Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Updated installation method in metadata from "uv" to "pip" for compatibility. - Streamlined and condensed SKILL.md documentation for easier onboarding. - Clarified setup steps, proxy usage, CLI commands, and configuration. - Kept technical details and supported engines concise while preserving links and core instructions.
What This Skill Does
A transparent proxy that sits between your application and any LLM provider, evaluating every response against plain-English rules before output reaches users. Rules are defined in YAML and cover hallucinations, PII leaks, prompt injection, and multi-turn workflow violations. Any OpenAI-compatible client works with it without code changes.
Because it operates at the proxy layer, any OpenAI-compatible client gets policy enforcement without modifying application code.
When to use it
- Blocking PII leaks in customer-facing chatbots
- Enforcing multi-step refund workflows in support agents
- Catching hallucinated citations before they reach end users
- Detecting prompt injection attempts in user-facing AI tools
- Auditing model responses against internal company policy rules
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'What are the internal pricing tiers for enterprise plans?'
- 1Client sends request to proxy at localhost:4000 instead of the LLM provider directly
- 2Proxy forwards the request to the configured LLM and receives the response
- 3Judge engine evaluates the response asynchronously against the active policy rules
- 4Proxy detects that the response contains restricted internal pricing information
- 5Response is blocked before it reaches the user
Request is blocked; the user does not receive the restricted pricing information
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.