Autonomous long-running development from specifications. Use when user wants to build an application from a spec file, run continuous development, or automate feature implementation. Triggers on phrases like "marathon this", "build from spec", "autonomous development", "keep coding until done".
Autonomous long-running development from specifications. Triggers on phrases like "marathon this", "build from spec", or "keep coding until done" to create Linear projects and systematically implement features with continuous verification.
/plugin marketplace add gruckion/marathon-ralph/plugin install marathon-ralph@marathon-ralphThis skill inherits all available tools. When active, it can use any tool Claude has access to.
This skill enables autonomous, long-running development sessions that:
Activate this skill when the user:
/marathon-ralph:run
Or naturally: "Continue the marathon" or "Keep going"
/marathon-ralph:run path/to/spec.md
Or naturally: "Marathon this spec.md until complete"
/marathon-ralph:status
Or naturally: "How's the marathon going?"
/marathon-ralph:cancel
Or naturally: "Stop the marathon"
User must have Linear MCP configured:
claude mcp add --transport http linear https://mcp.linear.app/mcp/mcp - Select Linear and authenticate via OAuthUser: "Marathon this todo-app-spec.md until it's done"
/marathon-ralph:run --spec-file todo-app-spec.mdUser: "How far along is the marathon?"
/marathon-ralph:statusUser: "Stop the marathon, I need to change the spec"
/marathon-ralph:cancelMarathon state is stored in .claude/marathon-ralph.json in the project root. This tracks:
The Stop hook reads this state to determine whether to continue autonomous operation or allow exit.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.