Exa financial report search

Skill CodeAlive-AI/exa-skills/exa-financial-report-search

Exa web search as standalone Agent Skills — no MCP server, just an EXA_API_KEY. Company, people, papers, code, finance, personal-site & X search + lead generation for Claude Code, Codex, Cursor, OpenCode, Gemini CLI, and any SKILL.md agent.

Install

npx -y skills add CodeAlive-AI/exa-skills --skill exa-financial-report-search

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Find financial filings with Exa — SEC filings (10-K, 10-Q, S-1), earnings reports, and annual reports. Use to pull a company's financials, compare results across periods, or locate a specific filing. Runs a local script against the Exa API; no MCP server required.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.6 KB, as published. Nobody here has run it

Financial Report Search (Exa)

Find SEC filings, earnings, and annual reports via Exa's financial-report index. Calls the Exa REST API through a local script; no MCP server needed, only an EXA_API_KEY.

Setup (once)

export EXA_API_KEY=your-key            # or EXA_API_KEY=... in a .env at the repo root

Get a key at https://dashboard.exa.ai/api-keys. Shared details: exa-native-base.

Run it

python scripts/financial_report_search.py "<company + report type + fiscal year>" [-n N] [--text]

Examples:

python scripts/financial_report_search.py "Nvidia 10-K annual report fiscal 2024 revenue" -n 8
python scripts/financial_report_search.py "Tesla Q3 2025 earnings results guidance" -n 8
python scripts/financial_report_search.py "Stripe S-1 filing prospectus" -c pdf -n 5

Defaults to category=financial report. Encode the report type and fiscal year (10-K, 10-Q, S-1, 8-K, earnings; FY/quarter) — it's the strongest relevance signal.

Query patterns

# Annual / quarterly filings
python scripts/financial_report_search.py "Apple 10-K fiscal 2023 risk factors segment revenue" -n 8

# Earnings & guidance
python scripts/financial_report_search.py "Microsoft Q2 FY2025 earnings call revenue cloud guidance" -n 8

# Primary source on SEC EDGAR
python ../exa-native-base/scripts/exa.py search "Nvidia 10-K 2024" --include-domains sec.gov -n 8

Reading the actual numbers

Search finds the filing; read it to extract figures:

python ../exa-native-base/scripts/exa.py contents <filing-url> --text

For long filings, fetch the specific document (not the index) and pull the line items you need. Distinguish reported figures from estimates, and always cite the filing URL + period.

Override categories with `-c`

financial report (default) · pdf (PDF filings/prospectuses) · news (analyst/press coverage) · company (company profile/context).

After you get results

Prefer primary sources (sec.gov / investor-relations) over secondary commentary for figures.
Treat results as similarity, not validation — confirm the company, period, and figure from the filing itself.
Deliver: the figures with their period and a link to the exact filing; flag any number you couldn't verify in a primary source.