Financial Research
firecrawl/web-agent
Pulls a public company's latest 10-K or 10-Q figures and analyst consensus from SEC EDGAR and Yahoo Finance, then cross-checks the two sources.
Free Python scripts that fetch US stock data, SEC filings, insider trades and macro indicators, and run financial score calculators and portfolio analytics.
Install US Market Data Toolkit
$ npx skills add Geeksfino/finskills --skill findata-toolkit-us -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Geeksfino/finskills findata-toolkit-us --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Geeksfino/finskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/US-market/findata-toolkit .claude/skills/findata-toolkit-us && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "findata-toolkit-us" agent skill from https://github.com/Geeksfino/finskills/tree/main/US-market/findata-toolkit into .claude/skills/findata-toolkit-us/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "findata-toolkit-us", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Geeksfino/finskills/tree/main/US-market/findata-toolkitType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Geeksfino/finskills --skill findata-toolkit-us -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Geeksfino/finskills findata-toolkit-us --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Geeksfino/finskills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/US-market/findata-toolkit .agents/skills/findata-toolkit-us && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "findata-toolkit-us" agent skill from https://github.com/Geeksfino/finskills/tree/main/US-market/findata-toolkit into .agents/skills/findata-toolkit-us/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "findata-toolkit-us", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Geeksfino/finskills --skill findata-toolkit-us -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Geeksfino/finskills findata-toolkit-us --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Geeksfino/finskills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/US-market/findata-toolkit .cursor/skills/findata-toolkit-us && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "findata-toolkit-us" agent skill from https://github.com/Geeksfino/finskills/tree/main/US-market/findata-toolkit into .cursor/skills/findata-toolkit-us/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "findata-toolkit-us", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Geeksfino/finskills.git --path US-market/findata-toolkit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Geeksfino/finskills --skill findata-toolkit-us -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Geeksfino/finskills findata-toolkit-us --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Geeksfino/finskills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/US-market/findata-toolkit .gemini/skills/findata-toolkit-us && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "findata-toolkit-us" agent skill from https://github.com/Geeksfino/finskills/tree/main/US-market/findata-toolkit into .gemini/skills/findata-toolkit-us/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "findata-toolkit-us", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Geeksfino/finskills findata-toolkit-usInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Geeksfino/finskills --skill findata-toolkit-us -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Geeksfino/finskills.git skills-src && mkdir -p .github/skills && cp -r skills-src/US-market/findata-toolkit .github/skills/findata-toolkit-us && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "findata-toolkit-us" agent skill from https://github.com/Geeksfino/finskills/tree/main/US-market/findata-toolkit into .github/skills/findata-toolkit-us/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "findata-toolkit-us", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Geeksfino/finskills --skill findata-toolkit-us -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Geeksfino/finskills findata-toolkit-us --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Geeksfino/finskills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/US-market/findata-toolkit .opencode/skills/findata-toolkit-us && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "findata-toolkit-us" agent skill from https://github.com/Geeksfino/finskills/tree/main/US-market/findata-toolkit into .opencode/skills/findata-toolkit-us/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "findata-toolkit-us", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
findata-toolkit-us- GitHub stars
- 282
- Token cost
- ~1.2k tokens
- SKILL.md length
- 433 words
- Files
- 13 (incl. scripts)
- Skills in repo
- 30
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Free Python scripts that fetch US stock data, SEC filings, insider trades and macro indicators, and run financial score calculators and portfolio analytics.
- Works in 6 steps: Stock Data (scripts/stock_data.py) → SEC EDGAR (scripts/sec_edgar.py) → Financial Calculators… → …
- Pulling fundamentals and price history for a US-listed stock
- SKILL.md covers Setup, Available Tools, Data Sources and Output Format, plus 1 more section
- Runs Python scripts from its folder; calls python and pip
What it does
The toolkit is a set of Python scripts run from the skill's root directory after `pip install -r requirements.txt`. `stock_data.py` pulls company info, financial metrics, price history, statements and a value-filter screen through yfinance. `sec_edgar.py` fetches Form 4 insider trades, filings by form type such as 10-K and CIK lookups from EDGAR.
