Back to Details

kryptogo-meme-trader

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

KryptoGO Meme Trader Agent Skill

KryptoGO 模因币交易Agent Skill

Overview

概述

This skill enables an AI agent to analyze and trade meme coins through the KryptoGO platform, combining deep on-chain cluster analysis with trade execution.
Analysis (multi-chain: Solana, BSC, Base, Monad): wallet clustering, accumulation/distribution detection, address behavior labels, network-wide accumulation signals (Pro/Alpha tier).
Trading (Solana only): portfolio monitoring with PnL tracking, swap execution via DEX aggregator, local transaction signing (private key never leaves the machine).
Default mode is supervised — all trades require user confirmation. Autonomous trading is available as opt-in. See 
references/autonomous-trading.md
for autonomous mode, cron setup, and learning system details.
本Skill支持AI Agent通过KryptoGO平台分析和交易模因币，将深度链上集群分析与交易执行相结合。
分析功能（多链支持：Solana、BSC、Base、Monad）：钱包聚类、筹码收集/派发检测、地址行为标签、全网络筹码收集信号（Pro/Alpha层级）。
交易功能（仅支持Solana）：投资组合监控与盈亏追踪、通过DEX聚合器执行兑换、本地交易签名（私钥绝不会离开设备）。
默认模式为监督模式 — 所有交易都需要用户确认。自主交易为可选开启功能。有关自主模式、定时任务设置和学习系统的详细信息，请参阅
references/autonomous-trading.md
。

When to Use

适用场景

  • User asks to analyze a meme coin or token on Solana/BSC/Base/Monad
  • User asks to trade, buy, or sell tokens
  • User asks to scan for trending tokens or market opportunities
  • User asks to monitor portfolio positions or check PnL
  • Cron-triggered periodic portfolio monitoring and signal scanning
  • 用户要求分析Solana/BSC/Base/Monad链上的模因币或代币
  • 用户要求进行交易、买入或卖出代币
  • 用户要求扫描热门代币或市场机会
  • 用户要求监控投资组合仓位或查看盈亏
  • 定时任务触发的周期性投资组合监控和信号扫描

When NOT to Use

不适用场景

  • BTC/ETH/major L1 macro analysis, NFTs, cross-chain bridging, non-DEX transactions, non-Solana trading
  • BTC/ETH等主流Layer1公链的宏观分析、NFT、跨链桥接、非DEX交易、非Solana链上交易

Setup Flow

设置流程

1. Get API Key

1. 获取API Key

  1. Go to kryptogo.xyz/account and create an API key
  2. Add to 
    ~/.openclaw/workspace/.env
    :
    bash
    echo 'KRYPTOGO_API_KEY=sk_live_YOUR_KEY' >> ~/.openclaw/workspace/.env && chmod 600 ~/.openclaw/workspace/.env
Do NOT paste your API key directly in chat. Always set secrets via 
.env
file.
  1. 访问kryptogo.xyz/account并创建API Key
  2. 将其添加到
    ~/.openclaw/workspace/.env
    文件中：
    bash
    echo 'KRYPTOGO_API_KEY=sk_live_YOUR_KEY' >> ~/.openclaw/workspace/.env && chmod 600 ~/.openclaw/workspace/.env
请勿直接在聊天中粘贴API Key。请始终通过
.env
文件设置密钥。

2. Generate Agent Wallet

2. 生成Agent钱包

bash
python3 scripts/setup.py
Creates a Solana keypair, saves to 
.env
with chmod 600, prints public address to fund.
bash
python3 scripts/setup.py
此命令将创建Solana密钥对，保存到
.env
文件并设置权限为600，同时打印需要充值的钱包公钥。

3. Fund the Wallet

3. 为钱包充值

Send SOL to the agent's public address (minimum 0.1 SOL).
向Agent的钱包公钥发送SOL（最低0.1 SOL）。

