Stock Screener

List the markets that have published data, so you know which market codes the other tools accept and how fresh each one is. Call this first when the user names a country or exchange, or asks how current the data is. For one market's health, breadth and leading groups, use market_overview instead. Each market returns its code (pass it as `market` to the other tools), name, as_of_date (the trading day the data covers), status ("current"; "late" if it is behind its latest completed session or its next update is over a day overdue; or "unknown"), and features: which of "scan" (run_screen, get_stock, list_screens, audit_stocks), "breadth" (market_overview breadth), "groups" (group_rankings) and "track_record" (screen_track_record) are published for it. unavailable_markets lists markets that failed this publish. Takes no arguments. Results are cached for up to 10 minutes; markets are published after their close by two scheduled runs, one for Asia and one for US/Europe.

Takes no parameters.

Preset screens (Minervini, CANSLIM, VCP, chart patterns, momentum...) with their exact rules. Pass a screen's id to run_screen or audit_stocks.

Define scan fields and count what a market's rows hold for them. Call it before quoting or filtering on a field you have not used, because names mislead: volume is traded value rather than shares, and pct_day is a percentile rank rather than a percent change. Each field returns its group, type, unit and meaning. note says what a reader would otherwise get wrong, range appears only where the code guarantees a hard bound, and alias_of names the row field this name reads. rows_with_value counts this market's rows with a non-null, non-empty value. At 0 the field supports no claim here. It is null for fields the tools drop, which exist only in the published JSON. true_rows appears on boolean fields and counts the rows that are true. values appears on text and list label fields as {label: rows}, most common first, unless the market has more than 15 distinct labels. Filters can test only the text ones. These counts say what this publish holds and not why. They cannot separate a field that cannot be computed from a result where nothing qualified. Internal fields, which are bookkeeping fields and rule names, appear only when named in `fields`. `fields` and `group` together keep the named fields that are in the group.

Run a preset screen and/or custom filters over a market's full daily scan (every listed stock). A preset matches exactly the stocks the project's website shows for it. Filters are combined with AND, including with the preset.

Everything the daily scan knows about one stock: RS ratings, stage, scores, growth, group rank, setup/pattern fields, and which preset screens it currently passes.

Check a watchlist or holdings against the preset screens in one call: which screens each stock passes, and which it nearly passes. Use it to review a list of stocks, find near misses, or see what a position fails today. Use get_stock for every field on one symbol, and run_screen to discover new candidates. A long list over every screen returns a lot of text, so pass a `screens` list when you only need some. Each stock returns a snapshot, `passes` (screen ids in list_screens order, matching the website and get_stock's passes_screens), near_misses, and notes when there are any. The top-level `screens` list minus `passes` gives the failing ids. near_misses maps each screen the stock fails on exactly one of at least two rules to "field short_by N", or to the field alone when short_by is absent. It ignores how far short the stock is, so check short_by before calling one close. short_by is the positive distance between a failed numeric rule's bound and the stock's value (rs_rating 60 against a min of 70 is short_by 10); on a max rule it is how far the value is above the bound (ibd_group_rank 154 against a max of 40 is short_by 114); it is absent when the value is missing and on non-numeric rules. notes maps a screen to the reason when its rules alone don't explain the result: a failing optional rule group, or a disabled required group. detail=True adds failed_rules: every failed rule for each failing screen. Any response over 80,000 characters of JSON is refused with an error that says how many symbols fit, so for detail pass fewer symbols or a shorter `screens` list. Symbols absent from the market's scan are listed in not_found rather than raising an error.

What happened after stocks newly entered each preset screen, at one holding period. Use it to judge how much weight a screen's output deserves, or to see whether a screen has a record yet. Use run_screen for today's matches. Each call reports one horizon; call again with horizon=5 or horizon=60 for the others. Rows in `cohorts` keep the published order, which is not a ranking. how_to_read in each result defines the fields; read it before quoting a number. Any response over 80,000 characters of JSON is refused with an error; pass `screen` for one screen's rows. A market with no published record returns an error naming the markets that have one. In list_markets those markets show the track_record feature.

Market health in one call: exposure score and stance (distribution days, follow-through day, trend), StockBee-style breadth (4% movers, 5/10-day ratios, T2108, 52-week highs/lows), key index/asset moves, and the strongest industry groups.

Rank a market's IBD-style industry groups by their stocks' relative strength (1 = strongest), with 1W/1M/3M/6M rank changes and this week's biggest movers. Use it to find leading or improving industries. Pass `group` (full name, or any part of it that matches only one group) for that group's rank history and its stocks, strongest RS first. For a quick top-5 alongside breadth, market_overview is enough; to filter stocks by group rank, use run_screen with ibd_group_rank. Rankings are end-of-day and update once a day.