跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Create Agent

技能 已验证 活跃

Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.

目的

Empower users to create specialized AI agents that learn and remember across sessions, enhancing conversational AI and task automation.

功能

  • Create subagents with long-term memory
  • Support for interactive agent creation
  • Ingest content from prepared directories
  • Manage knowledge pages and memory search
  • Integrate with Hindsight memory system

使用场景

  • Building specialized AI agents for complex tasks
  • Developing personalized chatbots with user-specific memory
  • Automating workflows that require learning and adaptation over time
  • Creating AI employees that approximate human learning capabilities

非目标

  • Managing the Hindsight server itself
  • Directly interacting with memory banks outside of agent creation context
  • Providing a generic agent framework not powered by Hindsight

安装

请先添加 Marketplace

/plugin marketplace add vectorize-io/hindsight
/plugin install claude-code@hindsight-local

质量评分

已验证
98 /100
1 day ago 分析

信任信号

最近提交1 day ago
星标13.2k
许可证MIT
状态
查看源代码

类似扩展

Orchestrate

100

Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.

技能
rohitg00

Context Compression

100

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.

技能
muratcankoylan

Wrap Up Ritual

100

End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.

技能
rohitg00

TradeMemory Protocol

100

Evolution Engine 的领域知识 — 支持 LLM 从原始 OHLCV 数据中自主发现策略。涵盖生成-回测-选择-进化循环、向量化回测、样本外验证和策略梯度。在发现交易模式、运行回测、进化策略或审查进化日志时使用。由“evolve”、“discover patterns”、“backtest”、“evolution”、“strategy generation”、“candidate strategy”触发。

技能
mnemox-ai

Agentdb Memory Patterns

99

Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.

技能
ruvnet

Mcp Setup

100

Configure popular MCP servers for enhanced agent capabilities

技能
Yeachan-Heo