Aicoin Freqtrade

Wraps Freqtrade's entire lifecycle inside CoinClaw containers: strategy creation, backtesting, hyperopt, and live deployment. The main trick here is daemon awareness. OpenClaw, Hermes, and Claude Code all run Freqtrade as a supervisord process on port 8080, so this skill never spawns competing instances. It auto-detects which engine you're in, finds the right config paths, and handles restarts through supervisorctl. Includes a quick strategy generator for common indicators (RSI, MACD, Bollinger) and integrates AiCoin's whale signals, funding rates, and liquidation data into custom Python strategies. Strong on guarding against common mistakes like forgetting to reload config or misreporting P&L by skipping the profit API.

skills.sh installs: 660
GitHub stars: 58
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aicoincom/coinos-skills --skill aicoin-freqtrade --agent claude-code

Installs into .claude/skills of the current project.

Files

AiCoin Freqtrade

Freqtrade 策略 / 回测 / 部署 / 实时控制 — 跨 CoinClaw 三引擎自动适配。

关键原则(读完再动手)

一、CoinClaw 容器里 freqtrade 是常驻 daemon

OpenClaw / Hermes / Claude Code 三个引擎容器都通过 supervisord 把 freqtrade 起为常驻进程, 监听 127.0.0.1:8080, 默认跑 NoOpStrategy(空跑). 不要自己起 freqtrade 进程 — 会跟 daemon 抢端口, dashboard 立刻 offline.

正确流程是: 写策略文件 → 调 ft-deploy.mjs deploy {"strategy":"..."} → 脚本改 config + 重启 daemon. dashboard 会自动刷出新策略.

scripts/ft.mjs + scripts/ft-deploy.mjs 内置三引擎自动识别(lib/coinclaw-env.mjs), 路径 / auth / supervisord socket 都自动解析, agent 不用关心是哪个引擎.

二、永远先调 freqtrade REST API, 不要"自己计算"

用户问	必须先调
现在赚多少 / 总盈亏 / 今天涨了多少	`ft.mjs profit` (`/api/v1/profit`)
持仓 / 现在开了哪些	`ft.mjs trades_open` (`/api/v1/status`)
余额 / 资金多少	`ft.mjs balance` (`/api/v1/balance`)
跑的什么策略 / 当前模式	`ft.mjs daemon_info` 或 `config`
历史交易 / 已平仓	`ft.mjs trades_history`
单交易对绩效	`ft.mjs profit_per_pair`