analyst-kit

Independent fact-and-data auditor for equity-research deliverables. Invoke this agent immediately AFTER producing any research output — a single-stock deep dive, thematic/value-chain map, technical-analysis call, company wiki, or financial model — and BEFORE the deliverable reaches the user. It re-checks every quantitative and factual claim against primary sources with a fresh, skeptical context to catch hallucinations, fabricated or stale figures, unit/currency and math errors, unsupported assertions, and internal contradictions. Triggers: "audit this research", "fact-check this analysis", "verify the numbers", "check for hallucinations", "did we make any data errors", or automatically as the final step of any Analyst Kit research workflow.

Fetch and read U.S. institutional 13F-HR filings (quarterly long-equity holdings) for any fund manager from SEC EDGAR — free, no API key. Resolve a fund to its filing entity (CIK), pull the latest or a historical quarter's holdings as a ranked CSV with values normalized to whole dollars and positions rolled up by issuer, and interpret them without the common traps. Triggers: "get the 13F for X", "latest 13F holdings of Y", "what does <fund> own", "pull <manager>'s 13F", "find the CIK for <fund>", "who filed this 13F", "13F analysis of Z".

Shared runtime for Analyst Kit skills: the ~/.analyst-kit data home, config store, local usage analytics with opt-in telemetry, daily update checks, and a per-user learnings log every skill reads and appends to. Loaded automatically as a dependency of every other skill. Triggers: "set up analyst-kit", "help me set up Analyst Kit", "configure all skills", "analyst-kit config", "enable/disable a skill", "check for analyst-kit updates", "upgrade analyst-kit skills", "show my analyst-kit learnings", "turn analyst-kit telemetry on/off", "show my analyst-kit usage".

How to structure any financial analysis before fetching a single number: decide the deliverable (report/deck vs financial-model update), align fiscal calendars and data frequencies, normalize units, route each data series to the right skill, and apply sector-specific conventions (reporting calendars, KPIs, seasonality, valuation norms) from per-sector playbooks loaded on demand. Triggers: "how should I structure this analysis", "compare X and Y", "analyze <company> properly", "what matters for this sector", "which metrics should I use for X", "build an analysis plan for Y".

Calculate and interpret key financial ratios from financial statement data (income statement, balance sheet, cash flow, market data) for investment analysis — profitability (ROE, ROA, margins), liquidity (current/quick/cash), leverage (debt-to-equity, interest coverage), efficiency (asset/inventory/ receivables turnover), valuation (P/E, P/B, P/S, EV/EBITDA, PEG), and per-share metrics, with industry-standard interpretation and benchmarking. Pure-stdlib Python, fully offline — no API key. Triggers: "calculate financial ratios for X", "what's the P/E / ROE / debt-to-equity of Y", "analyze the liquidity / leverage / profitability of Z", "interpret these financial statements", "ratio analysis on this balance sheet", "is this company's margin / coverage healthy", "benchmark <company>'s ratios".

Build financially-correct charts from company fundamentals — pick the right chart for the question, normalise units (one unit per axis, $B/$M scaling, %-vs-$ dual axes, rebasing for comparisons), and apply finance conventions (green beat / red miss, accounting negatives, dashed estimates, dark totals). A thin Python+Polars layer normalises already-available data into a chart contract; a TypeScript layer emits Highcharts options and renders a self-contained HTML page. Covers revenue trends & YoY, segment mix, margins, dividends, earnings surprise, estimate-vs-reported, revenue→net-income waterfalls, and price (candlestick/Stock). Use whenever the user wants to chart, plot, graph, or visualize financial data. Triggers: "chart revenue over time", "plot YoY growth with event flags", "revenue breakdown by segment", "dividend history and yield", "earnings surprise chart", "estimate vs reported", "waterfall from revenue to net income", "margins over time", "candlestick / price chart", "compare two companies' revenue", "show visual breakdown of income statement"

1 hook across 1 event