stock-screener / contracts
llms.txt417 starsChanged 6 days agoApache-2.0View on GitHub
End-of-day stock screening data for 12 markets (US, CA, DE, HK, CN, JP, KR, TW, IN, SG, MY, AU) from the open-source stock-screener project. It covers preset screens such as Minervini, CANSLIM and VCP, relative-strength ratings, market breadth and industry group rankings. This is educational screening data, not investment advice. There is no intraday data. The data is static JSON published after each market's close. Each publish lives in a new generation folder, so always start from the manifest.
The file
Files
# Stock Screener > End-of-day stock screening data for 12 markets (US, CA, DE, HK, CN, JP, KR, TW, IN, SG, MY, AU) from the open-source stock-screener project. It covers preset screens such as Minervini, CANSLIM and VCP, relative-strength ratings, market breadth and industry group rankings. This is educational screening data, not investment advice. There is no intraday data. The data is static JSON published after each market's close. Each publish lives in a new generation folder, so always start from the manifest. ## Data - [Manifest](https://xang1234.github.io/stock-screener/static-data/manifest.json): The entry point. `data_root` names the current generation folder, and every other path below is relative to `static-data/<data_root>`. `markets.<CODE>` gives each market's `as_of_date`, `features`, `pages` and `assets`. - Scan rows: `markets.<CODE>.pages.scan.path` is a scan manifest with the screen rules in `preset_screens` and the row files in `chunks`. Each chunk's `path` holds `rows`, and together the chunks hold every row. - Track record: `markets.<CODE>.assets.scoreboard.path`, present only for a market with a published record. - [Field dictionary](https://xang1234.github.io/stock-screener/fields.json): The meaning, unit and hard range of every scan row field. Read it before quoting a number, because names mislead: `volume` is traded value rather than shares, and `pct_day` is a percentile rank rather than a percent change. ## MCP server - [stockscreen-mcp](https://github.com/xang1234/stock-screener/tree/main/stockscreen-mcp): Tools over this data, with no API key. Run `uvx stockscreen-mcp`, or `claude mcp add stockscreen -- uvx stockscreen-mcp`. The `stockscreen://skill` resource teaches the workflow and reading rules. ## Optional - [Live site](https://xang1234.github.io/stock-screener/): The same data in a browser. - [Source](https://github.com/xang1234/stock-screener): Code that computes every field.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.