Stock AI Analyzer

This package mostly does what it claims (fetch Tushare data, compute ratios, and send analysis prompts to an AI model). Key points before installing/using: - Metadata mismatch: the registry lists no required env vars, but the SKILL.md and code require TUSHARE_TOKEN and an AI model configuration (OPENAI_API_KEY or LLM_* or OPENCLAW_MODEL_ENDPOINT). Do not assume no secrets are needed. - Secrets handling: provide TUSHARE_TOKEN and any model API keys only to trusted environments. The skill will send stock and financial data (and the constructed prompts) to whichever AI endpoint you configure — ensure that endpoint is trusted and that sending this data is acceptable. - .env behavior: the data fetcher will read a .env file in the current working directory for TUSHARE_TOKEN if ENV not set. Ensure you do not leave sensitive tokens in world-readable files in that directory. - Dependencies and execution: the bundle contains Python scripts that import tushare, pandas, numpy; you'll need to install these yourself. Review the code locally before running and run in an isolated environment if you are unsure. - Provenance: the skill's source/homepage is unknown. If you require higher assurance, ask the publisher for a homepage or source repository, or review the full code locally and run in an isolated environment. If you proceed, set only the minimal required env vars in a controlled environment, confirm the AI endpoint is trusted, and inspect the scripts yourself (especially network-calling ai_client.py and data_fetcher.py) before running.