Security Rules

安全规则

  • NEVER print, log, or include private keys in any message or CLI argument
  • NEVER accept secrets pasted directly in chat — instruct users to set them in 
    .env
  • NEVER use the Read tool on 
    .env
    — load credentials via 
    source
    command only
  • Runtime scripts do NOT read 
    .env
    directly — all credentials are accessed via environment variables only, which must be pre-loaded by the caller (
    source ~/.openclaw/workspace/.env
    )
  • Exception: 
    scripts/setup.py
    reads and writes 
    .env
    for initial keypair generation and address repair — this is the only script that touches credential files
  • Private key stays in memory only during local signing — never sent to any server
  • 绝对不要打印、记录或在任何消息或CLI参数中包含私钥
  • 绝对不要接受直接粘贴在聊天中的密钥 — 指导用户在
    .env
    文件中设置
  • 绝对不要使用读取工具访问
    .env
    文件 — 仅通过
    source
    命令加载凭证
  • 运行时脚本不会直接读取
    .env
    文件 — 所有凭证仅通过环境变量访问，且必须由调用者预先加载（
    source ~/.openclaw/workspace/.env
    ）
  • 例外情况：
    scripts/setup.py
    会读取和写入
    .env
    文件以生成初始密钥对和修复地址 — 这是唯一会接触凭证文件的脚本
  • 私钥仅在本地签名时保留在内存中 — 绝不会发送到任何服务器

Authentication

认证信息

All endpoints require: 
Authorization: Bearer sk_live_<48 hex chars>
TierDaily API CallsTrading FeeSignal DashboardKOL Finder
Free100 calls/day1%NoNo
Pro1,000 calls/day0.5%YesYes
Alpha5,000 calls/day0%YesYes
所有接口都需要携带：
Authorization: Bearer sk_live_<48位十六进制字符>
层级每日API调用次数交易手续费信号仪表盘KOL查找工具
免费版100次/天1%无无
Pro版1000次/天0.5%有有
Alpha版5000次/天0%有有

Agent Behavior

Agent行为规范

Session Initialization

会话初始化

On every session start (including heartbeat/cron), the agent MUST load credentials BEFORE running any scripts:
bash
source ~/.openclaw/workspace/.env
This is REQUIRED — scripts do not read 
.env
directly. All credentials are accessed via environment variables only.
在每次会话启动时（包括心跳/定时任务），Agent必须在运行任何脚本之前加载凭证：
bash
source ~/.openclaw/workspace/.env
这是必须执行的步骤 — 脚本不会直接读取
.env
文件。所有凭证仅通过环境变量访问。

Default Mode: Supervised

默认模式：监督模式

By default, the agent operates in supervised mode: it analyzes tokens, presents recommendations, and waits for user approval before executing any trade. Stop-loss/take-profit conditions are reported to the user but not auto-executed.
To enable autonomous trading, set 
require_trade_confirmation: false
in preferences. See 
references/autonomous-trading.md
for full details.
默认情况下，Agent运行在监督模式：它会分析代币、给出建议，并在执行任何交易前等待用户批准。止损/止盈条件会告知用户，但不会自动执行。
要启用自主交易，请在偏好设置中设置
require_trade_confirmation: false
。详细信息请参阅
references/autonomous-trading.md
。

Persistence (CRITICAL)

状态持久化（至关重要）

IMMEDIATELY after submitting a transaction, the agent MUST:
  1. Write trade details to 
    memory/trading-journal.json
    with 
    status: "OPEN"
  2. Include: 
    token_symbol
    , 
    token_address
    , 
    entry_price
    , 
    position_size_sol
    , 
    tx_hash
    , 
    timestamp
提交交易后必须立即执行以下操作：
  1. 将交易详情写入
    memory/trading-journal.json
    ，并标记
    status: "OPEN"
  2. 需包含的字段：
    token_symbol
    、
    token_address
    、
    entry_price
    、
    position_size_sol
    、
    tx_hash
    、
    timestamp

