Options Strategy logo

Options Strategy

Community
PatrickSUDO
options-strategy

Calculate and compare options strategies (sell put, covered call, LEAPS, naked call) for a given ticker. Usage - /options-strategy TICKER STRATEGY

Overview

PublisherPatrickSUDO
Repositoryfadacai-portfolio
Skill nameoptions-strategy
Stars
144
Forks
12
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by PatrickSUDO on GitHub. Read the source before you install it.

Installation

Install the Options Strategy AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/PatrickSUDO/fadacai-portfolio/tree/main/.agents/skills/options-strategy
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/PatrickSUDO/fadacai-portfolio.git /tmp/fadacai-portfolio
mkdir -p .claude/skills
cp -r /tmp/fadacai-portfolio/.agents/skills/options-strategy .claude/skills/options-strategy
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Options Strategy in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Options Strategy on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Options Strategy is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Options Strategy Calculator

Evaluate options strategies for a given ticker with risk/reward analysis.

Step 0: 配置同步 & 倉位偵測

執行 AGENTS.md 的 Step 0 統一規範(0a → 0b → 0c → 0d → 0e)。

  • 讀 plan.md + feedback/*.md(必做);了解此標的在計畫中的進場策略與 strikes
  • 呼叫 get_account_position 取即時持倉(確認現有部位與資金狀況)
  • 今日 journal 不存在 → 執行 gap-fill + 變動偵測 + 自動建立 journal
  • 0e 第一性原理紀律:在 Recommendation 之前必須完成「方向 thesis / 證偽條件 / IV 機率分布」三題(見 AGENTS.md 0e)

Arguments

  • /options-strategy TEAM sell-put — Sell put analysis
  • /options-strategy SSRM covered-call — Covered call analysis
  • /options-strategy MU leaps — LEAPS replacement analysis
  • /options-strategy FSLY naked-call — Speculative call analysis
  • /options-strategy PLTR all — Show all applicable strategies
  • /options-strategy PLTR AMD MU sell-put — 多標的比較(平行)
  • /options-strategy MU sell-put --codex — 加 Codex 第二意見(adversarial review of strike selection)

Workflow

  1. Parse ticker and strategy from arguments

Multi-Ticker Parallel Mode

當偵測到多個 ticker(如 /options-strategy PLTR AMD MU sell-put):

  1. 為每個 ticker 派出獨立 Agent 子代理(subagent_type: "data-collector",Sonnet 5),每個 Agent 執行:
    • get_stock_info — 現價 + 基本面
    • get_option_chain — 選擇權鏈
    • get_technical_indicators — 波動率 + RSI + 動量
    • get_support_resistance — S/R levels for strike selection
  2. 每個 Agent 回傳 raw 選擇權數據,主 skill 計算所選策略 3-4 個 strike 的損益數據
  3. 整合為比較表,依 E_adj 排序:
Ticker現價StrategyBest Strike(s)Max ProfitMax Loss損益比ATR%E_adj排名

若 Agent tool 不可用,依序處理各 ticker 亦可。


  1. Get Current Price & Technicals

    • If Yahoo Finance MCP is available, fetch real-time quote
    • Otherwise use WebSearch: "[TICKER] stock price today"
    • 現有持倉從 Step 0 的 get_account_position 取(已淘汰 current-position.md)
    • Use mcp__technical-mcp__get_technical_indicators to get volatility regime, ATR, and RSI
    • Use mcp__technical-mcp__get_support_resistance to identify key levels for strike selection
  2. Get Options Data

    • If Options Chain MCP or Yahoo Finance MCP is available, fetch actual options chain
    • Otherwise, estimate premiums based on:
      • Stock price and volatility
      • Days to expiry
      • Strike distance from current price
      • Historical IV if available via WebSearch
  3. Strategy Analysis

Sell Put

For 3-4 strike levels (near ATM to 15-20% OTM): | Strike | OTM % | Expiry | Est. Premium | Breakeven | Annualized Return | P(assign) | Margin Est. |

  • Margin estimate = 20-25% of (strike × 100) for margin account
  • Annualized return = (premium / margin) × (365 / DTE)
  • Show assignment scenario: what happens if assigned

