From managelm
Diagnose ManageLM connection errors, offline agents, failing tasks, and missing tools. Invoke when users report issues with their ManageLM setup.
How this skill is triggered — by the user, by Claude, or both
Slash command
/managelm:troubleshootThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Help the user diagnose and resolve ManageLM issues. Work through these checks in order, stopping when the problem is identified.
Help the user diagnose and resolve ManageLM issues. Work through these checks in order, stopping when the problem is identified.
If the user cannot connect or gets authentication errors:
/mcp)."type": "url" in the .mcp.json or Claude Code settings. Check Claude Code version is 1.0.33+.If agents are not appearing or are shown as offline:
search_agents (no args) to check the current state of all agents.systemctl status managelm-agent on the target server.If tasks are failing or returning errors:
get_task_status with the task ID to check the detailed status and error message.get_task_history to see recent tasks for the agent and identify patterns.get_agent_skills to verify the required skill is assigned to the agent.If specific ManageLM tools are not appearing in Claude's toolkit:
/mcp status in Claude Code./reload-plugins to refresh the plugin and MCP connection.list_available_skills to see skills not yet imported, and import them from the portal.get_account_info to check plan limits and current usage.search_agents to filter agents by health, OS, or status when investigating fleet-wide issues.Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub managelm/claude-extension