`financial_calc.py` runs DuPont decomposition, Altman Z-Score, Beneish M-Score, Piotroski F-Score, earnings quality and working capital analysis, individually or all at once. The description adds portfolio analytics (VaR, stress testing, health scoring), multi-factor screening and FRED macro indicators, though the excerpt is cut off before those sections. Every data source is free and needs no API keys, and the live data is meant to ground investment analysis.
When your agent uses it
- Pulling fundamentals and price history for a US-listed stock
- Checking recent insider trades or 10-K filings on EDGAR
- Screening a company's financials for bankruptcy or manipulation risk
- Measuring portfolio value at risk with stress tests
Example prompts
- “Get the full financial metrics for AAPL and summarize valuation and debt levels.”
- “Show insider trades for MSFT over the past 90 days.”
- “Run the Altman Z-Score and Piotroski F-Score on AAPL and explain the results.”
- “Screen AAPL, MSFT and GOOGL against value filters.”
Requirements
- Python with the packages in `requirements.txt`
- Network access to Yahoo Finance, SEC EDGAR and FRED data
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 8722415. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 9 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonpip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
US Market Data Toolkit loads about 1.2k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 433 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from Geeksfino/finskills at commit 8722415, republished under its Apache-2.0 licence (© Geeksfino). 433 words, ~1,234 tokens.
Download SKILL.mdSave it as
.claude/skills/findata-toolkit-us/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.- name
- findata-toolkit-us
- description
- Financial data toolkit for US market analysis. Provides scripts to fetch real-time stock data (yfinance), SEC filings and insider trades (EDGAR), financial statement calculators (DuPont, Z-Score, M-Score, F-Score), portfolio analytics (VaR, stress testing, health scoring), multi-factor screening, and macro indicators (FRED). Use when you need live US market data to ground investment analysis. All data sources are free — no API keys required.
- license
- Apache-2.0
FinData Toolkit — US Market
A self-contained data toolkit providing live financial data and quantitative calculations for US market analysis. All data sources are free and require no API keys.
Setup
Install dependencies (one-time):
pip install -r requirements.txtAvailable Tools
All scripts are in the scripts/ directory. Run from the skill root directory.
1. Stock Data (scripts/stock_data.py)
Fetch stock fundamentals, price history, and financial metrics via yfinance.
| Command | Purpose |
|---|---|
python scripts/stock_data.py AAPL | Basic company info |
python scripts/stock_data.py AAPL --metrics | Full financial metrics (valuation, profitability, leverage, growth, analyst consensus) |
python scripts/stock_data.py AAPL --history --period 1y | OHLCV price history |
python scripts/stock_data.py AAPL --financials | Income statement, balance sheet, cash flow |
python scripts/stock_data.py AAPL MSFT GOOGL --screen | Screen stocks against value filters |
2. SEC EDGAR (scripts/sec_edgar.py)
Fetch insider trading data (Form 4), company filings, and CIK lookups.
| Command | Purpose |
|---|---|
python scripts/sec_edgar.py insider AAPL | Recent insider trades |
python scripts/sec_edgar.py insider AAPL --days 90 | Insider trades in last 90 days |
python scripts/sec_edgar.py filings AAPL --form-type 10-K | Recent 10-K filings |
python scripts/sec_edgar.py cik AAPL | Look up CIK number |
3. Financial Calculators (scripts/financial_calc.py)
DuPont decomposition, Altman Z-Score, Beneish M-Score, Piotroski F-Score, earnings quality, and working capital analysis.
| Command | Purpose |
|---|---|
python scripts/financial_calc.py AAPL --all | All calculations |
python scripts/financial_calc.py AAPL --dupont | 5-factor DuPont decomposition |
python scripts/financial_calc.py AAPL --zscore | Altman Z-Score (bankruptcy risk) |
python scripts/financial_calc.py AAPL --mscore | Beneish M-Score (manipulation detection) |
python scripts/financial_calc.py AAPL --fscore | Piotroski F-Score (financial strength) |
python scripts/financial_calc.py AAPL --quality | Earnings quality assessment |
python scripts/financial_calc.py AAPL --working-capital | Working capital & CCC analysis |
Show full SKILL.md (195 more words)Show less
4. Portfolio Analytics (scripts/portfolio_analytics.py)
Portfolio risk analysis: concentration, correlation clusters, VaR/CVaR, stress testing, and health scoring.