Covered Call

Requires existing shares(從 get_account_position 確認): | Strike | OTM % | Expiry | Est. Premium | Max Profit | Annualized Yield | P(called away) |

  • Flag if user has enough shares for round lot (100)

LEAPS (Stock Replacement)

For 2-3 strike levels (10-25% ITM): | Strike | ITM % | Expiry | Est. Cost | Delta | Equiv. Shares | vs. Holding Stock |

  • Compare capital required: LEAPS vs equivalent shares
  • Calculate capital freed
  • Time value at risk
  • Note: if the user's broker is Level 2 only (no spreads), PMCC is unavailable

Bull Put Spread

For 2-3 strike combinations (short strike near support, long strike $10-20 below): | Short Strike | Long Strike | Width | Max Profit | Max Loss | Breakeven | P(profit) | Margin |

  • Max profit = net premium received
  • Max loss = width × 100 - premium
  • Margin requirement = width × 100
  • 引用配置計畫中建議的 strike levels(如有)

Bear Call Spread

For stocks with revision 下修/flat + 現價已超分析師 PT(不以 RSI 過高為條件): | Short Strike | Long Strike | Width | Max Profit | Max Loss | Breakeven | P(profit) |

  • Suitable for: revision 下修/flat + 已超分析師 PT 的標的(RSI 過高不是開 BCS 的理由 — 不對 revision 上修中的強者反向封頂)

Naked Call (Speculative)

| Strike | OTM % | Expiry | Est. Cost | Breakeven | Max Loss |

  • Flag this as high risk
  • Only for small speculative positions
  1. Broker Constraints(內部參考,不輸出) 分析時遵守以下限制,但不在輸出中顯示此區塊:
    • Options Level 2 + Spread 已開通(2026/03/03 起)
    • 可做 Bull/Bear Put/Call Spread、PMCC
    • Sell Put 使用 Margin(非 cash-secured 全額)
    • 不能做裸賣 Call(需 Level 3+)
    • 配置計畫原則:不再開裸 Sell Put,全部用 Spread
    • 財報 ±48h 不開新選擇權部位(IV 扭曲定價失準,per feedback/options-leaps-playbook.md);既有部位管理不受限

5.5 策略角色對映(飛輪定位 — 每次 Recommendation 前先確認本次操作在飛輪哪一環)

策略飛輪角色適用桶/情境紀律
Covered Callharvest 端:肥利潤落袋替代直接賣股🟢 認列桶 ≥100 股 + revision 轉折/題材降溫信念桶不開 CC 封頂(>10% 紅線減碼除外);strike 近 R1/分析師 PT,30-45 DTE
Bull Call Spreadredeploy 端:加速領導者貼高/超買的定義風險參與revision 上修中 + 貼 52W 高(「超買」不是不追的理由,是換結構的理由)max loss = net debit,凸性參與強者恆強
Bull Put Spreadredeploy 端:支撐區進場替代限價單回檔至支撐 + thesis 完好short strike 貼支撐,寬 $10-20
LEAPS deep ITM信念端:股票替代,釋放資金給飛輪🔵 信念桶多年 thesisdelta 0.80–0.88、12-18 個月、<90 DTE 評估 roll;未實現 >+80% → 評估 roll-up 收回本金留曝險(LEAPS 版分批停利,per feedback/tiered-profit-taking.md)
Bear Call Spread對沖/超目標價 harvest 輔助revision 下修 + 超分析師 PT 的認列桶不對 revision 上修中的持倉開(會反向封頂強者)
短 DTE OTM Call 樂透衛星倉binary catalyst 30d 內 + 具體論述總成本 ≤2% 帳戶,IV Rank >80 不做;+100% 賣半回本,剩餘 house-money runner
  1. Volatility-Adjusted Guidance Based on mcp__technical-mcp__get_technical_indicators volatility regime:

    • High volatility regime → sell premium strategies more attractive (higher premiums), wider strikes
    • Low volatility regime → buying options cheaper, tighter strikes for sell strategies
    • RSI oversold (<30) → sell put premiums attractive, consider buying calls
    • RSI 過高不作任何指引(2026-07-01 移除舊「overbought → avoid buying calls」— revision 上修中的強者照樣可用 bull call spread 參與,方向由 revision 定)
    • Use support levels from get_support_resistance to suggest sell put strikes near support
  2. 倉位管理 & 波動率標準化

