Borrowing it
Nothing to install: this file belongs to PatrickSUDO/fadacai-portfolio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PatrickSUDO/fadacai-portfolio/main/.agents/skills/event-vol-scan/SKILL.mdgit clone --depth 1 https://github.com/PatrickSUDO/fadacai-portfolioWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/patricksudo/fadacai-portfolio/event-vol-scan)<a href="https://agentmods.dev/skills/patricksudo/fadacai-portfolio/event-vol-scan"><img src="https://agentmods.dev/badge/skills/patricksudo/fadacai-portfolio/event-vol-scan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/patricksudo/fadacai-portfolio/event-vol-scan"><img src="https://agentmods.dev/badge/skills/patricksudo/fadacai-portfolio/event-vol-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.02065 |
| Opus 5 | $0.00041 | $0.01033 |
| Sonnet 5 | $0.00016 | $0.00413 |
| Haiku 4.5 | $0.00008 | $0.00206 |
Grade A, and why
event-vol-scan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Event Vol Scan — 事件前買方機會掃描
定位：把 portfolio-review I.5 樂透掃描升級為事件驅動買方掃描 — 在財報 / CPI / FOMC 前找兩類機會： ① 末日 buy call（方向凸性：base rate + revision 一面倒，且隱含移動不貴） ② 雙買 straddle（純波動：隱含移動 < 歷史實際移動，不賭方向賭幅度）
與既有規則的關係（必讀）
- 「財報 ±48h 不新開期權倉」（options-leaps-playbook）的例外聲明：那條禁的是「方向性建倉被事件 IV 扭曲定價而不自知」。本 skill 是有意識的事件波動買方（吃 gamma / vol），屬明確 opt-in 例外。賣方策略（BPS/BCS/CC）仍完全遵守 ±48h 禁令，本 skill 絕不輸出事件窗內的賣方單。
- 沿用樂透鐵則（playbook + I.5）：總成本 ≤ 2% 帳戶（Quarter-Kelly）、OI > 500、已漲 >30%（5日）排除、不用 OTM LEAPS 當樂透（vega 干擾凸性）。
- 機率語言紀律：不寫「應該會大漲」— 引擎輸出 VRP（隱含/歷史）與 base rate，判讀 conditional 在這兩個數字。
Step 0
執行 AGENTS.md Step 0 統一規範（0a 讀 plan.md + feedback、0b get_account_position、0c/0d journal 檢查）。本 skill 需要：持倉 ticker 清單、帳戶總值（算 2% 預算）、plan.md L1 On-Deck / 觀察清單。
Workflow
1. Universe 組建
- 預設：持倉全部 ticker + plan.md「L1 On-Deck」+「觀察清單」標的
- 用戶 args 指定 ticker → 只掃指定的
- 宏觀事件：
mcp__eodhd-mcp__get_economic_calendar(from, to, country="US", high_impact_only=True)抓窗內 CPI / FOMC / NFP 日期 → 以SPY:<date>:<label>,QQQ:<date>:<label>注入（半導體集中事件可加 SMH）
2. 跑掃描引擎（機械層 — 不手算 chain）
python3 tools/event_vol_scan.py \
--tickers <逗號清單> \
--days <N，預設 14> \
--extra-events "SPY:YYYY-MM-DD:CPI,QQQ:YYYY-MM-DD:FOMC" \
--account-value <live 帳戶總值> \
--json briefing-out/cache/event-vol-scan.json
引擎輸出（每 ticker×事件）：事件後首個到期、ATM straddle 隱含移動、過去 8Q 財報實際移動中位（earnings-history cache 日期 × 日線）、VRP = 隱含/歷史、beat rate + 30d revisions、5 日 run-up、OI/spread 流動性、1×IM 末日 call 候選報價，以及機械裁決：
| 裁決 | 條件 | 意義 |
|---|---|---|
BUY_CALL |
beat ≥ 7/8 且 rev up ≥ 5×dn 且 avg surprise ≥ +5%（非 unreliable）且 VRP ≤ 1.2 | 方向凸性候選 |
STRADDLE |
VRP < 0.85 且歷史中位移動 ≥ 4% | 雙買候選（隱含 < 歷史） |
STRADDLE_RV |
無財報基準（ETF/新股），隱含 < 20d 實現波動×√T | 雙買候選（次級基準） |
SKIP_RICH |
VRP > 1.2 | 隱含太貴，IV crush 風險 |
EXCLUDE |
5日漲幅 >30% 或 OI/spread 不及格 | 淘汰 |
WATCH |
無明確 edge | 列示不建議 |
3. 判斷層（Claude — 引擎裁決之上，逐條檢核）
STRADDLE_RV的 rv 灌水檢查：近 5 日若有 >3% 單日（崩盤週），rv20 被灌高 → VRP_rv 失真偏便宜。此時降級為 WATCH，除非隱含移動絕對值也低於長期常態。BUY_CALL的 thesis 一致性：對照 plan.md 桶別 / 候補層 — 與現有持倉同題材 binary 不重複開（已有同板塊事件樂透 → 優先補強既有）。- 末日進場時點（重要 — 掃描日 ≠ 進場日）：
- 雙買：事件前 2–5 個交易日進場（IV ramp 前段，theta 尚可控）
- 純末日 call：事件前 1 日或當日（最大 gamma，premium = max loss 心態）
- 今天距事件 >5 日 → 輸出「價格警報 + 預定結構」，不是現在就買（複式單無法 GTC）
- 口數與預算：總樂透預算 ≤2% 帳戶（引擎已算出金額）；單筆 1-2 口；每筆必寫「上行 +XXX% / max loss = premium $X」。
- 出場紀律（開倉時就寫死）：
- 雙買：事件後首個交易日內了結（IV crush 前），不留倉「等第二波」
- 末日 call：+100% 賣半回本（house-money runner），事件後歸零風險自負
- 入選 0 筆 → 誠實輸出「⏳ 本次無符合凸性條件的事件買方機會」+ 最接近門檻的 1-2 筆與差多少。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 94 lines · 81 tokens per session scan A a21139c732f7
event-vol-scan is a skill published in the GitHub repository PatrickSUDO/fadacai-portfolio (139 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 2,065 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.