| Command | Purpose |
|---|---|
python scripts/portfolio_analytics.py --holdings "AAPL:30,MSFT:25,GOOGL:20,AMZN:15,META:10" | Full health score (0–100) |
... --concentration | Concentration analysis (HHI, sector) |
... --correlation | Correlation clusters & EDR |
... --risk | VaR/CVaR, Sharpe, Sortino, beta |
... --stress | Historical stress testing (5 scenarios) |
5. Factor Screener (scripts/factor_screener.py)
Multi-factor stock scoring: value, momentum, quality, low volatility, size, growth.
| Command | Purpose |
|---|---|
python scripts/factor_screener.py --universe "AAPL,MSFT,GOOGL,AMZN" --top 5 | Screen custom universe |
python scripts/factor_screener.py --sp500-sample --top 10 | Screen S&P 500 sample |
... --factors value,quality | Use specific factors only |
6. Macro Data (scripts/macro_data.py)
US macroeconomic indicators from FRED.
| Command | Purpose |
|---|---|
python scripts/macro_data.py --dashboard | Full macro dashboard |
python scripts/macro_data.py --rates | Interest rates & yield curve |
python scripts/macro_data.py --inflation | CPI, PCE, breakevens |
python scripts/macro_data.py --gdp | GDP & leading indicators |
python scripts/macro_data.py --employment | Unemployment, payrolls, JOLTS |
python scripts/macro_data.py --cycle | Business cycle phase assessment |
Data Sources
| Source | Data | API Key |
|---|---|---|
| Yahoo Finance (yfinance) | Stock quotes, financials, history | Not required |
| SEC EDGAR | Filings, insider trades (Form 4) | Not required |
| FRED | Macro indicators | Not required |
Output Format
All scripts output JSON to stdout for easy parsing. Errors go to stderr.
Configuration
Optional: Edit config/data_sources.yaml to customize rate limits or add API keys for premium data sources.
© Geeksfino, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 12 other files (scripts) in US-market/findata-toolkit of Geeksfino/finskills.
- SKILL.md
- LICENSE.txt
- config/data_sources.yaml
- requirements.txt
- scripts/common/__init__.py
- scripts/common/config.py
- scripts/common/utils.py
- scripts/factor_screener.py
- scripts/financial_calc.py
- scripts/macro_data.py
- scripts/portfolio_analytics.py
- scripts/sec_edgar.py
- scripts/stock_data.py
Open the folder on GitHubat commit 8722415
Compare with similar skills
US Market Data Toolkit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| US Market Data Toolkit this skillGeeksfino/finskills | 282 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Financial Researchfirecrawl/web-agent | 1.2k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Yfinance Datahimself65/finance-skills | 3.4k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Fin Yfinance Datacriptogus/agent-evolve-network | 288 | — | ~806 | Automated safety check: Pass | MIT | |
| Eastmoney Market DataHKUDS/Vibe-Trading | 35k | — | ~1k | Automated safety check: Pass | MIT | |
| SEC EDGAR Filings FetcherHKUDS/Vibe-Trading | 35k | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
Yfinance Data
himself65/finance-skills
Fetch financial and market data with the yfinance Python library (Yahoo Finance).
Fin Yfinance Data
criptogus/agent-evolve-network
Fetch market and fundamental data via the yfinance Python library — quotes, OHLC history, financial statements, holders, dividends, options, and more.
Eastmoney Market Data
HKUDS/Vibe-Trading
Index of Eastmoney's free, no-token market data interfaces for China A-shares and Hong Kong stocks: fund flows, dragon-tiger lists, margin trading, reports and news.
SEC EDGAR Filings Fetcher
HKUDS/Vibe-Trading
Fetches U.S. SEC EDGAR data: resolves tickers to CIK numbers, lists recent 10-K, 10-Q and 8-K filings with document URLs, and pulls XBRL financial series.
