Aerodrome logo

Aerodrome

Organization
Superior-Trade
aerodrome

Use when creating, validating, backtesting, deploying, sizing, or troubleshooting Aerodrome/Base spot trading strategies through the Superior Trade API, especially Freqtrade configs using exchange.name "aerodrome", AERO/USDC or CHECK/USDC pairs, AMM market swaps, wallet/gas balance checks, no-orderbook pricing, or Aerodrome live deployment safety.

Overview

PublisherSuperior-Trade
Repositorysuperior-skills
Skill nameaerodrome
Stars
215
Forks
9
Bundled files
3
LicenseMIT
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.

  • 3 bundled files

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

  • Open source

    Published by Superior-Trade on GitHub. Read the source before you install it.

Installation

Install the Aerodrome 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/Superior-Trade/superior-skills/tree/main/skills/aerodrome
  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/Superior-Trade/superior-skills.git /tmp/superior-skills
mkdir -p .claude/skills
cp -r /tmp/superior-skills/skills/aerodrome .claude/skills/aerodrome
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Aerodrome 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 Aerodrome 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 Aerodrome 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.

Aerodrome Trading

Read ../../references/unified-runtime.md before any Superior Trade request. Use the current OpenAPI schema for every payload and stop if Aerodrome/Freqtrade is not listed as supported.

Overview

Use this skill only for Aerodrome trading on Base through Superior Trade. Aerodrome is spot-only AMM swap execution: no futures, no margin, no shorting, no leverage, no sub-accounts, and no order book.

Production Defaults

  • Superior Trade API base URL: https://api.superior.trade
  • Auth header: x-api-key: $SUPERIOR_TRADE_API_KEY
  • Base RPC URL: https://mainnet.base.org
  • Keep setup simple: one pair, one numeric stake amount, static pairlist, market orders, and no orderbook pricing.

Source Of Truth

When behavior is unclear, inspect these local sources before answering:

  • Production API: https://api.superior.trade

Non-Negotiables

  • Use exchange.name: "aerodrome".
  • Use only the supported spot pairs: AERO/USDC and CHECK/USDC. Never use :USDC.
  • Omit trading_mode, or set it to "spot" only.
  • Never set margin_mode, leverage, short entries, or futures fields.
  • Set entry_pricing.use_order_book: false and exit_pricing.use_order_book: false.
  • Do not call self.dp.orderbook(), fetch_order_book, fetch_l2_order_book, or order-book depth checks in strategy code.
  • Use market orders. Aerodrome's CCXT adapter supports AMM market swaps, not limit-order-book execution.
  • Use explicit numeric stake_amount. Avoid "unlimited" unless the user explicitly accepts balance exhaustion risk.
  • Never include wallet private keys or platform-injected exchange credentials in config.
  • Use https://mainnet.base.org for exchange.ccxt_config.options.rpcUrl unless the user explicitly provides another Base RPC.
  • Always backtest before suggesting live deployment.
  • Never start live trading without explicit user confirmation.

Wallet And Balance Rules

Aerodrome live trading depends heavily on the Base wallet balances because every order is an on-chain swap.

Before live deployment or when troubleshooting zero trades:

  1. Verify the wallet has enough quote token for buys, usually USDC.
  2. Verify it has enough base token for sells, such as AERO for AERO/USDC.
  3. Verify it has Base ETH for gas. A small ETH balance is required even when trading USDC pairs.
  4. Size stake_amount * max_open_trades below free quote balance and leave room for AMM slippage, token fees, and gas. Prefer 70-90% of available quote balance, lower for small wallets.
  5. If the wallet balance cannot be checked in the current turn, say it has not been checked. Do not infer or fabricate balances.

Important distinction: Aerodrome uses Base wallet balances directly for on-chain swaps. Do not apply external exchange account rules here.

Supported Markets

Hard-code these Aerodrome/Base market definitions when configuring exchange.ccxt_config.options.markets:

SymbolBase addressBase decimalsQuote addressQuote decimalsPool addressStable
AERO/USDC0x940181a94A35A4569E4529A3CDfB74e38FD98631180x833589fcd6edb6e08f4c7c32d4f71b54bda0291360x6cdcb1c4a4d1c3c6d054b27ac5b77e89eafb971dfalse
CHECK/USDC0x9126236476eFBA9Ad8aB77855c60eB5BF37586Eb180x833589fcd6edb6e08f4c7c32d4f71b54bda0291360x6a4BeFa1337865071E27c62dc9d7E3bCa253cE0ffalse

Backtesting data is available for both supported pairs on 5m, 15m, 1h, 4h, and 1d.

