메뉴
Autonomous edge discovery — VARRD generates, tests, and validates trading hypotheses hands-free. Use when the user wants the AI to find trading edges on its own given a topic or market.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Browse VARRD's validated edge library — see which edges are firing right now, get stats and trade levels, or drill into the full methodology and performance of any edge.
Check VARRD credit balance and available credit packs. Use when the user asks about credits, billing, or how much research budget remains.
Get full details on a specific saved strategy — formula, metrics, version history. Use when the user wants to inspect a particular hypothesis or strategy in detail.
The core VARRD research tool — talk to a state-of-the-art quant AI to research, chart, test, optimize, and trade any market idea. Use when the user wants to test a trading hypothesis, find edges, or validate a strategy with real market data.
Reset a broken or stuck research session and start fresh. Use when a VARRD session is erroring or stuck.
Find saved strategies by keyword or natural language query. Use when the user wants to look up or browse previously validated trading strategies.
| name | varrd-discover |
| description | Autonomous edge discovery — VARRD generates, tests, and validates trading hypotheses hands-free. Use when the user wants the AI to find trading edges on its own given a topic or market. |
| version | 1.0.0 |
| tools | ["Bash"] |
| homepage | https://varrd.com |
| metadata | {"openclaw":{"requires":{"bins":["varrd"]},"emoji":"🔍"}} |
Use this skill when a user wants VARRD to autonomously discover trading edges without driving the conversation step-by-step.
varrd discover "<topic>"
Give it a topic and VARRD handles everything: generates a creative hypothesis from its market structure knowledge base, loads data, charts the pattern, runs statistical tests, and returns the trade setup if an edge is found. One command, one result.
Each call tests ONE hypothesis through the full pipeline. Call again for another — VARRD uses tangential idea propagation, so related concepts branch out from your seed idea.
varrd discover "momentum on grains"
varrd discover "mean reversion on crypto" --mode explore
varrd discover "volatility clustering on ES" --markets ES NQ
varrd discover "seasonal patterns in energy" --test-type backtest
| Flag | Values | Default | Description |
|---|---|---|---|
--mode | focused, explore | focused | focused = stay close to topic, explore = creative freedom |
--markets | e.g. ES NQ CL | auto | Focus on specific markets |
--test-type | event_study, backtest, both | event_study | Type of statistical test |
| Scenario | Use |
|---|---|
| You have a specific idea to test | varrd research "your idea" |
| You want broad exploration of a space | varrd discover "topic" |
| You want control over each step | varrd research |
| You want hands-free, one command | varrd discover |
| Running many hypotheses at scale | varrd discover in a loop |
The result includes:
--mode explore for more creative, tangential ideasfor topic in "momentum" "mean reversion" "breakouts"; do varrd discover "$topic"; donevarrd scan later to see what's firing~20-30 cents per discovery call.
from varrd import VARRD
v = VARRD()
result = v.discover("mean reversion on crypto", search_mode="explore")
print(result.has_edge, result.edge_verdict)