Value Stock Screener
okikusan-public/stock_skills
Screens for undervalued stocks across about 60 regions with yfinance's EquityQuery, using ratios such as PER, PBR, dividend yield and ROE, with optional theme filters.
More from Geeksfino/finskills
All 30 skills in this repoFinancial Statement Deep Dive
Geeksfino/finskills
Runs a forensic review of one company's financial statements covering DuPont profitability, earnings quality, financial health scores and fraud-risk signals.
Quantitative Factor Screener
Geeksfino/finskills
Screens a stock universe with a six-factor model, scores value, momentum, quality, low volatility, size and growth, ranks by composite score and notes which factors suit the macro regime.
Tech Hype vs Fundamentals
Geeksfino/finskills
Compares leading tech stocks to separate hype-driven valuations from fundamentally justified ones and to flag undervalued names the market overlooks.
Dividend Aristocrat Calculator
Geeksfino/finskills
Analyze Dividend Aristocrats (25+ years of consecutive dividend increases) for income reliability and total return.
ESG Stock Screener
Geeksfino/finskills
Screens US stocks through an ESG lens, applies optional exclusion lists, scores the environmental, social and governance pillars and judges whether ESG quality is improving.
Event Driven Detector
Geeksfino/finskills
Identify and analyze corporate events that create mispricing opportunities, including M&A, spinoffs, buybacks, restructurings, and index changes.
Related
Categories
Questions about US Market Data Toolkit
What does US Market Data Toolkit do?
Free Python scripts that fetch US stock data, SEC filings, insider trades and macro indicators, and run financial score calculators and portfolio analytics. txt`.py` pulls company info, financial metrics, price history, statements and a value-filter screen through yfinance.
When should I use US Market Data Toolkit?
US Market Data Toolkit fits situations like: pulling fundamentals and price history for a US-listed stock; checking recent insider trades or 10-K filings on EDGAR; screening a company's financials for bankruptcy or manipulation risk; measuring portfolio value at risk with stress tests.
How do I install US Market Data Toolkit in Claude Code?
Run `npx skills add Geeksfino/finskills --skill findata-toolkit-us -a claude-code`. Or copy the skill folder (US-market/findata-toolkit in Geeksfino/finskills) into .claude/skills/findata-toolkit-us in your project. Claude Code loads it when a task matches its description.
How do I install US Market Data Toolkit in Codex?
Run `npx skills add Geeksfino/finskills --skill findata-toolkit-us -a codex`. Or copy the skill folder (US-market/findata-toolkit in Geeksfino/finskills) into .agents/skills/findata-toolkit-us in your project. Codex loads it when a task matches its description.
Can I use US Market Data Toolkit in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Geeksfino/finskills --skill findata-toolkit-us -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/findata-toolkit-us, .gemini/skills/findata-toolkit-us, .github/skills/findata-toolkit-us and .opencode/skills/findata-toolkit-us in your project.
What does US Market Data Toolkit need to run?
Going by SKILL.md and its folder, US Market Data Toolkit needs Python for the scripts in its folder and the command-line tools its instructions call (python and pip). Our summary lists: Python with the packages in `requirements.txt`; Network access to Yahoo Finance, SEC EDGAR and FRED data.
Does US Market Data Toolkit access the network?
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is US Market Data Toolkit safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does US Market Data Toolkit use?
US Market Data Toolkit is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does US Market Data Toolkit use?
About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to US Market Data Toolkit?
Skills that share tags, products or a category with US Market Data Toolkit: Financial Research (firecrawl/web-agent, 1.2k stars), Yfinance Data (himself65/finance-skills, 3.4k stars), Fin Yfinance Data (criptogus/agent-evolve-network, 288 stars) and Eastmoney Market Data (HKUDS/Vibe-Trading, 35k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains US Market Data Toolkit?
Geeksfino (a GitHub user) maintains it in Geeksfino/finskills, which has 282 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on March 5, 2026.
Source: Geeksfino/finskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.