← Back to list
kalshi-weather-markets Checked
Daily temperature high/low bracket and threshold contracts on Kalshi — contract structure, foreca…
8.8Overall rating
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "kalshi-weather-markets" skill by following the instructions at https://skill123.me/install/kalshi-weather-markets.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/kalshi-weather-markets.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 12 KBAbout this skill
Overview
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
Source
- Repo: https://github.com/agiprolabs/claude-trading-skills
- Path: skills/kalshi-weather-markets
Score breakdown
Trigger
7.5
Description covers What (bracket/threshold structure, forecast-to-probability, settlement) and topic keywords well; When/When-Not only implicit via pointers to kalshi-api and prediction-market-strategy skills; no negative-trigger boundary. Keywords (bracket, threshold, settlement, cross-venue, high/low temperature) reasonably rich.
Structure
9.3
188-line SKILL.md with clean offload to two references/ and one script; Files section explains each file's role; no redundant docs; good progressive disclosure via inline pointers.
Workflow
8.0
Task-oriented formulas and procedures with deterministic math delegated to script; pitfalls act as explicit guards (strike_type from API, ticker-date joins, LST window); overround diagnostic and worked example provide verification; but no end-to-end ordered workflow (it is a domain reference more than a procedure).
Content
9.0
Tight imperative writing, runnable formulas with concrete parameters, no filler; a few reference-number tables are background-ish but earn their place.
Engineering
10.0
Valid frontmatter; script has shebang, stdlib-only, runs offline, includes __main__ example; all referenced paths exist.
Security
10.0
6.0 manifest: data reads none; side effects none; network destinations none in scripts (explicitly offline); credentials none; persistence none. Reference URLs are all official/trusted domains, presented as links not commands. Capabilities match declared scope. No injection text, no hardcoded secrets, no destructive commands.
Deep domain skill on Kalshi daily temperature bracket/threshold markets. Strong: exact settlement mechanics, half-integer continuity correction, leakage rules, cross-venue divergence, honest 'forecast skill != trading edge' framing. Pure-stdlib offline script with worked example. Deductions: D1 description is topic-enumeration without explicit when-not beyond 'see kalshi-api' pointer; D3 is reference-style rather than an ordered execution workflow. 6.0 manifest: no network calls, no file writes, no env/credential reads; references list only official docs URLs (kalshi.com, weather.gov, iastate.edu, wunderground.com, uma.xyz) as informational links - capabilities match declared scope. No investment-advice disclaimer but content is quant/analytical, includes explicit edge-skepticism caveat.