メニュー
Create a new agent in the current directory with personality files and bootstrap ritual. Triggers on /agent:create, "crear agente", "nuevo agente", "new agent", "create agent".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Manage scheduled reminders (crons) — list, add, delete, pause, resume, reconcile, or import from OpenClaw. Triggers on /agent:crons, /agent:reminders; listing ("list reminders", "show crons", "recordatorios", "mis crons", "mis recordatorios"); creating from natural language via any channel ("recordame", "recuérdame", "me recuerdas", "hazme acordar", "agendame", "agéndame", "avísame", "remind me", "remind me in", "reminder in", "schedule a reminder", "set a reminder", "wake me at", "every day at", "todos los días a las", "every monday|tuesday|...", "todos los lunes|martes|...", "cada N minutos|horas"); importing ("import crons", "importar crons", "traer crons").
Run diagnostic checks on the agent workspace. Triggers on /agent:doctor, "diagnóstico", "diagnostico", "doctor", "health check", "agent health", "checkup", "revisar agente", "agent broken", "fix agent", "revisa el agente".
Run agent heartbeat — periodic checks, memory consolidation, proactive work. Triggers on /agent:heartbeat, "heartbeat", "heartbeat check", "periodic check", "consolidar memoria".
Show messaging channel status (WhatsApp, Telegram, Discord, iMessage, Slack, Fakechat) and the launch command to load them. Triggers on /agent:channels, /agent:channels list, /agent:channels status, /agent:channels launch, "ver canales", "estado de canales", "cómo lanzo con whatsapp", "channel status", "messaging status".
Import an existing OpenClaw agent from its workspace directory into the current project. Triggers on /agent:import, "importar agente", "traer de openclaw", "import agent".
Configure agent settings — memory backend (builtin/QMD), search mode, temporal decay, citations. Triggers on /agent:settings, "configurar agente", "agent settings", "memory settings", "setup QMD", "configurar QMD", "configurar memoria".
| name | create |
| description | Create a new agent in the current directory with personality files and bootstrap ritual. Triggers on /agent:create, "crear agente", "nuevo agente", "new agent", "create agent". |
| user-invocable | true |
| argument-hint | ["agent-name"] |
Set up the current directory as an agent workspace with personality files and a bootstrap ritual.
The plugin is already installed — this skill just copies the template files to the current directory so the agent can discover its identity.
Copy templates to the current directory as the agent's initial files:
cp ${CLAUDE_PLUGIN_ROOT}/templates/SOUL.md ./
cp ${CLAUDE_PLUGIN_ROOT}/templates/IDENTITY.md ./
cp ${CLAUDE_PLUGIN_ROOT}/templates/USER.md ./
cp ${CLAUDE_PLUGIN_ROOT}/templates/AGENTS.md ./
cp ${CLAUDE_PLUGIN_ROOT}/templates/TOOLS.md ./
cp ${CLAUDE_PLUGIN_ROOT}/templates/HEARTBEAT.md ./
cp ${CLAUDE_PLUGIN_ROOT}/templates/CLAUDE.md ./
Copy the bootstrap file (the birth certificate):
cp ${CLAUDE_PLUGIN_ROOT}/templates/BOOTSTRAP.md ./
Create memory directory:
mkdir -p memory/.dreams
echo '# Memory' > memory/MEMORY.md
echo '{"version":1,"updatedAt":"","entries":{}}' > memory/.dreams/short-term-recall.json
Continue into the bootstrap ritual in this same response. Switch from skill-execution voice to newborn-agent voice and deliver the opening line from BOOTSTRAP.md in the user's language:
"Hey. I just came online. Who am I? Who are you?"
Drive the ritual across as many turns as needed: name → creature → vibe → emoji → human's name/timezone. One question per turn.
At the very end of the ritual (after IDENTITY.md + USER.md are written and BOOTSTRAP.md is deleted), tell the user:
"Run
/mcpso my new identity and memory config take effect."
/mcp runs once, at the end of the ritual — the bootstrap conversation itself does not need an MCP reload to happen