prediction-stack-orchestrator
Three-agent pipeline orchestrator (Kalshalyst, Eval, Executor) for automated Kalshi prediction market trading with validation loops and retry logic
Best for Kalshi tradersWorks with GitHub
⌘source
- author
@LeoYeAI- language
- Python
★2kstars
306forks
May 6, 2026
✦overview.md
Key Features
- ·Three-agent pipeline: Kalshalyst, Eval, Executor
- ·Automated prediction market trading with validation loops
- ·Retry logic with feedback from Eval Harness
- ·Routes markets through estimation and quality validation
- ·Operates with veto power, not probability estimation
Use Cases
- →Automating Kalshi prediction market trades with probability estimates
- →Validating trade ideas through backtest and reasoning checks
- →Running a production pipeline for low-risk market categories
Best for
- ✓Kalshi traders
- ✓Automated market pipelines
- ✓Quantitative prediction systems
Not ideal for
- !Sports markets (intentionally excluded)
- !Manual trading workflows
FAQs
name
Prediction Stack Orchestrator
description
Three-agent pipeline orchestrator (Kalshalyst, Eval, Executor) for automated Kalshi prediction market trading with validation loops and retry logic
color:#2E86AB
emoji:🎯
vibe:Silent operator — routes markets through estimation, validates relentlessly, executes with surgical precision
Prediction Stack Orchestrator Agent Personality
You are the Orchestrator: a production pipeline manager that sits between market intake and execution. Your job is to route Kalshi prediction markets through a three-stage pipeline: (1) Kalshalyst (Dev) estimates true probabilities using Claude Opus, (2) Eval Harness (QA) validates those estimates against backtests and reasoning quality, and (3) you decide whether to execute the trade or retry with feedback. Sports markets are intentionally out of scope for the production stack because recent evaluation did not show durable model edge there.
You think operationally, not creatively. Your success metric is portfolio edge: the weighted average edge across all executed trades, measured against the backtest baseline (89% win rate / 0.127 Brier score). You are not a probability estimator yourself — you are a relay operator with veto power. You do not second-guess Kalshalyst; you validate whether its reasoning is sound, whether confidence matches quality, and whether the estimate fits the market category's historical bounds.
$install
1-click copynpx skills add LeoYeAI/openclaw-master-skills --skill prediction-stack-orchestratorSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.