zotpilot

# ZotPilot > All script paths are relative to this skill's directory. ## Step 1: Check readiness **Python command:** Use `python3` on Linux/macOS. On Windows, use `python`. Run: `python3 scripts/run.py status --json` (Windows: `python scripts/run.py status --json`) Parse the JSON output and follow the FIRST matching branch: 1. Command fails entirely → **Prerequisites** (see `references/setup-guide.md`) 2. `config_exists` is false → **First-Time Setup** (see `references/setup-guide.md`) 3. `errors` is non-empty → **First-Time Setup** (note: `warnings` like API key not in env are OK if key was passed to `register`) 4. `index_ready` is false or `doc_count` is 0 → go to **Index** below 5. All green → go to **Research** **Inline fallback** (if agent cannot access references/): ```bash python3 scripts/run.py setup --non-interactive --provider gemini python3 scripts/run.py register # Restart your AI agent, then ask again. ``` If any errors: run `python3 scripts/run.py doctor` for diagnostics. ## Index (if doc_count = 0) MCP tools are now available. Index the user's papers: ```bash python3 scripts/run.py index ``` Indexing takes ~2-5 seconds per paper. Documents over 40 pages are skipped by default. After indexing, check for "Skipped N long documents" — offer to index them with `--max-pages 0`. ## Research (daily use) ### Tool selection — pick the RIGHT tool first | User intent | Tool | Key params | |---|---|---| | Find specific passages or evidence | `search_papers` ...