← 返回 Skills 市场
aixvcteam

Axelrod

作者 aixvcteam · GitHub ↗ · v0.1.0
cross-platform ⚠ suspicious
783
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install axelrod
功能描述
AI-powered Base-chain trading and on-chain query agent via natural language. Use when the user wants to trade crypto (buy/sell/swap tokens), set up automated strategies (DCA, limit orders, RSI), check portfolio balances, view token prices, query token info/analysis, check order status, manage take-profit/stop-loss orders, or ask about crypto/DeFi topics on Base chain. Always run scripts/axelrod_chat.py to fetch real-time results.
使用说明 (SKILL.md)

Axelrod

Execute Base-chain trading and on-chain queries using natural language through the AIxVC AI Automation.

Quick Start

First-Time Setup

  1. Configure credentials in OpenClaw config under skills.entries.axelrod.env:
{
  "skills": {
    "entries": {
      "axelrod": {
        "enabled": true,
        "env": {
          "AIXVC_ACCESS_KEY": "your_access_key",
          "AIXVC_SECRET_KEY": "your_secret_key"
        }
      }
    }
  }
}
  1. Install dependencies:
pip install -r skills/axelrod/requirements.txt
  1. Verify setup:
python skills/axelrod/scripts/axelrod_chat.py --message "check my balance"

Core Usage

Simple Query

For straightforward requests that complete quickly:

python skills/axelrod/scripts/axelrod_chat.py --message "check my ETH balance"
python skills/axelrod/scripts/axelrod_chat.py --message "what is ETH price now"

JSON Debug Mode

For inspecting the full API response:

python skills/axelrod/scripts/axelrod_chat.py --message "check my balance" --json

Mandatory Workflow

  1. Check AK/SK — If AIXVC_ACCESS_KEY or AIXVC_SECRET_KEY is missing, ask the user to configure them. Do not guess or fabricate credentials.
  2. Run the script — Whenever the request needs real-time on-chain data or execution, always run the CLI. Do not answer from model memory alone.
  3. Return stdout — Capture the script's stdout and return it to the user. Light formatting is fine, but do not omit key results (amounts, tx hashes, confirm keys, error messages).
  4. Handle confirmation — If the response includes confirmKey, guide the user to confirm or cancel (see Confirmation Flow below).

Capabilities Overview

Trading Operations

  • Spot Buy/Sell/Swap: Exchange tokens on Base chain
  • DCA: Dollar-cost averaging automation (e.g. "DCA 20u into ETH every day")
  • Limit/Trigger Orders: Execute at target prices or PnL rates
  • RSI Strategy: Conditional trading based on RSI indicators (e.g. "if 1h RSI \x3C 30, buy 100u BTC")
  • Take-Profit / Stop-Loss: Automated risk management via QUERY_ALGO

Reference: references/api.md

Query Operations

  • Balance Query: Single token or all-asset portfolio
  • Token Info & Analysis: Contract details, decimals, analytics
  • Price Query: Real-time prices with 24h change
  • Order Query: Active order list and details
  • TP/SL Order Query: Take-profit/stop-loss order status

Blockchain Assistant

  • Crypto/DeFi domain Q&A and execution guidance
  • Trading plan suggestions on Base chain

Confirmation Flow

Orders usually require risk-control confirmation; small orders (approximately ≤ $10) may skip confirmation. confirmKey is valid for about 10 minutes.

When the response includes confirmKey, ask the user to send one of:

yes, please execute \x3CconfirmKey>
no, please cancel \x3CconfirmKey>

If the key has expired, the user must submit the original request again.

Current Limitations

Limitation Details
Chain Base only
Multiple trades One trade per message; ask user to split if needed
Not supported Leverage/futures/options, lending, cross-chain, NFT, fiat on/off-ramp

