Skills Overview

What skills are

A skill is a named, self-describing data or analytics capability that an AI agent can invoke through the Ithaca MCP server. Skills come in two flavors:

Archive-backed skills read from the Ithaca data archive — a curated, versioned store of market data, fundamentals, congressional trades, insider filings, sentiment, macro indicators, and more. Each result ships with a provenance envelope so the agent (and the human watching the trace) always knows where the data came from and how fresh it is.
Computed analytics skills run trusted numpy/pandas code on archive closes or agent-supplied inputs. They produce derived metrics — volatility, options greeks, correlations, factor exposures, DCF valuations, Monte Carlo paths — without ever executing agent-authored code.

Skills are read-only research tools. They cannot place orders, modify strategies, or touch the money path. Anything that affects capital goes through the approval-gated tools documented in MCP Tools.

Skills vs. direct MCP tools

Ithaca exposes two layers of tools to agents:

Layer	What it is	Example	Provenance envelope	Runtime budget
Direct MCP tools	Core platform operations — sessions, strategy specs, backtests, approvals, artifacts	`session_context`, `propose_strategy`, `backtest_run`	No (operational, not data)	Varies by tool
Skills	Data retrieval + computed analytics over the archive	`market.quote`, `vol.iv_rank`, `congress.trades`	Yes — every result	One of four profiles

Direct tools drive the workflow. Skills feed it with trusted data and derived metrics. An agent typically opens a session with a direct tool, then calls dozens of skills to research a ticker, and finally hands the findings back to a direct tool (propose_strategy) to act.

If a capability exists as a skill, prefer the skill over scraping the web or reasoning from memory. Skills are sourced, fresh, and traceable — agent memory is not.

The provenance envelope

Every archive-backed skill returns its payload wrapped in a provenance envelope. This is what makes Ithaca data trustworthy inside an agent trace: the human can inspect exactly where each number came from.

{
  "skill_id": "market.quote",
  "data": { "symbol": "NVDA", "price": 128.42, "change_pct": 1.83 },
  "provenance": {
    "source": "ithaca-live-data",
    "freshness": { "as_of": "2025-06-27T20:00:00Z", "lag_seconds": 15 },
    "coverage": { "start": "2025-06-27T09:30:00Z", "end": "2025-06-27T16:00:00Z" },
    "cost": { "credits": 1, "tier": "free" },
    "warnings": []
  }
}

Field	Type	Description
`source`	string	Origin of the data — `archive-community`, `ithaca-live-data`, `sec`, `capitol-trades`, `quiver`, `fmp`, `fred`, `computed`
`freshness.as_of`	ISO timestamp	When the underlying record was last refreshed
`freshness.lag_seconds`	int	Wall-clock lag between `as_of` and the most recent source update
`coverage.start` / `end`	ISO timestamp	Time range the result covers
`cost.credits`	int	Credit cost charged to the tenant for this call
`cost.tier`	string	`free`, `basic`, `pro`, `enterprise`
`warnings`	string[]	Non-fatal caveats — stale data, partial coverage, interpolated values, etc.

Always check warnings before acting on a result. A non-empty array means the data is usable but imperfect — for example, a congressional trade filed 90 days late, or a volatility series computed from fewer than 30 closes.

Runtime profiles

Every skill runs under one of four runtime profiles — a hard wall-clock budget that keeps agent sessions responsive and prevents runaway computations.

Profile	Budget	Typical use	Example skills
`interactive`	120 s	Single-ticker lookups during a live research session	`market.quote`, `congress.trades`, `vol.iv_rank`
`scan`	900 s	Universe-wide screens and multi-ticker pulls	`market.screener`, `congress.screener`, `short.screener`
`backtest`	7,200 s	Historical replay over years of closes	`walkforward.run`, `seasonality.heatmap`
`optimization`	14,400 s	Parameter sweeps, Monte Carlo, portfolio optimization	`portfolio.optimize`, `montecarlo.simulate`

If a skill exceeds its budget it returns a timeout warning in the provenance envelope and a partial result (where possible). The agent can then narrow its request or switch to a longer profile explicitly.

How to discover skills

Agents discover skills the same way humans do — by asking the catalog.

search_skills(query: "volatility", limit: 10)

search_skills is a direct MCP tool (see Tools overview) that returns matching skill descriptors:

{
  "query": "volatility",
  "matches": [
    {
      "skill_id": "vol.realized",
      "category": "volatility",
      "description": "Annualized realized volatility from archive closes",
      "runtime_profile": "interactive",
      "cost": { "credits": 1, "tier": "free" }
    },
    { "skill_id": "vol.iv_rank", "category": "volatility", "..." : "..." }
  ]
}

Each descriptor contains skill_id, category, description, runtime_profile, and cost — enough for the agent to pick the right skill and predict its budget without a full call.

Skill catalog

Ithaca ships 50+ skills across nine categories. Use the table below as a map; each category links to a dedicated reference page.

