konnect-ai-gateway
Operate Konnect AI Gateway request flow, provider/model routing, AI Proxy behavior, prompt/response controls, and LLM analytics. Use when the issue is inside AI Gateway, not generic prompt engineering, provider SDK debugging, or non-AI Gateway rollout.
Install
With your agent
Install OMGSkills skill "kong/ai-marketplace:plugins/kong-konnect/skills/konnect-ai-gateway" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/Kong/ai-marketplace /tmp/ai-marketplace && ln -s /tmp/ai-marketplace/plugins/kong-konnect/skills/konnect-ai-gateway ~/.claude/skills/konnect-ai-gatewayFrom README
Konnect AI Gateway triage Goal Diagnose the narrowest Konnect AI Gateway failure layer across request path, provider targeting, AI policy, and AI-runtime visibility. Use this skill for AI Gateway operator workflows, not for generic prompt-engineering, provider SDK debugging, or model-quality evaluation. Tool Selection Use the shared kong-konnect MCP server first for live inspection of control planes, Gateway entities, and LLM analytics surfaces. Prefer LLM-specific analytics when the user is asking about token , latency, or AI request health. Use the LLM analytics MCP/query surface when AI-runtime data is the real question rather than generic API analytics. Preserve the repository's chosen declarative toolchain for implementation: deck-gateway for Gateway-entity GitOps, terraform-konnect for HCL-managed Konnect AI Gateway resources, terraform-kong-gateway for self-managed HCL, and kongctl-declarative only when the surrounding Konnect repo already uses that path.