Common Patterns

Check Before Trading

# Check balance
python skills/axelrod/scripts/axelrod_chat.py --message "check my ETH balance"

# Check price
python skills/axelrod/scripts/axelrod_chat.py --message "what is ETH price now"

# Then trade
python skills/axelrod/scripts/axelrod_chat.py --message "buy 50u of ETH"

Automated Strategies

# DCA strategy
python skills/axelrod/scripts/axelrod_chat.py --message "DCA 20u into ETH every day"

# RSI conditional strategy
python skills/axelrod/scripts/axelrod_chat.py --message "if 1h RSI \x3C 30, buy 100u BTC"

# Limit order
python skills/axelrod/scripts/axelrod_chat.py --message "buy ETH when price drops to 2500"

Portfolio Review

# Full portfolio
python skills/axelrod/scripts/axelrod_chat.py --message "check my balance"

# Token analysis
python skills/axelrod/scripts/axelrod_chat.py --message "analyze AXR token for me"

# Order status
python skills/axelrod/scripts/axelrod_chat.py --message "show my recent orders"

Error Handling

Exit Codes

Code Meaning Resolution
0 Success
2 Missing AK/SK Ask user to configure AIXVC_ACCESS_KEY and AIXVC_SECRET_KEY
3 HTTP failure or invalid/non-JSON response Check network, verify endpoint is reachable
4 API business error (code not in success set) Read the error message, guide user to fix

Common Issues

Issue Resolution
"Please login first" AK/SK is incorrect — reconfigure credentials
Authentication error Verify AK/SK are correct and not expired
Insufficient balance Reduce trade amount or add funds
Token not found Check token symbol or contract address
confirmKey expired Re-submit the original trade request
Multiple trades in one message Split into separate requests

Prompt Examples by Category

Trading

  • "buy 50u of AXR"
  • "sell 50% of my ETH"
  • "swap 10 SOL to ETH"

Automated Strategies

  • "DCA 20u into ETH every day"
  • "if 1h RSI \x3C 30, buy 100u BTC"
  • "buy ETH when price drops to 2500"

Portfolio & Queries

  • "check my balance"
  • "show AXR token info"
  • "what is ETH price now"
  • "show my recent orders"
  • "show my TP/SL orders"

Blockchain Assistant

  • "analyze AXR token for me"
  • "help me make a Base trading plan"

Best Practices

Security

  1. Never share your AK/SK credentials
  2. Start with small test amounts
  3. Verify token addresses before large trades
  4. Review confirmation details carefully before executing

Trading

  1. Check balance before trades
  2. Specify amounts clearly (50u, 50%, 0.1 ETH)
  3. Start small, scale up after validation
  4. Use limit orders for better entry prices
  5. Set TP/SL for risk management

API Reference

For the full API contract, SigV4 signing protocol, request/response format, and response field details, see:

Reference: references/api.md

Implementation Notes

  • The script uses AK/SK with SigV4-style signing to call the AIxVC.
  • Current endpoint: https://api.aixvc.io/gw/openapi/v2/public/twa/agent/chat (chain-id=base).
  • If documentation conflicts with code behavior, follow the script implementation.

File Structure

  • SKILL.md — Agent instructions (this file). The agent reads this to understand how to use the skill.
  • README.md — Human-facing setup and usage guide.
  • scripts/axelrod_chat.py — CLI client. Always invoke with python skills/axelrod/scripts/axelrod_chat.py --message "\x3Cinstruction>".
  • references/api.md — Full API contract and signing reference.
  • requirements.txt — Python dependencies (requests).

Troubleshooting

Script Not Working

# Ensure Python 3 is available
python --version

# Install dependencies
pip install -r skills/axelrod/requirements.txt

# Test connectivity
curl -I https://api.aixvc.io

API Errors

See exit codes and common issues tables above. If an error persists:

  1. Check the error message from stderr
  2. Use --json mode to inspect the full API response
  3. Verify AK/SK configuration
  4. Test with a simple query first ("check my balance")

💡 Pro Tip: The most common issue is missing or incorrect AK/SK. Always verify credentials first when encountering errors.

⚠️ Security: Keep your AK/SK private. Never commit credentials to version control. Only trade amounts you can afford to lose.

🚀 Quick Win: Start by checking your balance to verify setup, then try a small trade like "buy 1u of ETH" to get familiar with the flow.

