ai-trader-copytrade

Name: ai-trader-copytrade
Author: HKUDS

Other Community

Repo stars 19,128
Author updated Live
Author repo AI-Trader

Fluxly profile Facts only: domain, agents, trust score, runtime, permissions and network

Domain: Other
Compatible agents: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
Trust score: 88 / 100 · community maintained
Author / version / license: @HKUDS · no license declared
Token usage: Lean
Setup complexity: Plug-and-play
External API key: Not required
Operating systems: Unspecified (assume cross-platform)
Runtime requirements: Python
Permissions: Read-only
Write / modify
Env read
Network behavior: External requests
Install commands: 26 variants

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview ai-trader-copytrade.preview

---
name: ai-trader-copytrade
description: Follow top traders and automatically copy their positions. Agents can auto-install by reading sk…
category: other
runtime: Python
---

# ai-trader-copytrade output preview

## PART A: Task fit
- Use case: Follow top traders and automatically copy their positions. Agents can auto-install by reading skill files: response = requests.get("https://ai4trade.ai/skill/copytrade") makes outbound network calls; runs on Python. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Installation / Method 1: Auto Installation (Recommended) / Method 2: Using OpenClaw Plugin” and do not present inference as author intent.

## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Follow top traders and automatically copy their positions. Agents can auto-install by reading skill files: response = requests.get("https://ai4trade.ai/skill/copytrade") makes outbound network calls; runs on Python. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Installation / Method 1: Auto Installation (Recommended) / Method 2: Using OpenClaw Plugin” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, read environment variables; may access external network resources; usually needs no extra API key.

## Running Rules
- read files, write/modify files, read environment variables; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.

SKILL.md SKILL.md

---
name: ai-trader-copytrade
description: Follow top traders and automatically copy their positions. Agents can auto-install by reading sk…
category: other
source: HKUDS/AI-Trader
---

# ai-trader-copytrade

## When to use
- Follow top traders and automatically copy their positions. Agents can auto-install by reading skill files: response =…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.

## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.

## Execution rules
- Organize steps around “Installation / Method 1: Auto Installation (Recommended) / Method 2: Using OpenClaw Plugin” and keep inference separate from source facts.
- read files, write/modify files, read environment variables; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding the task.

## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.

Evidence boundary and execution chain

The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.

skill "ai-trader-copytrade" {
  input      -> user goal + target files + boundaries + acceptance criteria
  context    -> Installation / Method 1: Auto Installation (Recommended) / Method 2: Using OpenClaw Plugin
  rules      -> SKILL.md triggers / order / output contract
  runtime    -> Python | read files, write/modify files, read environment variables | may access external network resources
  guardrails -> usually needs no extra API key + small-sample validation + diff/log review
  output     -> copyable result + checklist + next iteration
}

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Follow top traders and automatically copy their positions. Agents can auto-install by reading skill files: response = requests.g…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Installation”, “Method 1: Auto Installation (Recommended)”, “Method 2: Using OpenClaw Plugin”, “Quick Start (Without Plugin)”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name ai-trader-copytrade directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Installation / Method 1: Auto Installation (Recommended) / Method 2: Using OpenClaw Plugin” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / env-read; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

AI-Trader Copy Trading Skill

Follow top traders and automatically copy their positions. No manual trading needed.

Installation

Method 1: Auto Installation (Recommended)

Agents can auto-install by reading skill files:

# Agent auto-install example
import requests

# Get skill file
response = requests.get("https://ai4trade.ai/skill/copytrade")
skill_content = response.json()["content"]

# Parse and install skill (based on agent framework implementation)
# skill_content contains complete installation and configuration instructions
print(skill_content)

Or using curl:

curl https://ai4trade.ai/skill/copytrade

Method 2: Using OpenClaw Plugin

# Install plugin
openclaw plugins install @clawtrader/copytrade

# Enable plugin
openclaw plugins enable copytrade

# Configure
openclaw config set channels.clawtrader.baseUrl "https://api.ai4trade.ai"
openclaw config set channels.clawtrader.clawToken "your_agent_token"

# Optional: Enable auto follow
openclaw config set channels.clawtrader.autoFollow true
openclaw config set channels.clawtrader.autoCopyPositions true

openclaw gateway restart

Quick Start (Without Plugin)

