Base Trader logo

Base Trader

Organization
sundial-org
base-trader

Autonomous crypto trading on Base via Bankr. Use for trading tokens, monitoring launches, executing strategies, or managing a trading portfolio. Triggers on "trade", "buy", "sell", "launch", "snipe", "profit", "PnL", "portfolio balance", or any crypto trading task on Base.

Overview

Publishersundial-org
Repositoryawesome-openclaw-skills
Skill namebase-trader
Stars
664
Forks
97
Bundled files
13
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 13 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by sundial-org on GitHub. Read the source before you install it.

Installation

Install the Base Trader AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/base-trader
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/sundial-org/awesome-openclaw-skills.git /tmp/awesome-openclaw-skills
mkdir -p .claude/skills
cp -r /tmp/awesome-openclaw-skills/skills/base-trader .claude/skills/base-trader
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Base Trader in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Base Trader on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Base Trader is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Base Trader 📈

Autonomous trading system for Base chain via Bankr API.

Philosophy

"The market is a machine for transferring wealth from the impatient to the patient."

This skill prioritizes capital preservation over aggressive gains. Every trade has defined risk parameters. No YOLO.

Prerequisites

  • Bankr API configured at ~/.clawdbot/skills/bankr/config.json
  • ETH in your Bankr wallet for gas and trading
  • Check your wallet address with: bankr.sh "What is my wallet address?"

Core Principles

1. Risk Management (NON-NEGOTIABLE)

MAX_POSITION_SIZE = 10% of portfolio
MAX_SINGLE_TRADE = $50 USD
STOP_LOSS = -15% from entry
TAKE_PROFIT = +30% minimum target
MAX_DAILY_LOSS = -20% of starting balance

If daily loss limit hit → STOP TRADING FOR 24 HOURS.

2. Entry Criteria (ALL must pass)

Before ANY buy:

  • Liquidity > $10k
  • Contract verified on Basescan
  • No honeypot indicators (can sell)
  • Not on known scam list
  • Age > 5 minutes (avoid rugs at launch)
  • Price action shows accumulation, not dump

3. Exit Rules

Take Profit (scale out):

  • 25% at +30%
  • 25% at +50%
  • 25% at +100%
  • Hold 25% moonbag

Stop Loss:

  • Hard stop at -15%
  • No averaging down on losers

Trading Strategies

Strategy 1: Launch Sniper (HIGH RISK)

Monitor new token launches, enter early with small size.

bash
# Check trending/new tokens
scripts/bankr.sh "What tokens are trending on Base?"

# Research before buying
scripts/bankr.sh "What's the liquidity for TOKEN on Base?"

# Small entry
scripts/bankr.sh "Buy $20 of TOKEN on Base"

Rules:

  • Max $20 per snipe
  • Sell 50% at 2x, rest at 5x or stop loss
  • Max 3 snipes per day

Strategy 2: Momentum Trading (MEDIUM RISK)

Trade established tokens showing strength.

Entry signals:

  • Price > 20-period MA
  • Volume increasing
  • Higher lows forming
bash
# Check momentum
scripts/bankr.sh "Do technical analysis on TOKEN"

# Enter with limit order
scripts/bankr.sh "Buy $30 of TOKEN if price drops to X"

Strategy 3: DCA Blue Chips (LOW RISK)

Steady accumulation of proven tokens.

bash
# Weekly DCA
scripts/bankr.sh "DCA $20 into ETH every week on Base"
scripts/bankr.sh "DCA $10 into USDC every week on Base"

Execution via Bankr

Check Portfolio

bash
~/clawd/skills/bankr/scripts/bankr.sh "Show my portfolio on Base"

Execute Trade

bash
~/clawd/skills/bankr/scripts/bankr.sh "Buy $25 of TOKEN on Base"

Set Stop Loss

bash
~/clawd/skills/bankr/scripts/bankr.sh "Set stop loss for TOKEN at -15%"

Check Price

bash
~/clawd/skills/bankr/scripts/bankr.sh "What's the price of TOKEN on Base?"

Trade Journal

Log every trade to data/trades.json:

json
{
  "timestamp": "2026-01-28T12:00:00Z",
  "action": "BUY",
  "token": "TOKEN",
  "amount_usd": 25,
  "price": 0.001,
  "reason": "Launch snipe - verified contract, good liquidity",
  "tx": "0x..."
}

After each trade, update the journal. Review weekly for pattern analysis.

Daily Routine

Morning (9 AM)

  1. Check portfolio balance
  2. Review overnight price action
  3. Identify opportunities
  4. Set limit orders for the day

Midday (1 PM)

  1. Check open positions
  2. Adjust stop losses if in profit
  3. Take profits if targets hit

Evening (6 PM)

  1. Close any day trades
  2. Log all trades to journal
  3. Calculate daily PnL
  4. Review what worked/didn't

Red Flags (DO NOT TRADE)

  • Honeypot (can't sell)
  • Liquidity < $5k
  • Unverified contract
  • Team anonymous with no track record
  • Promises of guaranteed returns
  • Excessive tax (>10%)
  • Locked liquidity < 30 days
  • Price already 10x+ from launch

Performance Tracking

Track in data/performance.json:

json
{
  "start_date": "2026-01-28",
  "starting_balance_usd": 100,
  "current_balance_usd": 100,
  "total_trades": 0,
  "winning_trades": 0,
  "losing_trades": 0,
  "win_rate": 0,
  "total_pnl_usd": 0,
  "best_trade": null,
  "worst_trade": null
}

Safety Overrides

If ANY of these occur, STOP ALL TRADING:

  1. Daily loss > 20%
  2. 3 consecutive losing trades
  3. Portfolio down > 30% from ATH
  4. Unexpected error in execution
  5. Market-wide crash (ETH -20% in 24h)

Wait 24 hours, reassess, then resume with smaller size.

Autonomous Trading Mode

When running autonomously (via cron or heartbeat):

Morning Scan (9 AM)

  1. Check portfolio balance
  2. Review overnight price action on holdings
  3. Scan for new opportunities
  4. Set limit orders for the day

Midday Check (1 PM)

  1. Monitor open positions
  2. Adjust trailing stops on winners
  3. Take profits if targets hit
  4. Log any executed trades

Evening Review (6 PM)

  1. Close day trades if any
  2. Calculate daily PnL
  3. Update performance.json
  4. Generate summary for user

Execution Commands

bash
# Morning
~/clawd/skills/bankr/scripts/bankr.sh "Show my portfolio on Base"
~/clawd/skills/bankr/scripts/bankr.sh "What tokens are trending on Base?"

# Execute trade
~/clawd/skills/bankr/scripts/bankr.sh "Buy $25 of TOKEN on Base"

# Set protection
~/clawd/skills/bankr/scripts/bankr.sh "Set stop loss for TOKEN at -15%"

# Take profit
~/clawd/skills/bankr/scripts/bankr.sh "Sell 25% of my TOKEN on Base"

References

Core Trading

Market & Research

Execution

Advanced


"The goal is not to make money on every trade. The goal is to be profitable over time."

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Base Trader AI skill do?

Autonomous crypto trading on Base via Bankr. Use for trading tokens, monitoring launches, executing strategies, or managing a trading portfolio. Triggers on "trade", "buy", "sell", "launch", "snipe", "profit", "PnL", "portfolio balance", or any crypto trading task on Base.

Why use Base Trader on TypingMind?

Because you install it once and use it with any model. Base Trader is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Base Trader in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/base-trader. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Base Trader?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Base Trader?

As many as you like. As long as a model supports skills, you can use Base Trader with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Base Trader AI skill free?

It is published on GitHub by sundial-org. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