monarchjuno

Create, update, or prepare Codex app Scheduled Tasks for any recurring TradingCodex work, including simple research, monitoring, recurring analysis, portfolio review, order preparation, assisted execution, explicitly turn-authorized execution, and explicitly turn-authorized Build work. Use when the user asks to automate, schedule, monitor, or periodically repeat a TradingCodex request.

Create or revise a user-owned local Investment Brain plugin from user-selected Decision Memory evidence, counterexamples, validated lessons, or an explicitly stated investment philosophy. Use when the user asks to curate general inquiry and interpretation heuristics into an `investment-brain-*` bundle, while keeping authoring separate from installation, activation, and publication.

Mark one exact root Codex turn as explicit workspace-local TradingCodex Build intent for workspace refresh, managed optional skill, Strategy, or Investment Brain lifecycle work, managed MCP configuration, and broker/API provider development without elevating filesystem permission or granting order execution.

Interview the user to create, inspect, update, enable, disable, or clear workspace-local investor suitability context. Use when the user explicitly asks to manage the objective, horizon, loss capacity, liquidity needs, holdings or concentration, or tax, account, and jurisdiction constraints applied to future workflows.

Review past investment decisions, run point-in-time historical replays, compare resolved forecasts and forward outcomes, and validate lesson candidates. Use when the user asks what happened before, why a thesis changed, whether a strategy lesson held out of sample, or what prior evidence is relevant to a current decision.

Authorize at most one TradingCodex order submission or cancellation later in the current root native Codex turn. Use only when the user intentionally places an exact `$tcx-order-allow --mode paper|validation|live` line first in a prompt, including a saved Codex app Scheduled Task prompt.

Cancel one known submitted TradingCodex broker order from a native Codex workspace session. Use only when the user intentionally requests the final cancel action and has the exact ticket, broker order, and approval receipt ids.

Submit one already-approved TradingCodex order from a native Codex workspace session. Use only when the user intentionally requests the final submit action and already has the exact order ticket id and matching approval receipt id.

Automatically analyze a company or company-related finance situation from a short user prompt such as a company name, "analyze [company]," M&A, LBO, IPO, debt, credit, or risk requests. Use when an agent must infer the correct valuation and finance framework without asking follow-up questions, begin from market-implied expectations instead of immediate fair value, run Reverse DCF before Forward DCF for listed companies, perform web-verified data gathering and deal-radar checks, defend against hallucinations with explicit data tags and uncertainty statements, and produce a plain-text output with no markdown and no row-column tables.

Fetch financial, market, economic, fundamental, news, options, crypto, ETF, index, and macro data through the OpenBB Python interface instead of the OpenBB MCP server. Use when an agent needs current or historical data from OpenBB-supported providers, needs to replace OpenBB MCP calls with direct Python/OpenBB usage, or must return source-tagged, reproducible datasets with clear query parameters, provider details, and data-quality notes.

Analyze a company, sector situation, or valuation question through Aswath Damodaran's lens. Use when the analysis should start with the business story, connect that story to revenue growth, margins, reinvestment, and risk, then judge valuation through disciplined intrinsic-value work, expectation testing, and explicit uncertainty rather than slogan-level cheap or expensive language.

Analyze an investment through Benjamin Graham's conservative value-investing lens. Use when the analysis should focus on margin of safety, balance-sheet strength, earnings stability, Graham-style valuation measures such as Graham Number or net-net logic, and avoidance of speculation or aggressive growth assumptions.

Analyze an investment through Bill Ackman's concentrated activist lens. Use when the analysis should focus on high-quality businesses, durable moats, free-cash-flow generation, capital allocation, valuation support, and the presence or absence of catalysts, strategic change, or activist-style value creation.

Analyze an investment through Cathie Wood's disruptive-innovation lens. Use when the analysis should focus on breakthrough technology, large total addressable markets, multi-year growth optionality, platform scalability, and management willingness to invest in R&D even when near-term volatility or valuation looks uncomfortable.

Analyze an investment through Charlie Munger's quality-first lens. Use when the analysis should emphasize durable business quality, incentives, management character, capital allocation, multidisciplinary thinking, avoidance of complexity or fragility, and willingness to pay a fair price for an exceptional business rather than a bargain price for a weak one.

Analyze an investment through Michael Burry's hard-number contrarian lens. Use when the analysis should focus on deep value, downside protection, balance-sheet skepticism, free-cash-flow and EV-based valuation, market overreaction, and the presence of concrete catalysts such as insider buying, asset sales, buybacks, or forced unwinds.

한국 전문직 기여자와 문답하며 k-sajja-agents 레포지토리의 직업별 agentskills 형식 SKILL.md를 설계하거나 업데이트할 때 사용합니다. 변호사, 의사, 변리사, 세무사 등 전문직이 자신의 반복 업무를 AI 에이전트 스킬로 만들고 싶어 할 때, 원본 skill-creator의 스킬 설계 절차를 바탕으로 직업 패키지 선택, 구체 예시 수집, 재사용 리소스 설계, 전문지식 출처 설계, AI 역할 경계, 전문가 연결, MIT 라이선스 및 레포 기여 형식까지 함께 정리합니다.

Use when a user is creating, evaluating, or implementing a product, app, feature, startup idea, repo, demo, landing page, launch plan, or vibe-coded project and wants development to be led by marketing, distribution, positioning, audience pull, memeability, or the user's experience of discovering the thing before code.