financial-codex-workspace

Use when users need A-share single-stock equity research, stock deep dives, China A-share thesis checks, technical analysis across daily/weekly/monthly OHLCV data, explicit research or decision_support modes, iFinD and AKShare cross-checks, catalyst tracking, watchlist inputs, market context, standardized A-share schemas, source capability matrices, decision support guardrails, report integrity checks, or historical thesis references without inventing financial, market, company, consensus, guidance, target-price, rating, or buy/sell data.

Use when users need productized A-share research workflows in Codex, including watchlist daily reviews, market context reviews, daily/weekly/monthly technical analysis, explicit research versus decision_support mode routing, investment decision-support framing, strategy checks, local JSONL history, thesis review logs, backtest-style post reviews, report integrity checks, or .research artifact conventions while preserving source logs, QA, and no target-price/rating/buy-sell guardrails.

Use when financial, investment, trading, valuation, accounting, market-data, broker-journal, or client-facing outputs need a final QA gate before delivery or persistence. This skill checks source logs, timestamps, missing data, Not investment advice, forbidden target-price/rating/position-sizing/return-promise language, unconditional trade instructions, artifact references, and output-contract compliance without performing new analysis or inventing data.

Router for all financial services, accounting, investing, capital markets, private equity, investment banking, wealth management, fund administration, KYC, valuation, earnings, equity research, and financial modeling requests. Use when any user request involves financial analysis, financial documents, spreadsheets, presentations, market data, company analysis, transaction work, portfolio review, or regulated financial workflows, before selecting a more specific financial-services skill.

Use when users need broker trade journal parsing, trading behavior diagnostics, FIFO roundtrip analysis, Shadow Account profile extraction, or post-trade review for 同花顺, 东方财富, 富途, generic CSV, or Excel exports. This skill uses trading_core journal adapters and Vibe-Trading-inspired Shadow Account concepts to produce win rate, profit/loss ratio, holding days, drawdown, overtrading, disposition effect, chasing momentum, anchoring, local .research artifacts, and Not investment advice without predicting returns or creating live trades.

Use when users need productized trading decision support, conditional buy/sell-point style planning, Vibe-Trading backtest validation, Alpha Zoo factor screening, or full-market stock monitoring through this workspace. This skill routes through financial-services-skill-router, china-market-overlay for China securities, and trading_core CLI adapters to produce source-backed decision_card, conditional_trade_plan, execution feasibility checks, source logs, QA status, and Not investment advice without target prices, ratings, personal position sizing, return promises, or unconditional trade instructions.

Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 75 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 6 data sources (tushare, yfinance, okx, akshare, ccxt, futu).

Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them.

Use AKShare, the Python open-source financial data interface library, for source-backed retrieval of public market data, Chinese A-share data, funds, bonds, futures, macroeconomic indicators, financial statements, and other finance datasets. Use when users ask to fetch, validate, refresh, or prototype analysis with publicly available financial data through AKShare, especially for China market workflows, while preserving source citations, interface names, parameters, timestamps, missing-data notes, and strict no-fabrication controls.

Use the iFinD / 同花顺 HTTP API for authenticated, source-backed retrieval of licensed financial market data, including access-token checks, real-time quotation, historical quotation, basic data, date sequence, EDB, announcements, and code conversion workflows. Use when users provide iFinD HTTP API credentials, refresh_token, access_token, or an iFinD API manual and ask to install, test, validate, or use 同花顺 data interfaces while protecting secrets, recording endpoint names, parameters, timestamps, missing data, and strict no-fabrication controls.

Use when building or reviewing China A-share comparable company analysis, peer sets, relative valuation, trading multiples, industry benchmarking, percentile analysis, and peer rejection logs with iFinD, AKShare, filings, RMB units, industry classification, ST or suspension filters, negative denominator handling, and strict source-backed QA.

Use when building or reviewing A-share public company valuation workflows that need market snapshot, trading multiples, historical valuation percentiles, DCF framework, equity value bridge, RMB units, disclosure mapping, iFinD or AKShare data sourcing, missing data handling, and strict no-fabrication QA before producing an investment memo, model framework, or Excel valuation output.

Use when a financial task involves China market securities, A shares, Hong Kong-listed Chinese companies, China market data, RMB financials, Chinese disclosures, iFinD, 同花顺, AKShare, 巨潮资讯, 上交所, 深交所, 北交所, 港交所, industry classifications, adjustment basis, trading calendars, or China-specific data integrity requirements before downstream valuation, DCF, comps, earnings, equity research, or financial modeling skills.

Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "sanity check this", "debug model", "model check", "model won't balance", "something's off in my model", "model review".

Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage. Fast-turnaround format focusing on beat/miss analysis, key metrics, updated estimates, and revised thesis. Includes 1-3 summary tables and 8-12 charts. Use when user requests "earnings update", "quarterly update", "earnings analysis", "Q1/Q2/Q3/Q4 results", or post-earnings report.

Earnings Preview workflow for earnings review. Use when users need to prepare earnings previews, expectations, key debates, scenario framing, questions, and model sensitivities, including source-backed inputs, structured analysis, quality checks, and client-ready deliverables without inventing financial, market, company, accounting, or client data.

Model Update workflow for earnings review. Use when users need to update financial models for new filings, earnings, guidance, estimates, KPIs, and changed assumptions, including source-backed inputs, structured analysis, quality checks, and client-ready deliverables without inventing financial, market, company, accounting, or client data.

Morning Note workflow for earnings review. Use when users need to draft equity research morning notes, market updates, company news summaries, and actionable analyst takeaways, including source-backed inputs, structured analysis, quality checks, and client-ready deliverables without inventing financial, market, company, accounting, or client data.

Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for headless Codex sessions with no open Office app. Use when users need to produce Excel workbooks as file artifacts with formulas, formatting, source notes, model checks, and recalculation guidance in earnings review workflows.

Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "sanity check this", "debug model", "model check", "model won't balance", "something's off in my model", "model review".

Root-cause a reconciliation break to its source transaction or posting — follow the audit trail from the break row back to the originating entry on each side and state what differs and why. Use after gl-recon has classified a break. Use when users need to trace reconciliation breaks, investigate ledger differences, and document root causes and resolving entries in general ledger reconciliation workflows.

Reconcile general ledger to subledger for a trade date or period — match at the position or transaction level, surface breaks, and classify each break by likely cause. Use for daily or month-end recon runs across asset classes. Use when users need to perform general ledger reconciliations, tie balances, explain differences, and prepare close-ready reconciliation support in general ledger reconciliation workflows.

Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for headless Codex sessions with no open Office app. Use when users need to produce Excel workbooks as file artifacts with formulas, formatting, source notes, model checks, and recalculation guidance in general ledger reconciliation workflows.

Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine. Use when users need to parse KYC documents, extract entity details, ownership, sanctions-relevant information, and onboarding evidence in KYC screening workflows.

Apply the firm's KYC/AML rules grid to a parsed onboarding record — assign a risk rating, list every rule outcome with the rule cited, and flag what's missing or escalation-worthy. Use after kyc-doc-parse; this skill decides nothing, it scores and routes. Use when users need to apply KYC rules, screening criteria, escalation logic, risk ratings, and compliance review workflows in KYC screening workflows.

Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for headless Codex sessions with no open Office app. Use when users need to produce Excel workbooks as file artifacts with formulas, formatting, source notes, model checks, and recalculation guidance in KYC screening workflows.

Framework for building competitive landscape decks — market positioning, competitor deep-dives, comparative analysis, strategic synthesis. Use when the user asks for a competitive landscape, competitor analysis, peer comparison, market positioning assessment, strategic review, or investment memo deck. Also triggers on "who are the competitors to X", "benchmark X against peers", "build a market map", or any request to systematically evaluate competitive dynamics across an industry.

Build institutional-grade comparable company analyses with operating metrics, valuation multiples, and statistical benchmarking in Excel/spreadsheet format. **Perfect for:** - Public company valuation (M&A, investment analysis) - Benchmarking performance vs. industry peers - Pricing IPOs or funding rounds - Identifying valuation outliers (over/under-valued) - Supporting investment committee presentations - Creating sector overview reports **Not ideal for:** - Private companies without comparable public peers - Highly diversified conglomerates - Distressed/bankrupt companies - Pre-revenue startups - Companies with unique business models Use when users need to build comparable company analyses, peer sets, operating metric spreads, trading multiples, and valuation summaries in market research workflows.

Idea Generation workflow for market research. Use when users need to generate equity research or market research ideas using screens, sector themes, catalysts, valuation gaps, and risk framing, including source-backed inputs, structured analysis, quality checks, and client-ready deliverables without inventing financial, market, company, accounting, or client data.

Produce a .pptx file on disk (headless) instead of driving a live PowerPoint document — for headless Codex sessions with no open Office app. Use when users need to produce PowerPoint decks as file artifacts with structured slides, charts, tables, branding, and quality checks in market research workflows.

Sector Overview workflow for market research. Use when users need to prepare sector overviews, market maps, trends, peer groups, KPI benchmarks, and investment implications, including source-backed inputs, structured analysis, quality checks, and client-ready deliverables without inventing financial, market, company, accounting, or client data.

Client Report workflow for wealth or client meeting preparation. Use when users need to produce client-ready wealth or advisory reports with portfolio results, allocation views, market commentary, and next actions, including source-backed inputs, structured analysis, quality checks, and client-ready deliverables without inventing financial, market, company, accounting, or client data.

Client Review Prep workflow for wealth or client meeting preparation. Use when users need to prepare client review meetings, agendas, portfolio discussion points, financial planning updates, and follow-up actions, including source-backed inputs, structured analysis, quality checks, and client-ready deliverables without inventing financial, market, company, accounting, or client data.

Investment Proposal workflow for wealth or client meeting preparation. Use when users need to prepare investment proposals with objectives, allocation, manager or security rationale, risks, and implementation plan, including source-backed inputs, structured analysis, quality checks, and client-ready deliverables without inventing financial, market, company, accounting, or client data.

Produce a .pptx file on disk (headless) instead of driving a live PowerPoint document — for headless Codex sessions with no open Office app. Use when users need to produce PowerPoint decks as file artifacts with structured slides, charts, tables, branding, and quality checks in wealth or client meeting preparation workflows.

Complete, populate and fill out 3-statement financial model templates (Income Statement, Balance Sheet, Cash Flow Statement) . Use when asked to fill out model templates, complete existing model frameworks, populate financial models with data, complete a partially filled IS/BS/CF framework, or link integrated financial statements within an existing template structure. Triggers include requests to fill in, complete, or populate a 3-statement model template

Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "sanity check this", "debug model", "model check", "model won't balance", "something's off in my model", "model review".

Build institutional-grade comparable company analyses with operating metrics, valuation multiples, and statistical benchmarking in Excel/spreadsheet format. **Perfect for:** - Public company valuation (M&A, investment analysis) - Benchmarking performance vs. industry peers - Pricing IPOs or funding rounds - Identifying valuation outliers (over/under-valued) - Supporting investment committee presentations - Creating sector overview reports **Not ideal for:** - Private companies without comparable public peers - Highly diversified conglomerates - Distressed/bankrupt companies - Pre-revenue startups - Companies with unique business models Use when users need to build comparable company analyses, peer sets, operating metric spreads, trading multiples, and valuation summaries in financial model building workflows.

Real DCF (Discounted Cash Flow) model creation for equity valuation. Retrieves financial data from SEC filings and analyst reports, builds comprehensive cash flow projections with proper WACC calculations, performs sensitivity analysis, and outputs professional Excel models with executive summaries. Use when users need to value a company using DCF methodology, request intrinsic value analysis, or ask for detailed financial modeling with growth projections and terminal value calculations.

This skill should be used when completing LBO (Leveraged Buyout) model templates in Excel for private equity transactions, deal materials, or investment committee presentations. The skill fills in formulas, validates calculations, and ensures professional formatting standards that adapt to any template structure. Use when users need to build or review LBO models with sources and uses, operating projections, debt schedule, returns, and sensitivities in financial model building workflows.