Summon (Grade A)安全测试数据-ai技能for克劳德AI。A级。召唤精神 — 持续.agent进程，可按 schedule或条件运行。与(/loop)不同(/loop), /Summon 设计了专业人员

What limitations should I be aware of when using Summon?

Summon requires a Claude AI environment and proper configuration; specifying complex agent behavior can be challenging, and low‑level control over the agent is limited compared to manual graph edits.

Asked by Hosanna Marte · Oct 30, 2025

What are the main steps in creating a spirit with Summon?

Summon first asks for the spirit’s purpose, generates options based on context (quests, sessions, existing spirits), then creates a reviewable spec before launching the agent via the chosen mode.

Asked by Xavier Costa · Oct 3, 2025

Can Summon run without connecting to the graph database?

Yes. In local mode, Summon bypasses all graph operations, generating and storing the spirit spec in the .spirits/ directory and using CronCreate/CronDelete for scheduling.

Asked by Zain Malik · Sep 13, 2025

How does Summon differ from the /loop command?

Summon uses adaptive questioning to build a reviewable specification for a persistent agent, while /loop is a simple scheduler that requires the user to know the exact task in advance.

Asked by Cristina Moreno · Jul 8, 2025