Minimum Config

Start from this shape and only change pair_whitelist, timeframe, stake, and strategy parameters. Keep the hard-coded supported markets and no-orderbook fields.

json
{
  "exchange": {
    "name": "aerodrome",
    "pair_whitelist": ["AERO/USDC"],
    "ccxt_config": {
      "options": {
        "rpcUrl": "https://mainnet.base.org",
        "markets": [
          {
            "symbol": "AERO/USDC",
            "baseAddress": "0x940181a94A35A4569E4529A3CDfB74e38FD98631",
            "baseDecimals": 18,
            "quoteAddress": "0x833589fcd6edb6e08f4c7c32d4f71b54bda02913",
            "quoteDecimals": 6,
            "poolAddress": "0x6cdcb1c4a4d1c3c6d054b27ac5b77e89eafb971d",
            "stable": false
          },
          {
            "symbol": "CHECK/USDC",
            "baseAddress": "0x9126236476eFBA9Ad8aB77855c60eB5BF37586Eb",
            "baseDecimals": 18,
            "quoteAddress": "0x833589fcd6edb6e08f4c7c32d4f71b54bda02913",
            "quoteDecimals": 6,
            "poolAddress": "0x6a4BeFa1337865071E27c62dc9d7E3bCa253cE0f",
            "stable": false
          }
        ]
      }
    }
  },
  "stake_currency": "USDC",
  "stake_amount": 10,
  "max_open_trades": 1,
  "timeframe": "5m",
  "stoploss": -0.1,
  "minimal_roi": { "0": 0.05 },
  "order_types": {
    "entry": "market",
    "exit": "market",
    "force_entry": "market",
    "force_exit": "market",
    "emergency_exit": "market",
    "stoploss": "market",
    "stoploss_on_exchange": false
  },
  "entry_pricing": { "price_side": "other", "use_order_book": false },
  "exit_pricing": { "price_side": "other", "use_order_book": false },
  "pairlists": [{ "method": "StaticPairList" }]
}

Notes:

  • stake_currency must appear in the configured markets. For AERO/USDC, use USDC.
  • Use trading_min_order_amount only when the strategy needs an explicit minimum; the API pads Aerodrome configs to 1 when omitted.
  • Do not include dry_run, initial_state, api_server, walletAddress, privateKey, wallet_address, or private_key.
  • ccxt_async_config is usually unnecessary for Aerodrome authoring unless current API tests show otherwise.

Backtest Workflow

  1. Build Aerodrome config and Freqtrade strategy code.
  2. Check data availability with GET https://api.superior.trade/runtime/backtests/dataset and the query fields published by OpenAPI.
  3. Create a backtest with POST https://api.superior.trade/runtime/backtests using framework: "freqtrade", venue: "aerodrome", strategy source/config, instruments, and timerange fields from the current contract.
  4. Creation queues the run; poll GET https://api.superior.trade/runtime/backtests/{id} until completed or failed.
  5. Fetch the backtest record and GET /runtime/backtests/{id}/logs for full metrics and diagnostics.
  6. Present total trades, win rate, profit, drawdown, and whether results justify live testing.

Do not offer live deployment after a zero-trade backtest unless the user explicitly wants to debug live behavior.

Live Deployment Workflow

  1. Create a deployment with POST https://api.superior.trade/runtime/deployments using top-level framework, venue, mode, name, code, and config fields.
  2. If credentials are required, use PUT /runtime/deployments/{id}/credentials with the exact form published by Unified OpenAPI. Never improvise private-key fields.
  3. Run the pre-deployment checklist below.
  4. Show a concise live trading summary and wait for explicit confirmation.
  5. Start with PUT https://api.superior.trade/runtime/deployments/{id}/status and { "action": "start" }.
  6. Monitor status and logs with GET https://api.superior.trade/runtime/deployments/{id} and GET https://api.superior.trade/runtime/deployments/{id}/logs.
  7. Stop with PUT https://api.superior.trade/runtime/deployments/{id}/status and { "action": "stop" }.

Pre-Deployment Checklist

  • Backtest completed and was reviewed.
  • Config is Aerodrome spot-only and has no margin_mode, leverage, shorting, or :USDC pair suffix.
  • entry_pricing.use_order_book and exit_pricing.use_order_book are false.
  • stake_amount is numeric and fits wallet balances with gas/slippage buffer.
  • Wallet has Base ETH for gas and enough relevant token balance for intended buys/sells.
  • Strategy has no custom orderbook or RPC polling.
  • User explicitly confirmed live trading.

Use this confirmation format:

text
Deployment Summary:
- Exchange: aerodrome on Base
- Trading mode: spot only
- Pair: [pair]
- Stake amount: [amount] [stake_currency] per trade
- Max open trades: [n]
- Stoploss: [percentage]
- Order execution: AMM market swaps, no orderbook
- Wallet balance checked: [yes/no, source]
- Base ETH gas checked: [yes/no, source]

This will trade with real funds. Proceed? (yes/no)

Reference files

Load on demand.

ReadWhen
references/api.mdYou need endpoint shapes or a complete AERO/USDC backtest payload.
references/strategy-template.mdYou are writing or adapting the strategy code.
references/troubleshooting.mdA swap failed, gas is short, or a deployment trades zero times.

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 Aerodrome AI skill do?

Use when creating, validating, backtesting, deploying, sizing, or troubleshooting Aerodrome/Base spot trading strategies through the Superior Trade API, especially Freqtrade configs using exchange.name "aerodrome", AERO/USDC or CHECK/USDC pairs, AMM market swaps, wallet/gas balance checks, no-orderbook pricing, or Aerodrome live deployment safety.

Why use Aerodrome on TypingMind?

Because you install it once and use it with any model. Aerodrome 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 Aerodrome in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Superior-Trade/superior-skills/tree/main/skills/aerodrome. 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 Aerodrome?

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 Aerodrome?

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

Is the Aerodrome AI skill free?

Yes. It is published on GitHub by Superior-Trade under the MIT license. 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 👇