User Preferences

用户偏好设置

Store in 
memory/trading-preferences.json
:
PreferenceDefaultDescription
max_position_size
0.1 SOLMax SOL per trade
max_open_positions
5Max concurrent open positions
max_daily_trades
20Max trades per day
stop_loss_pct
30%Notify/sell when loss exceeds this
take_profit_pct
100%Notify/sell when gain exceeds this
min_market_cap
$500KSkip tokens below this
scan_count
10Trending tokens per scan
risk_tolerance
"conservative""conservative" (skip medium risk), "moderate" (ask on medium), "aggressive" (auto-trade medium)
require_trade_confirmation
trueSet to false for autonomous mode
chains
["solana"]Chains to scan
存储在
memory/trading-preferences.json
中：
偏好项默认值描述
max_position_size
0.1 SOL单笔交易最大SOL金额
max_open_positions
5最大并发持仓数量
max_daily_trades
20每日最大交易次数
stop_loss_pct
30%亏损超过此比例时通知/卖出
take_profit_pct
100%盈利超过此比例时通知/卖出
min_market_cap
$500K跳过市值低于此值的代币
scan_count
10每次扫描返回的热门代币数量
risk_tolerance
"conservative""conservative"（跳过中等风险）、"moderate"（中等风险需询问用户）、"aggressive"（自动交易中等风险代币）
require_trade_confirmation
true设置为false以启用自主模式
chains
["solana"]要扫描的链

Safety Guardrails

安全防护规则

Trading Limits (Hard Caps)

交易限制（硬上限）

LimitDefaultOverridable?
Max single trade0.1 SOLYes, via 
max_position_size
Max concurrent positions5Yes, via 
max_open_positions
Max daily trade count20Yes, via 
max_daily_trades
Price impact abort>10%No — always abort
Price impact warn>5%No — always warn
If any limit is hit, the agent must stop and notify the user.
限制项默认值是否可覆盖
单笔交易最大金额0.1 SOL是，通过
max_position_size
设置
最大并发持仓数量5是，通过
max_open_positions
设置
每日最大交易次数20是，通过
max_daily_trades
设置
价格影响超过阈值则终止>10%否 — 始终终止
价格影响超过阈值则警告>5%否 — 始终警告
如果触发任何限制，Agent必须停止操作并通知用户。

Credential Isolation

凭证隔离

Runtime scripts in this skill do NOT read 
.env
files directly. All credentials are accessed via environment variables only, which must be pre-loaded by the caller (
source ~/.openclaw/workspace/.env
). This ensures no runtime script can independently access or exfiltrate credential files.
Exception: 
scripts/setup.py
reads and writes 
.env
— it loads existing keys to avoid regeneration, backs up 
.env
before changes, and writes new keypair entries. This is the only script that touches credential files, and it runs only during initial setup or explicit 
--force
regeneration.
本Skill中的运行时脚本不会直接读取
.env
文件。所有凭证仅通过环境变量访问，且必须由调用者预先加载（
source ~/.openclaw/workspace/.env
）。这确保了没有运行时脚本可以独立访问或泄露凭证文件。
例外情况：
scripts/setup.py
会读取和写入
.env
文件 — 它会加载现有密钥以避免重复生成，在修改前备份
.env
文件，并写入新的密钥对条目。这是唯一会接触凭证文件的脚本，且仅在初始设置或显式使用
--force
参数重新生成时运行。

Automated Monitoring (Cron)

自动化监控（定时任务）

Quick Setup

快速设置

bash
undefined
bash
undefined

Supervised mode (default): analysis + notifications, no auto-execution

监督模式（默认）：分析+通知，不自动执行交易

source ~/.openclaw/workspace/.env && bash scripts/cron-examples.sh setup-default
source ~/.openclaw/workspace/.env && bash scripts/cron-examples.sh setup-default

Autonomous mode (opt-in): auto-buys and auto-sells

自主模式（可选）：自动买入和自动卖出

source ~/.openclaw/workspace/.env && bash scripts/cron-examples.sh setup-autonomous
source ~/.openclaw/workspace/.env && bash scripts/cron-examples.sh setup-autonomous

Remove all cron jobs

删除所有定时任务

bash scripts/cron-examples.sh teardown

| Job | Interval | Default Behavior |
|-----|----------|---------|
| `stop-loss-tp` | 5 min | Report triggered conditions, do NOT auto-sell |
| `discovery-scan` | 1 hour | Analyze and send recommendations, do NOT auto-buy |

For full cron configuration, manual setup, heartbeat alternative, and monitoring workflow details, see `references/autonomous-trading.md`.

