Historical Guide

This skill appears to do what it says: it calls an LLM to produce persona-style museum commentary and will store generated persona JSON files under references/. Before installing or running it: 1) Ensure API_BASE points to a trusted model endpoint and only provide API_KEY to services you trust; anything sent to the model provider may be logged/retained by that provider. 2) Be aware that the skill will save generated persona files to the local references/ directory (persistence); inspect those files if you need to remove persisted content. 3) The package metadata in the registry incorrectly shows no required env vars / a malformed config path — rely on SKILL.md and scripts/api_config.py which expect API_KEY, API_BASE, MODEL_NAME or scripts/config.json. 4) Running the code executes subprocesses and network calls (requests) — run in an environment you control and audit the scripts if you require higher assurance. 5) If you plan to allow the skill to run autonomously, note it will invoke the configured model endpoint and may generate and store personas; consider limiting its privileges and using a least-privilege API key. If you want me to, I can list exact lines that perform network calls, file writes, and subprocess execution for manual review.