sec_edgarlisted

# SEC EDGAR Use this skill to answer questions that require SEC EDGAR public company filing or financial data. ## Setup Check whether the agent-gw Python SDK is available in the current Python environment, and install it only if the check fails: ```bash python3 -c "import agent_gw" || python3 -m pip install "$(curl -s https://cdn.kimi.com/agentgw/pysdk/manifest.json | python3 -c "import json,sys; print(json.load(sys.stdin)['latest']['url'])")" ``` The SDK needs an API key from `api_key=...`, `KIMI_API_KEY`, or `~/.kimi/agent-gw.json`. ## Workflow 1. Run `python3 scripts/sec_edgar_tool.py describe` from the plugin directory to call `get_data_source_desc({"name": "sec_edgar"})`. 2. Read the returned Markdown carefully. It contains the overall data source rules, SEC company and filing formats, global constraints, and each API's description, required parameters, optional parameters, defaults, and allowed values. 3. Select the API that best matches the user's question, such as company info, filings, XBRL facts, financial statements, insider trades, institutional holdings, or material company events. 4. Build `params` exactly from the Markdown requirements. Use documented company, ticker, CIK, form type, period, date, accession number, and pagination fields only when the API supports them. 5. Use `python3 scripts/sec_edgar_tool.py call` to call `call_data_source_tool`. 6. If the call fails, explain the failure reason from the response. 7. If the call