Coding

Invassistant

Try it

Apply a multi-market portfolio framework with A/B/C asset rules, 7 red-line risk controls, and 4-factor QMS scoring.

What it does

Manage a multi-market portfolio with a tiered framework covering US, A-share (China), and HK stocks. Holdings are classified into A (platform core, no trailing stop), B (high-beta cyclical, trailing stop + position management), and C (low-volatility income, DCA + rebalancing) tiers, each with its own entry and exit logic. Portfolio risk is governed by 7 non-overridable red lines on single-position concentration (>25%), single-sector concentration (>35%), single-narrative exposure (>50%), drawdown thresholds (-12% and -15%), VIX spikes (≥40), and pre-trade log compliance. A 4-factor QMS score (Earnings Trend, Sector Relative Strength, EPS Revision, Price Structure) gates entries and B-class …

When to use it

  • Reviewing a portfolio against the 7 non-overridable red-line risk controls
  • Classifying a stock into A, B, or C tier to choose the matching exit logic
  • Evaluating an entry candidate with the 4-factor QMS score and thresholds
  • Logging and reviewing trades against monthly KPI targets

The skill document

name: invassistant description: > Multi-asset investment portfolio management framework with A/B/C asset-class differentiated rules, 7 red-line portfolio risk controls, and 4-factor QMS quality scoring. Covers US, A-share (China), and HK stocks with disciplined entry/exit logic. description_zh: "多资产投资组合管理框架:A/B/C 类资产差异化规则、7 条红线组合风险控制、四因子质量管理;覆盖美股、A 股、港股,纪律化进出场逻辑。" version: "2.3.6" read_when:

  • "User requests portfolio review, A/B/C asset classification, or 7-red-line risk check for their holdings"
  • "User asks about entry/exit logic for US stocks, A-shares (China), or HK stocks under the framework"
  • "User requests QMS (quality scoring) evaluation of a stock candidate"
  • "User asks about portfolio risk controls, warning lines, or position sizing rules"
  • "User wants to log a trade or review trade history against the framework" not_for:
  • "Real-time trading signals or market timing predictions"
  • "Specific stock buy/sell recommendations without portfolio context"
  • "Tax, legal, or regulatory advice — this is a portfolio management framework, not financial advice"
  • "Analysis of assets outside US / A-share / HK stocks (crypto, commodities, fixed income) without adaptation"

allowed-tools:

  • read_file
  • write_to_file
  • replace_in_file
  • execute_command disable: false metadata: openclaw: requires: bins: - python3 env: [] tags:
    • investment
    • trading
    • portfolio
    • stock
    • finance
    • us-stock
    • a-share
    • hk-stock
    • risk-control

InvAssistant

Multi-asset investment portfolio management framework — current version v2.3.6 (2026-08-07). Core philosophy: portfolio before stock-picking, discipline before inspiration. Rules are guardrails, not cages.

⚠️ Risk Warning: This is a decision-support framework, not financial advice. AI guidance is probabilistic; executable rules can take action (red-line reductions, Mode B entries); send_*.py pushes holdings to external messaging platforms — review before pushing. Author assumes no liability for trading losses.


1. Asset Classification (Three Tiers)

This is the foundation of v2.1+. Different assets use different exit logic.

TierDefinitionRulesWhen To Sell
A-Class (Platform Core)Long-moat, cash-flow-stable platform companiesHOLD, no trailing stop; DCA entriesOnly 3 reasons: ① fundamental deterioration (2+ quarters) ② narrative change ③ portfolio limit breach
B-Class (High-Beta Cyclical)High-beta, narrative-driven growthTrailing stop + position managementQMS < 40 triggers review
C-Class (Low-Volatility Income)Broad-market/dividend ETFs, utilitiesDCA + rebalancingNo active timing

Key insight: A-class price drawdowns ≠ sell signals. Using trailing stops on A-class washes out long-term compounders.


