Stats
Actions
Tags
From flevinsky-ai
Manage project services declared in .flevinsky-ai/services.json (falls back to .services/.pi/.claude). Subcommands: list, start, stop, restart, logs, run.
How this skill is triggered — by the user, by Claude, or both
Slash command
/flevinsky-ai:services [list|start|stop|restart|logs|run] [name][list|start|stop|restart|logs|run] [name]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Route the user's command to the appropriate `flevinsky-ai` MCP tool.
Route the user's command to the appropriate flevinsky-ai MCP tool.
User arguments: $ARGUMENTS
Behavior:
$ARGUMENTS is empty or list → call services_list.start → call services_start with name = second token.stop → call services_stop with name = second token.restart → call services_restart with name = second token.logs → call services_logs with name = second token (and tail = third token if numeric).run → print: flevinsky-ai run <name> -- <cmd> (the attached runner CLI; not callable from inside Claude Code, only from the user's terminal).Always report the tool's result back to the user verbatim. If the requested service name does not exist in state or in the project's services.json, surface the error from the tool.
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 fabianlevi/flevinsky-ai --plugin flevinsky-ai