---
bash scripts/cron-examples.sh teardown

| 任务 | 执行间隔 | 默认行为 |
|-----|----------|---------|
| `stop-loss-tp` | 5分钟 | 报告触发的条件，**不**自动卖出 |
| `discovery-scan` | 1小时 | 分析并发送建议，**不**自动买入 |

有关定时任务的完整配置、手动设置、心跳替代方案和监控工作流的详细信息，请参阅`references/autonomous-trading.md`。

---

On-Chain Analysis Framework (7-Step Pipeline)

链上分析框架（7步流程）

Step 1: Token Overview & Market Cap Filter

步骤1：代币概览与市值过滤

/token-overview?address=<mint>&chain_id=<id>
— get name, price, market cap, holders, risk_level. Skip if market cap < 
min_market_cap
.
/token-overview?address=<mint>&chain_id=<id>
— 获取代币名称、价格、市值、持有者数量、风险等级。如果市值低于
min_market_cap
则跳过该代币。

Step 2: Cluster Analysis

步骤2：集群分析

/analyze/<mint>?chain_id=<id>
— wallet clusters, top holders, metadata.
  • ≥30-35% = "controlled" — major entity present
  • ≥50% = high concentration risk
  • Single cluster >50% → skip (rug pull risk)
Free tier limitation: Cluster analysis only returns the top 2 clusters. To see full cluster data, upgrade at kryptogo.xyz/pricing.
/analyze/<mint>?chain_id=<id>
— 钱包集群、顶级持有者、元数据。
  • ≥30-35% = "受控" — 存在主要实体
  • ≥50% = 高集中度风险
  • 单个集群占比>50% → 跳过（存在rug pull风险）
免费版限制：集群分析仅返回前2个集群。如需查看完整集群数据，请访问kryptogo.xyz/pricing升级。

Step 3: Cluster Trend (Multi-Timeframe)

步骤3：集群趋势（多时间维度）

/analyze-cluster-change/<mint>
— 
cluster_ratio
+ 
changes
across 15m/1h/4h/1d/7d.
Core insight: Price and cluster holdings DIVERGING is the key signal.
  • Rising price + falling cluster % = distribution (bearish)
  • Falling price + rising cluster % = accumulation (bullish)
/analyze-cluster-change/<mint>
— 获取
cluster_ratio
以及15分钟/1小时/4小时/1天/7天的
changes
数据。
核心洞察：价格与集群持仓出现背离是关键信号。
  • 价格上涨 + 集群占比下降 = 筹码派发（看空）
  • 价格下跌 + 集群占比上升 = 筹码收集（看多）

Step 4: Address Labels + Sell Pressure Verification

步骤4：地址标签 + 抛压验证

  1. /token-wallet-labels
    → identify dev/sniper/bundle wallets
  2. /balance-history
    for each risky address → check if still holding
  3. Compute 
    risky_ratio
    = active risky holdings / total cluster holdings
  4. 30% = high risk, 10-30% = medium, <10% = low
Labels represent behavioral history, not current holdings. Always verify via 
/balance-history
.
  1. /token-wallet-labels
    → 识别开发者/抢跑/批量钱包
  2. 为每个高风险地址调用
    /balance-history
    → 检查是否仍持有代币
  3. 计算
    risky_ratio
    = 活跃高风险持仓 / 总集群持仓
  4. 30% = 高风险，10-30% = 中等风险，<10% = 低风险
标签代表历史行为，而非当前持仓。请始终通过
/balance-history
验证。

Step 5: Deep Dive (Optional)

步骤5：深度分析（可选）

/balance-history
, 
/balance-increase/<mint>
, 
/top-holders-snapshot/<mint>
, 
/analyze-dca-limit-orders/<mint>
, 
/cluster-wallet-connections
可调用接口：
/balance-history
、
/balance-increase/<mint>
、
/top-holders-snapshot/<mint>
、
/analyze-dca-limit-orders/<mint>
、
/cluster-wallet-connections

Step 6: Decision

步骤6：决策

Apply Bullish Checklist from 
references/decision-framework.md
.
应用
references/decision-framework.md
中的看多 checklist。

Step 7: Execute Trade

步骤7：执行交易

Use 
scripts/swap.py
for execution — handles wallet_address injection, error checking, and journal logging.
bash
source ~/.openclaw/workspace/.env && python3 scripts/swap.py <token_mint> 0.1
source ~/.openclaw/workspace/.env && python3 scripts/swap.py <token_mint> <amount> --sell
使用
scripts/swap.py
执行交易 — 该脚本处理钱包地址注入、错误检查和日志记录。
bash
source ~/.openclaw/workspace/.env && python3 scripts/swap.py <token_mint> 0.1
source ~/.openclaw/workspace/.env && python3 scripts/swap.py <token_mint> <amount> --sell