2. Portfolio Risk Controls: 7 Red Lines (Non-Overridable)

#RuleThresholdAction
1Single position concentration>25%Reduce to ≤20% within 3 months
2Single sector concentration>35%Reduce to ≤30% within 3 months
3AI single-narrative>50%Reduce to ≤40% within 6 months
4Portfolio drawdown (mild)>-12%Halve satellite positions
5Portfolio drawdown (severe)>-15%Total position ≤60%
6VIX systemic risk≥40Reduce total to ≤50%
7Pre-Trade Log compliance<100%Log immediately

3. US Stock Strategy

Entry Modes

ModeApplies ToLogic
A (Panic Mispricing)B-Class (TSLA/NVDA extreme)Emotion release + technical support + VIX <25
B (Trend Confirmation)B-ClassPrice > MA50 + breakout + fundamentals + valuation
C (Rebalancing)Portfolio-levelTriggered by Red Lines 1-3 only
D (A-Class Candidate Zone Entry)Candidate pool (non-tech diversification targets)Callback-based, no observation delay

Mode D: A-Class Candidate Zone Entry (v2.1.1)

Applied to new A-class candidates before they join the core portfolio. Designed to solve the "observation delay misses entry window" problem.

Principle: No observation delay. A -10% pullback from 20D high on an A-class candidate is itself a complete entry signal — the underlying moat business doesn't change with share price.

ZoneTriggerAllocationExecution
First tranche-10% from 20D high50% of targetExecute immediately
Add-15% (or >3% further drop after first)30%Execute on trigger
Final-20% (or 5+ days sideways without new low)20%Within zone

Constraints: total ≤2% portfolio; MCO requires PE percentile <60%; no chasing after rebound.

Why Different from TSLA Mode A

TSLA (B-Class satellite) needs bottom confirmation — the drop might be fundamentally justified. A-class candidates (moat compounders) only need price confirmation — a -10% discount on a quality business is self-evidently an opportunity.


4. A-Share Strategy (3-Condition Engine)

All three conditions must pass for entry:

ConditionStandard
① Engine score ≥80 + 3 consecutive days on listCore selection pool
② Current price ≤ dynamic target (with floor)max(static×0.85, min(static, MA20×0.95))
③ MA20 flat or turning upMA20 delta ≥ -0.05

Flex window: 2/3 conditions met + 3rd deviation ≤10% → half-position trial. Time stop: 6 months max in selection pool without entry → forced review.


5. HK Stock Strategy

SourceFramework
Actively boughtFollow A/B/C classification rules
Company allocation/incentiveWarning line + reduction framework (not hard stop)

Warning line (not hard stop): Triggers 48h review upon breach. Time limit: 18 months post-vesting with remaining position → unconditional full exit.


6. QMS Scoring (4-Factor)

QMS = 0.35 × Earnings Trend
    + 0.25 × Sector Relative Strength
    + 0.25 × EPS Revision
    + 0.15 × Price Structure
ScoreMeaningAction
≥70High quality + good timingHold / observe entry
50-70Healthy, not at entry pointHOLD
<50Quality or timing issuesNo new positions
<40Review exit queueEvaluate reduction (B-Class only)

Boundary: QMS is entry reference for A-Class, NOT an exit trigger. Only B-Class uses QMS <40 as reduction signal.


7. Monthly KPIs

KPIThresholdType
Monthly turnover rate≤15%Red line
Pre-Trade Log compliance=100%Red line
A-Class sold on price volatility=0Red line
Panic-period reduction (VIX≥30)=0Red line
System execution rate≥80%KPI

8. Hard Rules Summary

  1. Asset classification determines action semantics: A-Class no trailing stop, B-Class uses trailing stop
  2. Held vs. watchlist semantics must not be mixed
  3. A-share 3-condition is a filter: all pass → entry (flex window = 2/3 + deviation + half-size)
  4. US B-Class dual-mode: Mode A (3 red lines all pass) / Mode B (4 conditions all pass)
  5. Unfilled ≠ holding: portfolio data must reflect actual positions
  6. Never fabricate data: all indicators must come from live data sources
  7. A-Class only sells on 3 fundamental reasons (never price)
  8. 7 Red Lines triggered = must follow, no override
  9. Allocation/incentive positions do not use standard stops
  10. Every override must be logged
  11. Max 2 overrides per ticker per quarter; 3rd is void
  12. Daily self-check: 5 questions, all "no" = no trade today

9. Data Sources

Data TypePrimaryFallback
US stock quotes/technicalswestock-dataYahoo Finance
A-share K-line/technicalswestock-dataAKShare
HK stock quoteswestock-dataYahoo Finance
VIXwestock-dataYahoo Finance
North-bound capitalNeoDataAKShare
Financial reports/consensuswestock-dataNeoData

