index1 Doctor

Diagnose index1 environment - check Python, Ollama, models, index health.

Security Scan

The skill's requests and runtime instructions match its stated purpose (diagnosing an index1 environment); it is instruction-only and coherent, but it recommends running third‑party installers (pip and a curl | sh) which you should treat with caution.

Purpose & Capability

Name/description (diagnose index1) align with the SKILL.md: it runs index1 diagnostic/status commands and checks Ollama and models. Required resources (none declared) are consistent with an instruction-only diagnostic skill.

Instruction Scope

Instructions are narrowly scoped to running three commands: `index1 doctor`, `index1 status`, and `ollama list`, and interpreting their output. However the document also suggests installing software (via `pip install index1` and `curl -fsSL https://ollama.com/install.sh | sh`) — these are out-of-band actions that will fetch and execute remote code and should be reviewed before use.

Install Mechanism

The skill itself has no install spec (instruction-only). The SKILL.md recommends third-party installers, including a curl|sh installer from ollama.com and installing a pip package; recommending such installs is common but is a higher-risk operation because they execute code fetched from the network.

Credentials

The skill declares no environment variables, credentials, or config paths. The checks it runs legitimately require local environment access (Python, SQLite, local DB size), so the lack of requested secrets is proportional.

Persistence & Privilege

always is false and the skill is instruction-only with no code to persist on the agent. It does not request elevated or persistent privileges.

Assessment

This skill appears to do what it says: run local diagnostic commands for index1 and (optionally) check Ollama models. Before running it, be aware it recommends installing third-party software (pip install index1 and an Ollama install script fetched with curl | sh). Those installers will download and execute code on your machine — inspect installer scripts or prefer official package manager methods, run them in a sandbox or container, and avoid running install scripts as root. Also note the diagnostic commands will report local environment details (Python/SQLite versions, DB sizes, model lists) which may reveal system information; only run if you are comfortable sharing that info with the agent runtime/environment. If you want extra caution, manually run the listed commands yourself or review the installer code before accepting recommendations.

Environment diagnostic skill for index1. Runs health checks and provides fix recommendations.

Usage

Type /doctor or ask the agent to diagnose index1.

What it checks

The skill runs three commands sequentially and analyzes results:

1. Environment Check

index1 doctor

Checks:

• Python version (>= 3.10 required)
• SQLite version (>= 3.43.0 for full features)
• sqlite-vec extension
• ONNX embedding (built-in, bge-small-en-v1.5)
• Ollama connectivity (optional, for multilingual/CJK)
• Embedding model availability
• CJK/Chinese support (jieba)

2. Index Status

index1 status

Shows:

• Document count and chunk count
• Collections list
• Last index time
• Database size

3. Ollama Models

ollama list

Shows installed models. Recommended embedding models:

• nomic-embed-text — Standard, 270MB
• bge-m3 — Best for CJK content, 1.2GB

Interpreting Results

Check	Pass	Fail Fix
Python	>= 3.10	Install Python 3.11+
SQLite	>= 3.43.0	Auto-degrades, no action needed
sqlite-vec	Loaded	pip install index1 (bundled)
Ollama	Connected	curl -fsSL https://ollama.com/install.sh | sh
Model	Available	ollama pull nomic-embed-text
CJK	jieba loaded	pip install index1[chinese]
Index	Has documents	index1 index ./src ./docs

When to use

• First-time setup verification
• After upgrading index1
• When search returns unexpected results
• When vector search stops working
• Before reporting issues