    Quarter-Kelly 倉位上限: 單筆 Spread 最大配置 = min(總資產 5%, Spread 最大損失)。 同方向 Spread 合計 ≤ 總資產 15%。 (總資產從 Step 0 的 get_account_balance 即時取得)

    Swing Risk / Adjusted Risk 框架(per feedback/realized-pnl-business-model.md):

    • 既有選擇權部位的 Swing Risk = Premium 成本 + 當前未實現利潤(以歸零為最壞情境 = Expiry Risk);肥利潤未落袋 → 主動建議部分平倉/roll 鎖利
    • Roll 決策用 Adjusted Risk 視角:同標的累積已認列獲利後,新倉真實風險 = 新倉成本 − 該標的累積已認列;累積認列 ≥ 起始投入 = Risk-Free State。建議 roll/落袋時用此框架呈現,不寫「賣了就少賺」
    • BPS/BCS 達 50–75% 最大利潤 → 建議平倉認列(theta 後段風險報酬比惡化),釋放 margin 回飛輪

    波動率標準化比較 (E_adj): 當同時評估多個 Spread 機會時,計算:

    E_adj = 損益比 / ATR%
    損益比 = Max Profit / Max Loss
    ATR%  = ATR / 現價 × 100(從 get_technical_indicators 取得)

    E_adj 越高 = 風險調整報酬越好,應優先開倉。 在 Recommendation 中顯示 E_adj 排序。

  3. 第一性檢查(Recommendation 前必填)

    ### 第一性檢查(Options 層級)
    - **方向 thesis:** [1 句可驗證命題,例:「MU FY26 EPS forward $XX 隱含 PE XX,週期高點未到」]
    - **證偽條件:** [2-3 個 falsifiable — 例:「下季 ASP 連續下跌」「庫存週數超 X 週」「DRAM spot price -10%」]
    - **IV / 機率分布:**
    
      | 情境 | 機率 | 標的 12 個月價 | Strategy P/L |
      |------|------|--------------|--------------|
      | 樂觀 | XX% | $XXX | +$XXX |
      | 基準 | XX% | $XXX | +$XXX |
      | 悲觀 | XX% | $XXX | -$XXX |
    
      Expected P/L = Σ(機率 × 損益) = $XXX
      對比單純買現股的 expected return:哪個更優?
  4. Recommendation

    • Which strike/expiry combination is best for this ticker
    • How it fits with existing portfolio
    • 飛輪定位(引用 5.5 對映表:本操作是 harvest / redeploy / 信念端哪一環;若是 harvest,同時給盈餘配對去處或標 dry powder)
    • Position sizing(根據 Quarter-Kelly 上限)
    • E_adj 分數(如有比較對象)
    • 明確說 Recommendation conditional on 哪個情境 + 機率
    • 結尾附可掛的單(per feedback/actionable-firstrade-orders.md):結構 + 買賣別 + 履約價 + 到期 + limit credit/debit + 口數 + 效期,照抄可下;複式單無法 GTC → 給價格警報價位 + 預定結構(觸發後 2 分鐘執行)

Step 9: Codex 第二意見(opt-in)

僅當 arguments 含 --codex 或 --2nd 時執行。

B1. 獨立第一性分析(預設,independent first-principles)

核心原則:Codex 不看 Claude 的 strike 選擇與 Recommendation,只給 raw market data,讓它獨立挑 strike + 計 E_adj。Claude 與 Codex 兩個獨立輸出並排比較。

呼叫 Codex(用 AGENTS.md「Codex 呼叫方式」的 codex exec CLI;勿用 codex:codex-rescue subagent / /codex:rescue,會卡 superpowers preamble),prompt 首行加強制 no-tool 指令,模板:

我是一名美股投資人,使用 Level 2 options + Spread 的 margin 帳戶。
請對 [TICKER] 在策略 [STRATEGY] 下,**完全獨立**選 strike + 計算 E_adj — 不要看任何先前推薦,這是獨立第二意見。

**Raw market data(只給事實):**
- 現價:$XXX
- ATR / IV / IV Rank:[數據]
- 分析師中位 PT:$XXX
- 技術面:RSI / 趨勢 / 距 52W 高 / R1 / S1 / SMA50
- 近期催化:[財報日、產業事件]
- 配置上下文:用戶帳戶 ~$XXX,Quarter-Kelly 單筆上限 5%(~$XX,XXX)
- 用戶持倉:[已持有 X 股 / 未持有]

**可選 strike 範圍:**
[列出該策略下合理的 3-5 個 strike + DTE 組合,不標註哪個是 Claude 選]
- Strike $X DTE Y → 權利金 $X / 損益比 X.X / breakeven $X
- Strike $X DTE Y → ...

**請輸出:**

1. **核心 thesis**(1 句可驗證命題:為何此標的此時適合此策略?)

2. **證偽條件**(2-3 個 falsifiable — 例如:IV 跌破某值、現價跌破 SMA50、財報 miss)

3. **strike 選擇 + E_adj 計算:**

   | Strike | DTE | 權利金 | 損益比 | ATR% | E_adj | 機率盈利 |
   |--------|-----|-------|--------|------|-------|---------|
   | ... |

   推薦 strike:[$X DTE Y] / 開 [N] 口 / 總收入 $X / 鎖定資本 $X / 最大損失 $X

4. **Verdict**(1 句):建議執行 / 暫緩 / 換策略,並說明 conditional 在什麼前提。

**規則:**
- E_adj = 損益比 / ATR%(越高越優先)
- 必須講口數(AGENTS.md feedback 規定)
- 不假設 Claude 選哪個 strike
- 用客觀數據與你自己的 mental model

請以繁體中文回覆,控制在 600 字內。

--effort high --fresh

輸出整合

## 🤖 Codex 第二意見(獨立第一性分析)

### Codex 獨立輸出

**核心 thesis:** [Codex thesis]
**證偽條件:** [Codex 列的條件]
**Codex 推薦 strike:** $X DTE Y,開 N 口
- 總收入:$X
- 鎖定資本:$X
- E_adj:X.X

**Codex Verdict:** [...]

---

### 並排比較:Claude vs Codex(獨立輸出)

| 維度 | Claude | Codex | 一致性 |
|------|--------|-------|--------|
| 推薦 strike | $X DTE Y | $X DTE Y | 同 / 異 |
| 口數 | N | N | — |
| 總收入 | $X | $X | 差異 |
| E_adj | X.X | X.X | — |
| Verdict | 執行 / 暫緩 | 執行 / 暫緩 | 同 / 異 |

**真實共識**(兩邊獨立都認同):[1-2 條 — 高信心結論]
**真實分歧**(兩邊獨立得出不同結論):[1-3 條 — 值得深入]
**整合建議:** [基於真實共識的最終 strike + 口數,或建議再等資料]

進階:--codex-adversarial(opt-in 壓力測試)

僅當 arguments 含 --codex-adversarial 時,追加對立面審查段落(攻擊 strike 選擇、找最弱假設)。預設 --codex 不執行。

若 Codex 失敗 → 輸出 ⚠️ Codex 不可用:[error],跳過第二意見,繼續正常輸出。


Output Language

Use Traditional Chinese (繁體中文) for all text output.

存檔 + HTML 生成

報告完成後:

  1. 使用 Write tool 把完整 markdown 寫到 briefing-out/options-strategy-<TICKER>-YYYY-MM-DD.md
  2. 執行:
bash
python3 tools/generate_html.py options-strategy briefing-out/options-strategy-<TICKER>-YYYY-MM-DD.md --push

成功時印出網頁連結,失敗時印警告並繼續。

Frequently asked questions

What does the Options Strategy AI skill do?

Calculate and compare options strategies (sell put, covered call, LEAPS, naked call) for a given ticker. Usage - /options-strategy TICKER STRATEGY

Why use Options Strategy on TypingMind?

Because you install it once and use it with any model. Options Strategy is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Options Strategy in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/PatrickSUDO/fadacai-portfolio/tree/main/.agents/skills/options-strategy. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Options Strategy?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Options Strategy?

As many as you like. As long as a model supports skills, you can use Options Strategy with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Options Strategy AI skill free?

Yes. It is published on GitHub by PatrickSUDO under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