10. Common Mistakes

#MistakeFix
P1Treating A-Class as B-Class (v2.0's worst error)Ask "Is this A or B?" before acting
P2Writing "reduce" for watchlist stocksAsk "Is this held?" first
P3Cross-market strategy pushed to sub-pagesCross-market → main page; specific rules → sub-page
P4LaTeX $xxx swallows first digitUse US$ / HK$ / ¥ / \$
P5Wrong code block language ('plain')Must use 'plain text' (with space)

Version History

VersionDateSummary
v2.3.32026-08-07Sync SKILL.md version declaration with ClawHub package metadata
v2.3.22026-06-06Fix display name (remove Clean suffix)
v2.1.22026-06-06Audit cleanup: bilingual README, remove legacy files
v2.1.12026-06-04Mode D: A-class candidate zone entry (no observation delay)
v2.12026-05-18A/B/C asset classification; 7 red lines; 4-factor QMS; trailing stop removed from A-class
v2.02026-05-18Full rebuild: decision pyramid, 5-factor QMS, 10 red lines (replaced)
v1.52026 Q1-Q23-condition engine, dual-mode entry, trailing stops

中文简介:InvAssistant 是一个多市场投资组合管理框架。按资产三层分类(A/B/C)执行差异化规则,7 条组合红线不可覆盖,4 因子 QMS 评分辅助决策。覆盖美股、A 股、港股。核心信念:组合优先于选股,纪律优先于灵感。规则是栏杆,不是牢笼。

Related skills

个人投资决策辅助系统。基于 INVEST 六维决策框架(意图/数字/价值/优势/安全/时机), 将分散的市场信息、持仓数据、投资目标和风控纪律串成一个完整的决策闭环。 提供持仓管理、决策评分、仓位计算、风控检查和交互式 HTML 可视化报告。 触发词:投资决策, 买卖决策, 持仓分析, 投资复盘, 仓位计算, 风...

openInvest multi-asset AI investment committee — **daily use**. Read portfolio / live prices / strategy / decision history / adjust positions / run a 4-role...

1 installs

产业园招商 AI 个人助手。面向招商人员,四步工作流:今天客户 → 客户情况 → 客户推进 → 处理完成。 AI 贯穿全程(排序优先级·推荐下一步·分析客户·自动记录),不替代人做决策。 核心场景:客户管理·房源查询·客户接待·报价方案·选址建议·合同生成·渠道管理。 含时效性校验、No Agency护栏(金额让步需审批)、每日09:00自动推送今日客户列表。 支持多项目架构和知识库分离(SQLite本地库 + IMA知识库)。

23 installs

# 🦞 股票投资决策系统 > 五维贝叶斯框架 × 六层镜头决策矩阵 × 行为金融纠偏 > 适合A股/港股中长线投资者 ## 这是什么? 这不是一个简单的「问股价」工具。这是一套完整、可执行的**投资决策操作系统**,把专业投资者的方法论封装成了AI可以直接调用的流水线。 ## 核心能力 ### 五维贝叶斯投资法 1. **本末** — 先验校准,知道自己知道什么、不知道什么 2. **终始** — 护城河五维检查 + A股四因子校正 3. **变量** — 死法卡片 + 叙事拥挤度 + 事件驱动清单 4. **路径** — 双维裁决矩阵 + 索普半凯利仓位管理 5. **结构** — 投后监测 + 退出条件(买入时就写好) ### 六层镜头决策矩阵 | 层 | 镜头 | 作用 | |----|------|------| | L1 | 价值锚 | 公司值多少?安全边际在哪? | | L2 | 价格结构 | 走势在什么位置? | | L3 | 时机能量 | 当前周期方向? | | L4 | 资金验证 | 主力在进还是出? | | L5 | 市场环境 | 政策/散户/量化/A

9 installs

统一大类资产配置分析技能(融合版)。基于宏观经济分析和申万一级行业趋势,生成中国大类资产配置建议报告。数据源采用 AKShare(底层对接国家统计局/东方财富等权威源,非黑盒)。输出三格式:HTML(可视化卡片+产业链图)、Markdown(完整分析文档)、Excel(8 Sheet结构化数据)。覆盖宏观经济→资...

6 installs

Multi-market intelligent stock selection for A-share/HK/US stocks and ETFs. Use when user asks about stock analysis, market scanning, portfolio construction,...