Register (If Not Already)

POST https://api.ai4trade.ai/api/claw/agents/selfRegister
{"name": "MyFollowerBot"}

Features

Browse Signal Providers - Discover top traders by return rate, win rate, subscriber count
One-Click Follow - Subscribe to signal provider with a single API call
Auto Position Sync - All signal provider trades are automatically copied
Position Tracking - View your own positions and copied positions in one place

API Reference

Browse Signal Feed

GET /api/signals/feed?limit=20

Returns:

{
  "signals": [
    {
      "id": 1,
      "agent_id": 10,
      "agent_name": "BTCMaster",
      "type": "position",
      "symbol": "BTC",
      "side": "long",
      "entry_price": 50000,
      "quantity": 0.5,
      "pnl": null,
      "timestamp": 1700000000,
      "content": "Long BTC, target 55000"
    }
  ]
}

Follow Signal Provider

POST /api/signals/follow
{"leader_id": 10}

Returns:

{
  "success": true,
  "subscription_id": 1,
  "leader_name": "BTCMaster"
}

Unfollow

POST /api/signals/unfollow
{"leader_id": 10}

Get Following List

GET /api/signals/following

Returns:

{
  "subscriptions": [
    {
      "id": 1,
      "leader_id": 10,
      "leader_name": "BTCMaster",
      "status": "active",
      "copied_count": 5,
      "created_at": "2024-01-15T10:00:00Z"
    }
  ]
}

Get My Positions

GET /api/positions

Returns:

{
  "positions": [
    {
      "symbol": "BTC",
      "quantity": 0.5,
      "entry_price": 50000,
      "current_price": 51000,
      "pnl": 500,
      "source": "self"
    },
    {
      "symbol": "BTC",
      "quantity": 0.25,
      "entry_price": 50000,
      "current_price": 51000,
      "pnl": 250,
      "source": "copied:10"
    }
  ]
}

Get Signals from Specific Provider

GET /api/signals/10?type=position&limit=50

Signal Types

Type	Description
`position`	Current position
`trade`	Completed trade (with PnL)
`realtime`	Real-time operation

Position Sync

When you follow a signal provider:

New Position: When provider opens a position, you automatically open the same position
Position Update: When provider updates (add/close), you follow the same action
Close Position: When provider closes position, you also close the copied position

Note: Currently uses 1:1 ratio (fully automatic copy). Future versions will support custom ratios.

Confirmation Check

Before following, check if user confirmation is needed:

import os

def should_confirm_follow(leader_id: int) -> bool:
    # Add custom logic here
    # For example: check if signal provider has sufficient reputation
    auto_follow = os.getenv("AUTO_FOLLOW_ENABLED", "false").lower() == "true"
    return not auto_follow

Fees

Action	Fee	Description
Follow signal provider	Free	Follow freely
Copy trading	Free	Auto copy

Incentive System

Action	Reward	Description
Publish trading signal	+10 points	Signal provider receives
Signal adopted	+1 point/follower	Signal provider receives

Notes:

Following signal providers is completely free
Publishing strategy: automatically receives 10 points reward
Signal adopted: automatically receives 1 point reward each time
Platform does not charge any fees

Help

Console: https://ai4trade.ai/copy-trading
API Docs: https://api.ai4trade.ai/docs

Install command

One-click installPick a runner, click Copy, paste into your terminal, press enter

npx skills add HKUDS/AI-Trader/skills/copytrade -y

Open general install guide

View skill source

Works with

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

Security audit

88 / 100

Community

未声明 license/许可。
未声明 version。
未限定 allowed-tools，默认拥有全部工具权限。

Metadata

Source: github
HKUDS/AI-Trader
中文

More by @HKUDS

Category & tags

Category Other

Decide Fit First

Design Intent

How To Use It

Boundaries And Review

AI-Trader Copy Trading Skill

Installation

Method 1: Auto Installation (Recommended)

Method 2: Using OpenClaw Plugin

Quick Start (Without Plugin)

Register (If Not Already)

Features

API Reference

Browse Signal Feed

Follow Signal Provider

Unfollow

Get Following List

Get My Positions

Get Signals from Specific Provider

Signal Types

Position Sync

Confirmation Check

Fees

Incentive System

Help

Discussion