API Quick Reference

API快速参考

EndpointMethodPurpose
/agent/account
GETCheck tier & quota
/agent/trending-tokens
GETScan trending tokens
/agent/portfolio
GETWallet portfolio + PnL
/agent/swap
POSTBuild unsigned swap tx (Solana only)
/agent/submit
POSTSubmit signed tx (Solana only)
/token-overview
GETToken metadata & market data
/analyze/:token_mint
GETFull cluster analysis
/analyze-cluster-change/:token_mint
GETCluster ratio trends
/balance-history
POSTTime-series balance data
/wallet-labels
POSTBehavior labels
/token-wallet-labels
POSTToken-specific labels
/signal-dashboard
GETCurated accumulation signals (Pro+)
Full request/response details: see 
references/api-reference.md
接口请求方法用途
/agent/account
GET检查层级与配额
/agent/trending-tokens
GET扫描热门代币
/agent/portfolio
GET钱包投资组合+盈亏
/agent/swap
POST构建未签名的兑换交易（仅Solana）
/agent/submit
POST提交已签名的交易（仅Solana）
/token-overview
GET代币元数据与市场数据
/analyze/:token_mint
GET完整集群分析
/analyze-cluster-change/:token_mint
GET集群占比趋势
/balance-history
POST时间序列余额数据
/wallet-labels
POST行为标签
/token-wallet-labels
POST代币专属标签
/signal-dashboard
GET精选筹码收集信号（Pro+层级可用）
完整请求/响应详情：请参阅
references/api-reference.md

Multi-Chain Support

多链支持

Chainchain_idAnalysisTrading
Solana
501
YesYes
BSC
56
YesNo
Base
8453
YesNo
Monad
143
YesNo
链chain_id分析功能交易功能
Solana
501
支持支持
BSC
56
支持不支持
Base
8453
支持不支持
Monad
143
支持不支持

Error Handling

错误处理

CodeMeaningAction
400Bad RequestCheck parameters
401UnauthorizedCheck API key
402Quota ExceededWait for daily reset or upgrade
403ForbiddenRequires higher tier
502/504Server errorRetry once after 10s
错误码含义操作
400请求参数错误'检查参数
401未授权检查API Key
402配额用尽等待每日重置或升级层级
403禁止访问需要更高层级权限
502/504服务器错误10秒后重试一次

Operational Scripts

操作脚本

All scripts require credentials to be pre-loaded: 
source ~/.openclaw/workspace/.env
before running.
bash
source ~/.openclaw/workspace/.env && bash scripts/portfolio.sh              # Portfolio check
source ~/.openclaw/workspace/.env && bash scripts/trending.sh               # Trending tokens
source ~/.openclaw/workspace/.env && bash scripts/analysis.sh               # Full analysis dashboard
source ~/.openclaw/workspace/.env && python3 scripts/swap.py <mint> 0.1     # Buy
source ~/.openclaw/workspace/.env && python3 scripts/swap.py <mint> <amt> --sell  # Sell
source ~/.openclaw/workspace/.env && bash scripts/test-api.sh               # API connectivity test
所有脚本都需要预先加载凭证：运行前执行
source ~/.openclaw/workspace/.env
bash
source ~/.openclaw/workspace/.env && bash scripts/portfolio.sh              # 查看投资组合
source ~/.openclaw/workspace/.env && bash scripts/trending.sh               # 查看热门代币
source ~/.openclaw/workspace/.env && bash scripts/analysis.sh               # 查看完整分析仪表盘
source ~/.openclaw/workspace/.env && python3 scripts/swap.py <mint> 0.1     # 买入
source ~/.openclaw/workspace/.env && python3 scripts/swap.py <mint> <amt> --sell  # 卖出
source ~/.openclaw/workspace/.env && bash scripts/test-api.sh               # API连通性测试

