Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计提醒

autonomous-trading自主交易

Agent Skill

autonomous-trading 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

6,193

周安装

253

GitHub Stars

75

下载量

2,004
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:autonomous-trading(自主交易)
来源仓库:https://github.com/senpi-ai/senpi-skills
仓库路径:skills/autonomous-trading
安装命令:
npx skills add https://github.com/senpi-ai/senpi-skills --skill autonomous-trading
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/senpi-ai/senpi-skills --skill autonomous-trading

简介

自主交易允许 Agent 在设定预算、目标和截止时间后自动进行交易决策与执行。

  • 适用于金融策略模拟、机会扫描、仓位管理与风险控制等自动化交易场景。
  • 依赖多个配套技能协同工作,如动态止损 DSL 和市场扫描模块,形成完整交易闭环。
  • 使用前需确认是否接入真实市场接口,并评估其对资金账户和网络连接的潜在影响。
  • autonomous-trading 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Autonomous Trading v6

Give your agent a budget, a target, and a deadline — then let it trade. The agent creates a strategy wallet, scans for opportunities, opens positions, protects profits with DSL, and enforces risk controls.

Skill Attribution

When creating a strategy, include skill_name and skill_version in the call. See references/skill-attribution.md for details.


Prerequisites

Install these companion skills first:

  1. dsl-dynamic-stop-loss — trailing stops, auto-closing, per-tier retrace
  2. opportunity-scanner — market scanning, scoring, hourly trend gate
  3. emerging-movers — SM rotation detection, IMMEDIATE_MOVER signals

Minimum budget: $500 (recommend $1k+)

Known Bugs & Gotchas

See references/bugs-and-gotchas.md — critical issues from live trading including the dryRun bug, phantom closes, XYZ DEX margin type, Tier 1 lock misconception, and scanner leverage vs actual max.

The Flow

Step 1: Ask the User

Collect: budget, target, deadline, risk tolerance (conservative/moderate/aggressive), asset preferences.

Step 2: Calculate the Playbook

See references/risk-rules.md for complete risk rules by profile.

v6 Core Rules:

The #1 Rule — Hourly Trend Alignment. ALL trades must confirm with hourly candle structure. Counter-trend = hard skip, no exceptions. This single rule prevents the majority of losing trades.

Max Leverage Check. Always check max-leverage.json before entering. Scanner leverage is conservative, not actual max.

Concentration Over Diversification. At small account sizes ($500-$10k), 2-4 high-conviction positions beat 6 mediocre ones. Cross-margin math: 4 positions → 80.6% margin buffer, 2 positions → 89.7%.

Every Slot Must Maximize ROI. Empty slot > mediocre position. If a position isn't working, cut it and free the slot.

Speed Filter. Best moves happen FAST (XRP hit Tier 3 in 19 min, XMR Tier 2 in 37 min). Slow movers are suspects.

Directional Exposure Guard

Before opening, check total LONG vs SHORT notional. Cap at 70% in one direction.

Position Sizing by Score

Scanner ScorePosition Size
250+Up to max per-position
200-25075% of max
175-20050% of max
< 175Skip

Step 3: Create the Strategy

strategy_create_strategy(budgetUsd, leverageType, riskLabel)

Returns strategyId + walletAddress. Fund the wallet.

Step 4: Create the Playbook File

JSON config tracking: risk profile, position limits, score thresholds, active positions, trade journal. See references/playbook-schema.md.

Step 5: Set Up Cron Jobs

Race Condition Prevention (v6 — CRITICAL)

Multiple cron jobs (scanner, SM flip, DSL) can all try to close the same position. When ANY job closes a position:

# 1. Close the position
result = close_position(wallet, asset)

# 2. Immediately deactivate DSL state file
state["active"] = False
save_state(state)

# 3. Disable DSL cron for this asset
disable_cron(f"dsl-{asset}")

All three steps MUST happen in the same action. This prevents phantom closes.

Cron Schedule:

JobIntervalPurpose
Opportunity Scanner10-30 min (time-aware)Find setups
DSL Monitor2-3 min per positionTrailing stops
SM Flip Detector5 minConviction changes
Portfolio Update15 minReporting

See references/cron-setup.md for detailed cron configuration, time-aware scheduling, and SM flip detection logic.

Step 6: The Trading Loop

SCAN → EVALUATE → TRADE → PROTECT → REPEAT

For each scan result:
1. Check hourly trend alignment (HARD REQUIREMENT)
2. Check directional exposure guard
3. Check max leverage via max-leverage.json
4. Score ≥ 175? → Size by score tier
5. Open position → Create DSL state → Start DSL cron
6. Journal the trade (scanner snapshot at entry)

v6: Dead Weight Cutting

ConditionAction
SM conviction drops 4→1 (e.g., 220→24 traders in 10 min)Cut immediately
Dead weight at conviction 0Cut immediately — free the slot
Position stagnant, better opportunity availableRotate

Step 7: Safety Rails

Hard Stops (automatic):

  • Daily loss limit hit → stop trading for the day
  • Total drawdown hard stop → close all positions, alert user
  • DSL breach → auto-close (handled by script)

What the Agent Should NEVER Do:

  • Trade counter-trend on hourly
  • Exceed position size limits
  • Override DSL
  • Average down on a losing position
  • Ignore the directional exposure guard

Step 8: Lessons from the Field

See references/lessons.md for what works, what doesn't, retrace tuning, and fee awareness from live trading.

API Reference

See references/api-tools.md for the key Senpi tools used by this skill.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.3%
按下载量换算707

Claude

28.03%
按下载量换算562

Cursor

18.82%
按下载量换算377

Gemini CLI

8.74%
按下载量换算175

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills