aifolimizer

Run a parallel bull/bear adversarial research pipeline on a specific ticker. Use when the user asks for "adversarial research", "bull bear analysis", "deep research on [ticker]", a bull-bear debate on X, or wants a rigorous debate-style investment thesis. (Bare "should I buy X?" belongs to pre-trade-check.) Then spawns parallel sub-agents over live data.

Monthly rebalance + DCA prompt for the long-term core ETF sleeve only (broad-market index ETFs) - NOT single-stock adds (use cash-deployment) and NOT max-Sharpe reweighting (use optimize-allocation). Use when the user asks "should I rebalance?", "where should I deploy my paycheck?", "DCA recommendation", "is my allocation drifting?", "auto-invest plan", or on the 1st of each month. Computes target vs actual core allocation, suggests DCA amount per ETF, accounts for tax-account routing.

Plan how to deploy uninvested cash across existing portfolio holdings. Use when the user asks "where do I put my cash?", "I have $X to invest", "deploy my cash", "what should I buy with my settled funds?", or "add to my best names". Routes capital to existing tickers ranked by setup quality and avoids concentration pile-on. Fetches portfolio + technicals + fundamentals via aifolimizer MCP.

Run a one-shot morning portfolio digest that ties together health, alerts, macro regime, crowding risk, concentration, and earnings calendar into a single decision-ready brief. Use when the user asks for "morning briefing", "daily digest", "what's happening today?", "what changed overnight?", or "give me the morning rundown". Composes existing MCP tools - no new data sources.

Harvard Endowment-style dividend income analysis - yield, payout-ratio safety, DRIP projection, and tax-account placement for income holdings. Use when the user asks about dividends, passive income, DRIP, yield, payout ratio, dividend safety, or "what should I hold for income?".

Run a JPMorgan-style pre-earnings analysis on a specific ticker. Use when the user asks about an upcoming earnings report, "should I hold through earnings?", "what's the expected move?", or names a stock and earnings in the same query. Fetches portfolio via aifolimizer MCP.

Analyze employer / equity-plan stock (shares held via an employer equity plan, RSUs, ESPP) as a SEPARATE concentration and wealth problem from the rest of the portfolio. Use when the user mentions employer stock, RSUs, ESPP, vesting, an equity-plan platform, "my company shares", or asks "should I keep / sell / trim my employer stock". Treats single-employer exposure as the dominant long-term risk it usually is.

Self-diagnostic for the aifolimizer harness wiring. Use when something is silently broken or before relying on the system - "is everything working?", "health check", "why is the MCP not responding?", "check my setup", "diagnose aifolimizer". Audits MCP server, services, WS token freshness, hooks. Catches stale-token / unregistered-MCP / broken-hook silent failures.

Run a McKinsey-style macro economic impact briefing on the user's portfolio. Use when the user asks about rate impact, inflation, CAD/USD, recession risk, Fed/BoC policy, or how macro affects their holdings.

Scan portfolio holdings for 12-month price momentum and 52-week high proximity. Use when user asks "which stocks have momentum?", "rank my holdings by performance", "momentum scan", "12-month winners and losers", "52-week high analysis", "which momentum laggards should I trim?", or "show momentum signals".

Mean-variance (max-Sharpe) portfolio optimization over individual holdings. Use when the user asks "what are the optimal weights?", "how should I reweight?", "rebalance for best risk-adjusted return", "efficient frontier", "which positions to add/trim". For the active trading/holdings bucket - NOT the boring-core DCA sleeve (use auto-rebalance for that).

Run a BlackRock-style portfolio health analysis. Use when the user asks about portfolio health, allocation review, rebalancing, or asks "how is my portfolio doing?". Produces a point-in-time health snapshot (scores + flags), NOT a per-name decision table (use portfolio-review for that).

Whole-portfolio periodic review that produces ONE unified holdings decision table (Buy/Hold/Trim/Sell/Avoid per name) plus watchlist ranking, a keep-what-works list, and a tax/date-aware execution sequence. Use for "full portfolio review", "go through all my holdings", "what should I do across everything", "monthly review", "rebalance my whole book". Long-term-first; not a single-name desk pass (use trading-desk for one ticker) and not the daily digest (use daily-briefing).

Review a holding (or sweep top holdings) and return a HOLD / TRIM / SELL verdict with entry/stop/target. Routes each name to the right analysis - earnings-analyzer if earnings are imminent, earnings-postmortem if it just reported, the adversarial bull/bear pipeline for high-conviction names, lighter stock-analysis otherwise. Use when the user asks "should I hold or sell X", "review my NVDA position", "review my top holdings", "position review", or for an automated nightly top-holdings sweep (the unqualified whole-book "review my holdings" belongs to portfolio-review). Logs each verdict for forward tracking.

Forced discipline gate before any discretionary buy or sell. Use BEFORE placing any trade - intraday, swing, or position. Triggers on "should I buy X?", "thinking about X", "going to enter X", "is now a good time for X?", "I want to buy X", "saw X on twitter", "X is ripping". Refuses approval when FOMO, sizing, or stop-discipline rules are violated.

Capture or update the user's personal-finance context (age, province, salary, monthly expenses, contribution room RRSP/TFSA/FHSA, FTHB horizon, ESPP details, IOUs, debts, insurance, external crypto). Use when the user says "set up my profile", "personalize advice", "tell aifolimizer about me", "update my context", "I have new information", or whenever a downstream skill returns generic advice because get_personal_context.present is false. All fields optional.

Bridgewater-style portfolio risk assessment - correlation and factor concentration, VaR / recession stress test, tail-risk scenarios, and hedges. Use when the user asks about risk, drawdown, concentration, correlation, stress test, factor exposure, or hedging.

Run a Renaissance-style sector rotation and pattern analysis. Use when the user asks about sector trends, "what sectors should I overweight?", money flows, sector leadership, or institutional positioning.

Run a Goldman Sachs + Citadel combined fundamental and technical analysis on a specific ticker - a quick analytical deep-dive. Use when the user asks about a specific stock, wants a deep dive, or asks for entry/exit points. For a full bull/bear multi-agent debate hand off to adversarial-research.

Run a head-to-head comparison between two tickers (A vs B) for a growth, income, or value investor over a stated horizon. Use when the user asks "X vs Y", "which is better A or B?", "should I pick X or Y?", or wants a side-by-side fundamentals + technicals + valuation matchup.

Surface the top N actionable trade ideas for today across holdings + watchlist, each with entry, stop, target, R:R and conviction. Use when the user asks "top trades today", "what should I trade today", "best entries right now", "top stock picks", or wants a ranked, decision-ready trade shortlist. Composes get_trade_ideas + crowding + macro guards. One-shot.

End-to-end institutional trade pipeline with a hard Portfolio-Manager approve/reject gate. Use when the user wants a full desk workup before committing real money - "run the full process on X", "desk review for X", "take X through the whole pipeline", "should I actually buy X - do it properly". Chains research → risk gate → pre-trade discipline → trade ticket, and REFUSES to emit a ticket on reject.

Brutally honest weekly performance mirror. Use every Sunday or when the user asks "how am I doing?", "weekly review", "am I making money?", "show me my track record", "should I keep trading?". Surfaces real win rate, average win/loss R-multiple, trading P&L vs boring-core P&L, and recommends continue / cool-off / suspend.

Run a post-earnings report breakdown on a specific ticker - beat/miss vs consensus, last 4 quarters trend, management guidance shift, and "does the result change my thesis?". Use when the user pastes an earnings report, asks "did X beat?", "what did Y report?", "how did earnings go?", or names a stock with words like "reported", "earnings call", "Q1 results". Fetches portfolio via aifolimizer MCP.

Track Post-Earnings Announcement Drift (PEAD) across ALL portfolio holdings - which held names beat/missed last quarter and are still drifting in the surprise direction. Use for "post-earnings-surprise drift", "is PEAD still active for X?", "which holdings are still drifting after earnings?", "earnings beats still drifting", "earnings-drift overlay across my book". This is a whole-book drift scan - NOT a single-name post-report verdict (use earnings-postmortem) and NOT price-momentum ranking (use momentum-scanner).

Capture the psychological side of a trade - emotion, conviction source, confidence, and plan adherence - at entry and exit, then surface which felt-states actually lose money. Use when the user says "journal this trade", "log my entry", "I just bought/sold X", "reconcile my trade", "trade journal", "why do I keep losing", "what's my real psychological pattern", or wants emotional/behavioral review of their trading. Pairs with pre-trade-check (entry) and weekly-mirror (review).

Canadian tax-loss harvesting review. Use when the user asks about tax-loss harvesting, "should I sell my losers?", capital losses, superficial loss rules, or year-end tax moves. Fetches loss candidates via aifolimizer MCP.

Profile and optimize backend hotpaths (FastAPI handlers, MCP tools, services, caching layers) for latency, memory, and throughput. Use when the user asks "why is X slow?", "optimize Y", "this endpoint is slow", "reduce memory", "speed up the MCP server", or names a specific tool/route and complains about performance. Refuses to optimize code that's already fast enough or where the rewrite is not measurably better than the original.