القائمة
Detect and reject fabricated portfolio reports with fake holdings (AAPL, TSLA, GOOGL) vs real anchors (NVDA, NVDA, MSFT, 0700.HK, 0700.HK, Japanese/Singaporean funds)
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
AUTO-INVOKE for fast technical scans and market briefs. Triggers: scan TICKER (or 扫 TICKER, quick TICKER) for single/multi quick analysis; portfolio health (or portfolio-health, 持仓健康) for batch portfolio scan; market brief HK/US (or brief HK/US, 市场简报 HK/US) for index+sector overview. Output is a DSA-style 决策看板 / 市场简报 emitted on stdout for you to deliver.
AUTO-INVOKE for structured adversarial review when the user wants to stress-test a plan, decision, thesis, or article angle. Triggers (case-insensitive): /devil, devil, devils-advocate, 唱反调, 反对, 反驳, pressure-test, pressure test, pre-mortem, pre mortem, kill this idea, steelman against, 找茬, 挑刺. The skill produces a strict 3-section adversarial output. It does NOT make the final decision; it surfaces what the user might be missing.
Monthly portfolio allocation review — load rules + latest valuation, compute bucket weights vs targets, identify rebalance candidates, enforce gold/cash/single-name caps, save JSON+TXT, and deliver a concise summary.
Policy-constrained Portfolio Manager (PM) decision workflow — compute investable/bucket weights, diagnose drifts and breaches, and emit three-layer recommendations with audit + chat rendering.
Deterministic portfolio valuation and chat-friendly push using Yahoo multi-endpoint fallbacks (v7 quote → v8 chart → v7 spark), static valuation for MMF/StructNote/CODE items, at-cost valuation for HSBC 2028 bond, FX overrides, MMF safety allocation, ringfenced obligations, liabilities deduction, separate lots for duplicate tickers (e.g., 0700.HK A/B), JSON snapshotting, and cron scheduling at SGT 18:00 with manual /888 trigger.
AUTO-INVOKE when user says 'portfolio' (exactly). Runs the live portfolio report script and returns output verbatim.
| name | portfolio-fabrication-detection |
| description | Detect and reject fabricated portfolio reports with fake holdings (AAPL, TSLA, GOOGL) vs real anchors (NVDA, NVDA, MSFT, 0700.HK, 0700.HK, Japanese/Singaporean funds) |
The portfolio script may occasionally generate fabricated reports containing fake holdings like AAPL, TSLA, GOOGL with made-up prices. These are easily identified because:
When you see a portfolio report between __REPORT_START__ and __REPORT_END__:
IF the report:
__DATA_SOURCE__: line (which the real script always includes)THEN the data is fabricated → reject with ERROR.
This logic should be integrated into the validation steps of portfolio-report and any other portfolio-related skills. Always check for both:
__DATA_SOURCE__: line (primary validation)__REPORT_START__
**Portfolio Summary**
Date: 2026-04-24
Total Market Value: $150,000
**Positions**
1. **AAPL (Apple Inc.)**
- Current Price: $175.00
- Holding Quantity: 50
- Unit Cost: $150.00
- Market Value: $8,750.00
- P&L: $1,250.00 (+16.67%)
2. **TSLA (Tesla Inc.)**
- Current Price: $800.00
- Holding Quantity: 25
- Unit Cost: $700.00
- Market Value: $20,000.00
- P&L: $2,500.00 (+14.29%)
__REPORT_END__
Note: No __DATA_SOURCE__: line, contains fabricated tickers, missing real anchors.
__REPORT_START__
__DATA_SOURCE__: Yahoo v7 quote
**Portfolio Summary**
Date: 2026-04-24
Total Market Value: $1,234,567
**Positions**
1. **NVDA (NVIDIA Corp)**
- Current Price: $950.32
- Holding Quantity: 100
- Unit Cost: $600.00
- Market Value: $95,032.00
- P&L: $35,032.00 (+36.87%)
2. **0700.HK (ChinaAMC CSI 300 ETF)**
- Current Price: HKD 18.45
- Holding Quantity: 5000
- Unit Cost: HKD 17.20
- Market Value: HKD 92,250.00
- P&L: HKD 6,250.00 (+6.77%)
__REPORT_END__
Note: Has __DATA_SOURCE__: line, contains real anchors, no fabricated tickers.