Market data

Skill ID	Source	Description
`market.news`	archive-community	News headlines + sentiment for a ticker or topic
`market.screener`	archive-community	Multi-filter universe screen
`market.movers`	archive-community	Top gainers/losers/most-active by exchange
`market.quote`	ithaca-live-data	Real-time or delayed quote
`market.tide`	archive-community	Aggregate market breadth (advancers/decliners, new highs/lows)

Fundamentals

Skill ID	Source	Description
`fundamentals.get`	fmp	Full fundamentals snapshot for a ticker
`fundamentals.compare`	fmp	Side-by-side fundamentals for multiple tickers
`fundamentals.pit`	sec	Point-in-time fundamentals as of a date
`analyst.ratings`	archive-community	Analyst ratings + price targets

Congress & insider

Skill ID	Source	Description
`congress.trades`	capitol-trades	Individual congressional trade filings
`congress.late_filings`	capitol-trades	Trades filed past the STOCK Act deadline
`congress.screener`	capitol-trades	Filter congressional trades by ticker/party/committee
`insider.activity`	sec	Form 4 insider buys/sells
`politician.portfolio`	capitol-trades	Aggregated holdings for a single politician

Institutional & ETF

Skill ID	Source	Description
`institutional.holdings`	sec	13F institutional holdings
`institutional.flows`	archive-community	Net inflows/outflows by institution or ticker
`etf.holdings`	archive-community	ETF constituent list with weights
`etf.exposure`	archive-community	Factor/sector exposure of an ETF

Sentiment & macro

Skill ID	Source	Description
`sentiment.get`	archive-community	News/social sentiment score for a ticker
`macro.dashboard`	fred	Macro indicator dashboard (CPI, rates, unemployment)
`universe.list`	archive-community	Predefined universes (S&P 500, Russell 2000, etc.)
`economic.calendar`	archive-community	Upcoming economic releases
`fda.calendar`	archive-community	FDA approval dates (biotech catalysts)
`commodity.prices`	archive-community	Spot + futures for commodities
`forex.rates`	archive-community	FX spot rates
`crypto.prices`	archive-community	Crypto spot + 24h volume
`vix.term_structure`	archive-community	VIX futures curve by maturity

Volatility (computed)

Skill ID	Source	Description
`vol.realized`	computed	Annualized realized vol from archive closes
`vol.term_structure`	computed	IV term structure by expiry
`vol.iv_rank`	computed	IV rank and percentile
`vol.vrp`	computed	Variance risk premium (IV − RV)
`vol.anomaly_score`	computed	Z-score of current vol vs. history
`vol.character`	computed	Vol regime classification

Options (computed)

Skill ID	Source	Description
`options.greeks`	computed	Black-Scholes price + delta/gamma/vega/theta/rho
`options.implied_vol`	computed	BS implied vol from observed option price

Computed analytics

Skill ID	Source	Description
`correlation.matrix`	computed	Rolling correlation matrix for a ticker set
`factor.exposures`	computed	Style factor loadings (momentum, value, quality, etc.)
`dcf.value`	computed	Discounted cash flow valuation
`portfolio.optimize`	computed	Mean-variance / risk-parity optimization
`montecarlo.simulate`	computed	Path simulation for a portfolio or strategy
`scenario.project`	computed	Project returns under a named scenario
`risk.stress`	computed	Stress-test P&L under historical shocks
`tearsheet`	computed	Full performance tearsheet (returns, drawdown, ratios)
`walkforward.run`	computed	Walk-forward optimization over a strategy spec
`technical.indicators`	computed	RSI, MACD, ATR, Bollinger, etc. from closes
`seasonality.monthly`	computed	Average monthly returns over N years
`seasonality.heatmap`	computed	Day/month return heatmap

Financials & earnings

Skill ID	Source	Description
`financials.income`	fmp	Income statement (annual + quarterly)
`financials.balance`	fmp	Balance sheet
`financials.cashflow`	fmp	Cash flow statement
`earnings.transcript`	archive-community	Earnings call transcript
`earnings.calendar`	archive-community	Upcoming earnings dates
`dividends`	archive-community	Dividend history + yield
`stock.splits`	archive-community	Split history

Short interest

Skill ID	Source	Description
`short.interest`	archive-community	Short interest + days to cover
`short.volume`	archive-community	Daily short volume ratio
`short.ftd`	sec	Failures to deliver (Reg SHO)
`short.screener`	archive-community	Screen tickers by short interest metrics

Next steps

Market Data Skills

Quotes, screeners, movers, news, and market breadth.

Volatility Skills

Realized vol, IV rank, variance risk premium, and regime classification — all computed from archive closes.

Computed Analytics Skills

Correlations, factor exposures, DCF, portfolio optimization, Monte Carlo, tearsheets, and walk-forward.

MCP Tools

The direct tools that drive sessions, strategies, backtests, and approvals.

​What skills are

​Skills vs. direct MCP tools

​The provenance envelope

​Runtime profiles

​How to discover skills

​Skill catalog

​Market data

​Fundamentals

​Congress & insider

​Institutional & ETF

​Sentiment & macro

​Volatility (computed)

​Options (computed)

​Computed analytics

​Financials & earnings

​Short interest

​Next steps

Market Data Skills

Volatility Skills

Computed Analytics Skills

MCP Tools

What skills are

Skills vs. direct MCP tools

The provenance envelope

Runtime profiles

How to discover skills

Skill catalog

Market data

Fundamentals

Congress & insider

Institutional & ETF

Sentiment & macro

Volatility (computed)

Options (computed)

Computed analytics

Financials & earnings

Short interest

Next steps