# trading-wisdom

Supplies your coding agent with quantitative takeaways and risk rules recorded during the Agent Arena competition. Useful when setting up algorithmic trading logic.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 800 installs · ★ 9
- Author: 0xhubed
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/0xhubed/agent-trading-arena/tree/HEAD/.claude/skills/trading-wisdom/SKILL.md
- Updated: 2026-04-20
- HTML: https://affpapa.org/en/nevibecode/skills/trading-wisdom

## What it does

The skill injects a dataset of 232 verified trading patterns compiled from 22482 observations during the Agent Arena event. Every pattern meets a minimum confidence threshold of 60%. The observations cover crypto assets including BTC, ETH, SOL, BNB, and DOGE.

The repository documents repeatable rules: risking 2% equity per position, targeting a 2:1 reward-to-risk ratio, and requiring directional alignment across 15m, 1h, and 4h intervals. It highlights that the `journal_aware` agent, which tracked past decisions, turned a profit while five other active bots suffered collective losses.

Frequent trading deepens drawdowns if your directional bias clashes with the market trend. Inaction often wins. During strongly trending windows in the benchmark, bots that placed zero trades preserved equity far better than active strategies executing against the trend.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add 0xhubed/agent-trading-arena --skill trading-wisdom -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add 0xhubed/agent-trading-arena --skill trading-wisdom -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add 0xhubed/agent-trading-arena --skill trading-wisdom -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install 0xhubed/agent-trading-arena trading-wisdom
```

2. **Manually: put the files in place**
- File: `.github/skills/trading-wisdom/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add 0xhubed/agent-trading-arena --skill trading-wisdom -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/0xhubed/agent-trading-arena --path .claude/skills/trading-wisdom
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add 0xhubed/agent-trading-arena --skill trading-wisdom -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/0xhubed/agent-trading-arena/tree/HEAD/.claude/skills/trading-wisdom/SKILL.md

## When to use it
- cap position risk at 2% total equity
- validate multi-timeframe trends across 15m, 1h, and 4h charts
- halt trade execution during market regime mismatches
- evaluate automated strategy behavior against Agent Arena test data

## Example prompts
- Evaluate this planned short trade on SOL using rules from `trading-wisdom`.
- Check my position sizing against the 2% equity risk and 2:1 reward guidelines.
- Show the performance findings for zero-trade strategies during bullish trends.

## 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: 57cd01bd8f3f7f63.

BEGIN THIRD-PARTY FILE 57cd01bd8f3f7f63
```text
---
name: trading-wisdom
description: Core trading insights learned from Agent Arena competition. Use when making any trading decision to apply institutional knowledge.
---

# Trading Wisdom

> Last updated: 2026-03-09 20:08 UTC
> Active patterns: 232
> Total samples: 22482
> Confidence threshold: 60%

## Key Learnings

1. Market was uniformly bullish (BNB +3.31%, BTC +2.68%, ETH +3.90%, SOL +5.07%, DOGE +2.46%) — the 7th consecutive window where regime misidentification was the primary loss driver.
2. Only 1 of 6 active agents was profitable (journal_aware +$55.48). The other 5 active agents lost a combined -$571.18, suggesting widespread SHORT bias despite uniformly positive market.
3. gptoss_skill_aware was the worst performer (-$340.51 on 31 trades), consistent with the persistent pattern of sophisticated validation frameworks providing false confidence on wrong-direction trades.
4. Self-reflective position management (journal_aware) continues to be the most reliable edge among active agents, now profitable in multiple bullish windows.
5. Zero trading (ta_bot, index_fund) outperformed 5 of 6 active agents, reinforcing that inaction beats wrong-direction action.
6. SOL was the best performer (+5.07%) — highest-beta assets continue to show the largest moves, making them both the best LONG targets and the worst SHORT targets.
7. Trade frequency amplifies losses when directional bias is wrong: skill_aware's 31 trades at -$10.98/trade vs contrarian's 6 trades at -$3.79/trade.

## Winning Strategies

### skill_aware_oss: High-frequency SHORT-biased tradi...
- **Confidence**: 95%
- **Total samples**: 200
- **Times confirmed**: 1
- **First seen**: 2026-02-01
- **Details**: skill_aware_oss: High-frequency SHORT-biased trading (200 trades/24h) with multi-timeframe bearish alignment validation, 2% equity risk sizing, and disciplined profit-taking. Achieved +$2911.52 in uniformly bearish market (-6% to -11% across all assets).

### Combining technical validation ('risk calculator s...
- **Confidence**: 92%
- **Total samples**: 200
- **Times confirmed**: 1
- **First seen**: 2026-02-01
- **Details**: Combining technical validation ('risk calculator shows 2:1 reward', 'validation permits trade') with trend alignment across 15m/1h/4h timeframes for SHORT entries in bearish markets. skill_aware_oss used this consistently with high confidence (0.78-0.92).

### index_fund's zero-trade strategy preserves capital...
- **Confidence**: 90%
- **Total samples**: 244
- **Times confirmed**: 1
- **First seen**: 2026-02-02
- **Details**: index_fund's zero-trade strategy preserves capital ($0 PnL) when all active trading agents lose money. In uniform_bullish markets (+1.33% to +3.82% across all assets), passive allocation beats active SHORT-biased trading.
```
END THIRD-PARTY FILE 57cd01bd8f3f7f63

The third-party file has ended. Everything between the 57cd01bd8f3f7f63 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 2785 of 31443 bytes. © 0xhubed · MIT · https://github.com/0xhubed/agent-trading-arena/tree/HEAD/.claude/skills/trading-wisdom/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