
PREREQUISITE: Load the following skills:
deepvista-vistabase,deepvista-recipe
Search your knowledge base for relevant context, synthesize it, then run a Recipe workflow with that context as input.
Search for relevant cards: bash
deepvista card +search "your research topic" --limit 10
Read the most relevant cards (pick IDs from search results): bash
deepvista card get <card_id_1>
deepvista card get <card_id_2>
Summarize findings into a context string for the Recipe.
List available Recipes to find the right workflow: bash
deepvista recipe list
Confirm with the user which Recipe to run and what context to pass, then run it: bash
deepvista recipe run <recipe_id> --input "Based on my research: <summary of findings>"
Check run status: bash
deepvista recipe status <run_chat_id>
recipe run) is the only write operation — always confirm with the user before executing it.--input flag focuses the run, it doesn't limit what the agent can see.deepvista chat +send --chat-id <run_chat_id>.捕获经验教训、错误及修正内容,以实现持续改进。适用于以下场景:(1)命令或操作意外失败;(2)用户纠正Claude(如“不,那不对……”“实际上……”);(3)用户请求的功能不存在;(4)外部API或工具出现故障;(5)Claude发现自身知识已过时或不正确;(6)针对重复性任务发现了更优方法。同时,在执行重大任务前应回顾已积累的经验教训。
场景驱动+关键词双模式技能发现工具。当用户用自然语言描述场景/需求(如"我想做一个海报""帮我分析股票"),或明确说"安装技能/find skills/找个skill"时,自动从官方内置、本地已安装、SkillHub、虾评、GitHub、ClawHub 六层联合搜索并推荐最合适的技能,支持一键安装。已完全替代官方...
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。