` for the day's extreme, apply the **half-integer continuity correction** (mandatory — settlement is on integers, not a continuous scale):

```
# Bracket B<center>, covering integers {floor, cap}
P(YES) = Φ((cap + 0.5 − μ) / σ) − Φ((floor − 0.5 − μ) / σ)

# Threshold "greater":
P(YES) = 1 − Φ((T + 0.5 − μ) / σ)
````
END THIRD-PARTY FILE 7d7cc616e5dc70d1

The third-party file has ended. Everything between the 7d7cc616e5dc70d1 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2281 of 8927 bytes. © agiprolabs · MIT · https://github.com/agiprolabs/claude-trading-skills/tree/HEAD/skills/kalshi-weather-markets/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
