agentleFS
kohojkohoj/skills/market-data/SKILL.md

market-data

Skill1 starsChanged 7 months agoMITView on GitHub

Query market data from Yahoo Finance — prices, fundamentals, earnings, options, dividends, history. Pure data tool for any ticker (US, HK, A-shares, crypto, forex, ETFs). Use before analysis, not instead of it.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every subcommand returns one dimension of data for one or more tickers.

    line 10
  2. Distinctive:

    Before forming or updating a view — get current data, not stale memory

    line 48
  3. Distinctive:

    When the user asks about a stock, price, or financial metric

    line 49
  4. Distinctive:

    When building a briefing or comparison

    line 50
  5. Distinctive:

    When checking if a stored belief still holds

    line 51
  6. Distinctive:

    When the data is already in the conversation and still fresh

    line 56

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Market Data

Data is the raw material of judgment. This tool fetches it. What you do with it — that is analysis, and analysis is your job.

Every subcommand returns one dimension of data for one or more tickers. Combine them as needed. Don't fetch everything when you only need a price.

Usage

.agents/skills/market-data/finance <command> <args>

Commands

CommandPurposeExample
quotePrice, change, market cap, PE, 52W rangefinance quote AAPL 0700.HK
historyOHLCV price historyfinance history TSLA 1y
fundamentalsValuation, margins, debt, analyst targetsfinance fundamentals NVDA
earningsNext date, EPS estimates, past surprisesfinance earnings MSFT
profileSector, industry, employees, descriptionfinance profile GOOGL
dividendsYield, ex-date, payout historyfinance dividends KO
optionsNear-the-money calls and putsfinance options SPY
compareSide-by-side ticker comparisonfinance compare AAPL,MSFT,GOOGL

history periods

1d 5d 1mo 3mo 6mo 1y 2y 5y ytd max — default 1mo.

Symbol format

Any Yahoo Finance ticker works:

  • US: AAPL, MSFT
  • Hong Kong: 0700.HK, 9988.HK
  • A-shares: 600519.SS (Shanghai), 000858.SZ (Shenzhen)
  • Crypto: BTC-USD, ETH-USD
  • Forex: EURUSD=X
  • ETFs: SPY, QQQ
  • Indices: ^VIX, ^GSPC, ^HSI

When to use

  • Before forming or updating a view — get current data, not stale memory
  • When the user asks about a stock, price, or financial metric
  • When building a briefing or comparison
  • When checking if a stored belief still holds

When not to use

  • For news or narrative — use web-search instead
  • When the data is already in the conversation and still fresh

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.