Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

宝总霸盘Skill — 全市场智能操盘系统

v1.0.0

宝总霸盘Skill — A股/港股/美股全市场智能操盘系统。当用户提到以下任何场景时激活: 股票分析、个股诊断、持仓检查、盘前机会、每日复盘、选股、技术面、基本面、 政策影响、监管动态、研报解读、估值分析、买卖决策、风控检查、回测策略、 量化策略、自选股监控、异动预警、市场情绪、板块轮动、龙虎榜、主力动向、 北向...

0· 54·0 current·0 all-time
bymingyuan@zmy1006-sudo

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for zmy1006-sudo/baozong-trading.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "宝总霸盘Skill — 全市场智能操盘系统" (zmy1006-sudo/baozong-trading) from ClawHub.
Skill page: https://clawhub.ai/zmy1006-sudo/baozong-trading
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install baozong-trading

ClawHub CLI

Package manager switcher

npx clawhub@latest install baozong-trading
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
The skill claims full‑market monitoring, daily scheduled scans, account-level diagnostics and even '强制执行止损' (forced stop‑loss execution). Yet the package declares no required environment variables, no config paths, and no installation hooks for brokerage/data APIs. Legitimately performing these capabilities would normally require credentials (broker/API keys), persistent connectors, or explicit instructions on how trading orders and account reads are performed; those are missing.
!
Instruction Scope
SKILL.md contains detailed runbook-like instructions (daily 8:30 scans, 16:00 replays, account health checks, monitoring/alerts) and refers to collecting account balances and trade records. It does not explain how the agent should obtain that account data (no broker APIs, no file paths, no token names). The instructions also recommend external data sources (Tushare Pro, AKShare, real‑time news) but provide no binding or credential guidance.
Install Mechanism
This is an instruction‑only skill with no install spec and no code files — low surface area for disk writes or arbitrary downloads. That reduces install risk; there is nothing being pulled from third‑party URLs or package registries by the skill itself.
!
Credentials
The SKILL.md explicitly lists Tushare Pro and mentions account/position data access, which normally require API keys and/or broker credentials. However, the skill declares no required env vars, primary credential, or config paths. That mismatch means the skill expects sensitive access but does not state how it will obtain it — a proportionality and transparency concern. If you were to wire it up, you'd need to clarify exactly which keys/tokens are required and whether write (trade) scopes are requested.
Persistence & Privilege
The skill does not request 'always: true' and has no install-time persistence. Autonomous invocation is allowed (default) — this is normal for skills — but because the skill describes recurring tasks (daily scans, alerts), confirm how scheduling/authorization is handled before enabling autonomous runs.
What to consider before installing
This skill reads like a comprehensive trading assistant, but it does not say how it will access account data or send trades. Before installing: (1) Ask the author to document exactly which API keys, broker connectors, or config paths are required and whether any keys need write/trade scope. (2) Never hand over broker credentials or full‑privilege API keys to an untrusted or undocumented skill — prefer read‑only keys and least privilege. (3) Verify where real‑time data will come from (Tushare requires an API token) and whether you must install/configure those subskills separately. (4) If the skill will run autonomously, decide whether you want it to be allowed to act without explicit confirmation; require human approval for any trading actions. (5) If possible, test in a sandbox or with paper‑trading credentials first. Providing those clarifications (explicit required env vars, broker integration details, and trade‑execution gating) would raise confidence and could move this assessment toward benign.

Like a lobster shell, security has layers — review code before you run it.

latestvk97b6gvynge5chtqnctrc7jhdx851z4w
54downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

宝总霸盘Skill — 全市场智能操盘系统

灵感来源:袋鼠帝「金融养虾必装10大Skill」+ cangjie-skill投资思维体系 版本:v1.0.0 | 作者:赵铭远 | 定位:A股/港股/美股统一操盘AI助手


核心理念

"好生意 + 好价格 + 好人性 = 好投资"

三位一体框架:

  • 🧠 思维层:巴菲特/芒格/段永平的投资判断框架
  • 📊 分析层:基本面 × 技术面 × 资金面三维交叉验证
  • ⚡ 执行层:监控/复盘/回测/风控全链路闭环

能力一:思维决策层

1.1 巴菲特安全边际判断

触发条件:评估个股估值、决定买入时机、判断是否高估

判断流程

  1. 计算内在价值(ROE*合理PE法 或 现金流折现)
  2. 计算安全边际 = (内在价值 - 当前价格) / 内在价值 × 100%
  3. 安全边际 ≥ 30% → 可考虑建仓;20-30% → 等待;< 20% → 不符合
  4. 检查护城河:品牌/专利/网络效应/成本优势/转换成本
  5. 管理层诚信度评估