安全使用建议
Before installing: 1) Note the registry metadata is incomplete — the skill requires AIXVC_ACCESS_KEY and AIXVC_SECRET_KEY even though the registry lists none. Treat that as a red flag and confirm with the publisher. 2) Verify you trust the external endpoint (https://api.aixvc.io). Ask for an official homepage, docs, or publisher identity; do not use production funds until you confirm provenance. 3) Prefer injecting AK/SK via a secure secret store or environment variables rather than committing them into a plaintext OpenClaw config file. 4) Review the script (scripts/axelrod_chat.py) yourself — it performs SigV4-style signing and sends your requests; ensure it does not log secrets (it doesn't explicitly), and run it in a safe/test environment first. 5) Test with minimal amounts and monitor network traffic while exercising the CLI to confirm it only communicates with expected endpoints. If the publisher cannot explain the metadata mismatch and provide trustworthy source/homepage, consider not installing the skill.
功能分析
Type: OpenClaw Skill Name: axelrod Version: 0.1.0 The skill bundle is designed for AI-powered crypto trading and on-chain queries on the Base chain via the AIxVC API. The `scripts/axelrod_chat.py` script securely interacts with a fixed external endpoint (`https://api.aixvc.io/gw`) using AWS SigV4-style signing with API keys (`AIXVC_ACCESS_KEY`, `AIXVC_SECRET_KEY`) retrieved from environment variables. Crucially, the `SKILL.md` instructions and the script itself implement a mandatory confirmation flow for trading operations, requiring explicit user approval via a `confirmKey` before execution. There is no evidence of data exfiltration to unauthorized endpoints, malicious local command execution, obfuscation, or prompt injection attempts against the agent to bypass security controls or perform actions outside the stated purpose.
能力评估
Purpose & Capability
The skill's code, README, references/api.md, and SKILL.md all require AIXVC_ACCESS_KEY and AIXVC_SECRET_KEY and perform SigV4-style signed requests to https://api.aixvc.io/gw for Base-chain trading. However, the registry metadata lists no required environment variables or primary credential. That inconsistency is meaningful: a trading skill legitimately needs AK/SK, so the registry record is incomplete/misleading.
Instruction Scope
The SKILL.md instructions are focused on the stated purpose: always run scripts/axelrod_chat.py for real-time queries/trades, configure AK/SK in OpenClaw config, and return the CLI stdout (including confirmKey flow). The instructions do not ask the agent to read unrelated system files. They do instruct storing credentials in the OpenClaw config under skills.entries.axelrod.env (which is expected but has security implications noted below).
Install Mechanism
This is an instruction-only skill with one Python script and a requirements.txt (requests). There is no opaque download/install step. The only installation step is 'pip install -r requirements.txt' which is proportionate to the Python CLI.
Credentials
The script legitimately requires two secrets (AIXVC_ACCESS_KEY, AIXVC_SECRET_KEY) for signing requests. That is proportionate for a gateway-authenticated trading client — but the registry metadata does not declare those env vars or a primary credential, which is misleading and could result in the platform not prompting the user to supply or protect those secrets. Additionally, SKILL.md advises storing keys in OpenClaw config; persisting AK/SK in plaintext config increases exposure unless the user uses a protected secret store.
Persistence & Privilege
The skill does not request 'always: true' and is user-invocable only. It does not modify other skills or system-wide settings. The README instructs adding the skill directory to OpenClaw config, which is normal for third-party skills.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install axelrod
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /axelrod 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.0
Initial release of the Axelrod skill for AI-powered Base-chain crypto trading and on-chain queries. - Supports buy/sell/swap of Base-chain tokens, portfolio balance checks, token price queries, and order management via natural language. - Enables automated trading strategies such as DCA, limit orders, RSI-based trades, and take-profit/stop-loss management. - Requires real-time results by invoking scripts/axelrod_chat.py for each user request. - Built-in support for order confirmation flow and error handling, including credential checks and transaction status feedback. - Focuses on Base chain only; one trade per message; does not support leveraged products, lending, or cross-chain features.
元数据
Slug axelrod
版本 0.1.0
许可证
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Axelrod 是什么?

AI-powered Base-chain trading and on-chain query agent via natural language. Use when the user wants to trade crypto (buy/sell/swap tokens), set up automated strategies (DCA, limit orders, RSI), check portfolio balances, view token prices, query token info/analysis, check order status, manage take-profit/stop-loss orders, or ask about crypto/DeFi topics on Base chain. Always run scripts/axelrod_chat.py to fetch real-time results. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 783 次。

如何安装 Axelrod?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install axelrod」即可一键安装,无需额外配置。

Axelrod 是免费的吗?

是的,Axelrod 完全免费(开源免费),可自由下载、安装和使用。

Axelrod 支持哪些平台?

Axelrod 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Axelrod?

由 aixvcteam(@aixvcteam)开发并维护,当前版本 v0.1.0。

💬 留言讨论