Learning & Adaptation

学习与自适应

The agent improves over time by recording trades, analyzing outcomes, and adjusting strategy. Every trade is logged to 
memory/trading-journal.json
, losses trigger post-mortems, and periodic reviews propose parameter changes.
For full details on the learning system, trade journal format, post-mortem process, and strategy reviews, see 
references/autonomous-trading.md
.
Agent会通过记录交易、分析结果和调整策略来不断改进。每笔交易都会记录到
memory/trading-journal.json
中，亏损会触发事后分析，定期复盘会提出参数调整建议。
有关学习系统、交易日志格式、事后分析流程和策略复盘的详细信息，请参阅
references/autonomous-trading.md
。

Core Concepts

核心概念

ConceptKey Insight
ClusterGroup of wallets controlled by same entity
Cluster Ratio% of supply held by clusters. ≥30% = controlled, ≥50% = high risk
DeveloperDeployed the token. Highest dump risk
SniperBought within 1s of creation. Sell pressure if not cleared
Smart MoneyRealized profit >$100K. Accumulation often precedes price moves
AccumulationCluster % rising + price consolidating = bullish
DistributionPrice rising + cluster % falling = bearish
Full concepts guide: see 
references/concepts.md
概念关键洞察
Cluster（集群）由同一实体控制的钱包组
Cluster Ratio（集群占比）集群持有的供应量占比。≥30% = 受控，≥50% = 高风险
Developer（开发者）部署代币的主体。抛压风险最高
Sniper（抢跑者）代币创建后1秒内买入的地址。若未离场则存在抛压
Smart Money（聪明钱）已实现利润超过$100K的地址。其筹码收集往往预示价格上涨
Accumulation（筹码收集）集群占比上升 + 价格盘整 = 看多
Distribution（筹码派发）价格上涨 + 集群占比下降 = 看空
完整概念指南：请参阅
references/concepts.md

Best Practices

最佳实践

  1. Always check 
    /agent/account
    first to confirm tier and quota
  2. Always check 
    /agent/portfolio
    on startup to detect existing positions
  3. Never expose private keys in logs, messages, or CLI arguments
  4. Validate price impact before submitting — abort >10%, warn >5%
  5. Sign and submit promptly — blockhash expires after ~60 seconds
  6. Persist state to 
    memory/trading-state.json
    after every action
  7. Log every trade to journal — no exceptions
  8. Read 
    memory/trading-lessons.md
    before scanning — avoid repeating known bad patterns
  1. 始终先调用
    /agent/account
    确认层级和配额
  2. 会话启动时始终调用
    /agent/portfolio
    检测现有持仓
  3. 绝不在日志、消息或CLI参数中暴露私钥
  4. 提交交易前验证价格影响 — 超过10%则终止，超过5%则警告
  5. 及时签名并提交交易 — blockhash约60秒后过期
  6. 每次操作后将状态持久化到
    memory/trading-state.json
  7. 每笔交易都要记录到日志中 — 无例外
  8. 扫描前阅读
    memory/trading-lessons.md
    — 避免重复已知的错误模式

File Structure

文件结构

kryptogo-meme-trader/
├── SKILL.md                       ← You are here
├── package.json
├── .env.example
├── references/
│   ├── api-reference.md           ← Full API docs
│   ├── concepts.md                ← Core concepts
│   ├── decision-framework.md      ← Entry/exit strategies
│   └── autonomous-trading.md      ← Autonomous mode, cron, learning system
├── scripts/
│   ├── setup.py                   ← First-time setup
│   ├── cron-examples.sh           ← Cron configurations
│   ├── portfolio.sh / trending.sh / analysis.sh / test-api.sh
│   ├── swap.py                    ← Swap executor
│   └── trading-preferences.example.json
└── examples/
    ├── trading-workflow.py
    └── deep-analysis-workflow.py
kryptogo-meme-trader/
├── SKILL.md                       ← 当前文件
├── package.json
├── .env.example
├── references/
│   ├── api-reference.md           ← 完整API文档
│   ├── concepts.md                ← 核心概念
│   ├── decision-framework.md      ← 入场/离场策略
│   └── autonomous-trading.md      ← 自主模式、定时任务、学习系统
├── scripts/
│   ├── setup.py                   ← 首次设置
│   ├── cron-examples.sh           ← 定时任务配置
│   ├── portfolio.sh / trending.sh / analysis.sh / test-api.sh
│   ├── swap.py                    ← 兑换执行脚本
│   └── trading-preferences.example.json
└── examples/
    ├── trading-workflow.py
    └── deep-analysis-workflow.py