输出模板

【巴菲特安全边际分析】{股票名称} {代码}
━━━━━━━━━━━━━━━━━━
内在价值估算:¥{XX元}
当前价格:¥{XX元}
安全边际:{XX%}
护城河评级:{强/中/弱}
综合判断:{强烈买入/买入/观望/卖出}
⚠️ {风险提示}

1.2 芒格多元思维核查清单

触发条件:重大投资决策前,必须强制逐项输出

□ 数学层:期望值 = 概率 × 赔率,计算了吗?
□ 工程层:物理/供应链是否可实现?
□ 生物层:竞争格局,是否有自然选择压力?
□ 经济层:护城河来源,可持续性?
□ 心理层:我的判断是否受情绪偏差影响?(确认偏误/损失厌恶?)
□ 黑天鹅:最坏情景是什么?能承受吗?
□ 逆向:如果我是空头,如何攻击这只股票?

1.3 段永平"本分"商业逻辑

触发条件:评估商业模式的可持续性

判断标准:

  • ✓ 本分:不坑消费者、不做假账、不走监管擦边
  • ✓ 利润来源:靠产品竞争力,不是靠政策或垄断
  • ✓ 现金流:经营现金流持续为正
  • ✓ 管理层:不吹牛、不蹭热点、专注主业
  • ✓ 用户口碑:产品是否真的值得买

能力二:市场分析层

2.1 盘前机会扫描(每日 8:30 前执行)

触发条件:"今日机会"、"盘前分析"、"开盘前看看"

扫描维度:

  1. 隔夜美股:纳斯达克/标普500/道指涨跌幅,关联中概股ADR
  2. A50期货:A股开盘情绪(高开/低开/平开)
  3. 港股ADR:腾讯/阿里/美团ADR表现
  4. 恐慌贪婪:A股情绪指数参考
  5. 板块异动:昨夜美股热门板块映射
  6. 重要新闻:政策面/宏观面重大消息
  7. 外资动向:北向资金历史趋势

输出模板

【{日期} 盘前机会扫描】
━━━━━━━━━━━━━━━━━━
外盘情绪:{乐观/中性/谨慎}
A50开盘预期:{高开(+X%)/低开(-X%)/平开}
今日关注板块:{1... 2... 3...}
重点关注个股:{代码} {理由}
今日操作建议:{进攻/防守/观望}
⚠️ 风险提示:{若有重大风险事件}

2.2 个股深度分析(三维交叉验证)

触发条件:用户提供股票代码/名称,"分析{股票}"

基本面(价值锚)

  • ROE、毛利率、净利率(3年趋势)
  • 营收增速、净利润增速
  • 资产负债率,经营现金流/净利润比
  • PE/PB/PS 当前值 vs 历史分位数
  • 股息率是否可持续
  • 主流机构综合评级

技术面(择时参考)

  • MA5/MA20/MA60 多头排列 or 空头排列
  • RSI(14) 是否超买>70 or 超卖<30
  • 近30日高低点,关键支撑压力位
  • 成交量:量价配合是否健康
  • MACD:是否出现金叉/死叉

资金面(驱动力)

  • 北向资金近5日净流入/流出
  • 主力资金超大单/大单净流入
  • 是否近期登龙虎榜
  • 融资余额变化趋势

三维综合结论

基本面(价值):{低估/合理/高估}
技术面(择时):{强势/中性/弱势}
资金面(驱动):{净流入/净流出}
综合评级:{★★★★★}
建议操作:{买入区间/止损价/目标价}

2.3 政策影响评估

触发条件:提到政策、监管、文件、会议

评估流程:

  1. 来源定级:最高层(★★★) → 全市场影响;部委级(★★) → 板块影响;地方(★) → 局部
  2. 方向判断:利好板块 / 利空板块 / 中性(规范发展)
  3. 传导链:政策 → 行业 → 龙头公司 → 估值 → 股价
  4. 历史类比:同类政策出台后3个月内市场/板块表现

能力三:执行操作层

3.1 每日复盘(每日 16:00 后执行)

触发条件:"复盘"、"今天怎么样"、"收盘了"

复盘框架:

  1. 账户状况:今日盈亏,持仓涨跌,当日操作记录
  2. 持仓诊断:基本面变化?触发止损?量价健康?
  3. 机会回顾:有无操作机会被错过?
  4. 市场总结:最强板块/最弱板块/情绪指标(涨停跌停数)
  5. 明日计划:关注板块和个股 + 操作预案(高开/低开预案)

3.2 策略回测框架

触发条件:用户提出交易策略(选股条件/止损逻辑/仓位规则)

回测流程:

  1. 策略编码:将定性描述转化为量化条件
  2. 参数定义:回测区间(默认近3年)、手续费(默认0.03%)、滑点(默认0.1%)
  3. 核心指标:总收益率/年化收益率/最大回撤/夏普比率/胜率/盈亏比
  4. 敏感性分析:改变止损幅度/持仓周期后,指标如何变化
  5. 结论:策略有效?主要风险点?需优化什么?

3.3 自选股监控与异动预警

触发条件:"监控{股票}"、"设置提醒"、"盯盘"

监控指标(用户可自定义阈值):

  • 价格异动:单日涨跌超过 ±{X}%
  • 成交量异动:较20日均量放大{X}倍
  • 技术破位:跌破MA60 / 跌破前期低点
  • 资金异动:北向单日净流入超{XX}亿
  • 估值突破:PE达到历史{X}%分位数
  • 止损提醒:价格触及预设止损位

预警推送格式

🔔 【{股票}{代码} 异动提醒】
━━━━━━━━━━━━━━━━━━
异动类型:{类型}
当前价格:¥{XX}(今日{X%})
触发条件:{原设置的监控条件}
建议操作:{根据芒格清单重新评估}
⚠️ 风险提示
时间:{触发时间}

能力四:风控层

4.1 账户健康检查

触发条件:"风控检查"、"账户怎么样"、"看看风险"

检查维度:

  • 总仓位 {XX%} → >80% 为过重,建议减仓
  • 单股仓位 {XX%} → >20% 过于集中
  • 前3大持仓占总仓位 → 超过50%为高风险
  • 单一板块仓位是否超过30%?
  • 小盘股占比是否过高?(大熊市可能无法卖出)
  • 是否有持仓已触发止损但未执行?
  • 持仓股之间是否存在高度相关性?

4.2 止损决策辅助

触发条件:持仓股票下跌,用户犹豫是否止损

决策流程(强制执行):

Step 1: 初始止损 vs 当前亏损
   → 当前亏损 > 初始止损 → 触发止损,强制执行

Step 2: 基本面是否变化?
   → 基本面变差:立即止损
   → 基本面不变:考虑暂时持有观察

Step 3: 芒格清单复查
   → 有无重大误判? → 是:止损并反省

Step 4: 仓位决定
   → 止损后仓位可承受 → 执行止损
   → 止损后空仓 → 等待更好机会

使用示例

# 盘前
"今天有什么机会?"

# 个股分析
"帮我分析贵州茅台"
"腾讯今天怎么看?"

# 策略回测
"我的策略是MA20以上持有,跌破卖出,帮我回测"

# 监控
"帮我监控腾讯00700,跌破400块提醒我"

# 风控
"看看我账户的风险"
"帮我复盘今天"

# 政策
"最近的监管政策对新能源板块有什么影响?"

注意事项

风险免责

  • 本Skill分析仅供参考,不构成投资建议
  • 股市有风险,投资需谨慎,盈亏自负
  • 止损纪律是生存底线,必须严格执行
  • 回测结果不代表未来表现

能力边界

  • 本Skill不提供实时行情(需接入Tushare/AKShare数据API)
  • 不提供荐股服务,仅提供分析框架和决策辅助
  • 美股/港股分析能力相对A股弱(数据可得性限制)
  • 技术面分析依赖数据完整性,小盘股数据可能不完整

数据来源

  1. Tushare Pro API(A股,需注册)
  2. AKShare(免费备用)
  3. 公开研报和网络搜索(辅助验证)
  4. 财联社/雪球实时新闻(消息面)

关联Skill安装建议

子Skill用途推荐
skill-vetter安全审查⭐⭐⭐必装
multi-search-engine搜索政策/研报/舆情⭐⭐⭐必装
Policy Monitor监管政策追踪⭐⭐建议
Backtesting策略回测验证⭐⭐建议
Tushare数据APIA股数据接入⭐⭐建议
Stock Monitor实时异动监控⭐⭐建议

宝总霸盘Skill v1.0.0 | 作者:赵铭远 "好生意 + 好价格 + 好人性 = 好投资"

Comments

Loading comments...