Self-Improving Agent
一个面向 Automation 场景的 Agent 技能。原始说明:Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
一个面向 Automation 场景的 Agent 技能。原始说明:Open the ClawBuddy LiteKit mission-control dashboard for AI agents — live OpenClaw Gateway status, agent profiles, task board, meeting intelligence, council...
name: clawbuddy-litekit
description: Open the ClawBuddy LiteKit mission-control dashboard for AI agents — live OpenClaw Gateway status, agent profiles, task board, meeting intelligence, council debates, and AI logs. Use when the user wants to visually inspect agents, monitor gateway health, browse agent activity, or set up the OpenClaw integration.
A premium, NASA-style mission-control dashboard for your OpenClaw agents.
Use this skill to launch the dashboard, check Gateway status, or guide the
user through one-click setup.
| Goal | Run |
| --- | --- |
| Open the live dashboard | bash scripts/open-dashboard.sh |
| Check Gateway connection | bash scripts/status.sh |
| Jump straight to setup wizard | bash scripts/open-dashboard.sh setup |
Live: <https://agentcommander.lovable.app>
Local dev: clone <https://github.com/stevekaplanai/clawbuddy-litekit>, thenbun install && bun dev.
ClawBuddy proxies the OpenResponses HTTP API through a Lovable Cloud edge
function. To go live, the user adds two secrets in Lovable Cloud:
OPENCLAW_GATEWAY_URLOPENCLAW_API_KEYThe setup wizard at /setup walks through this in three steps.
See references/openclaw.md for endpoint details.
Stay visual. When the user asks for data the dashboard already surfaces,
prefer launching the relevant tab over re-fetching from the Gateway.