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。

Hindsight Memory Skill

技能 已验证 活跃

Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user)

目的

To empower AI agents with persistent memory, enabling them to learn from past tasks and user interactions to provide more informed and personalized assistance.

功能

  • Store structured facts and entities
  • Recall relevant context proactively
  • Reflect on memories to synthesize insights
  • Support for multiple LLM providers
  • Local and Dockerized deployment options

使用场景

  • Personalizing AI chatbots with user-specific memories
  • Enabling AI agents to learn from past task outcomes and failures
  • Automating complex tasks by recalling previous successful procedures
  • Building AI employees that adapt behavior based on user feedback

非目标

  • Simply recalling raw conversation history
  • Acting as a generic knowledge base without learning
  • Replacing core LLM functionality
  • Managing project files or code

工作流

  1. Configure Hindsight daemon (CLI or Docker)
  2. Retain memories with rich context
  3. Recall relevant memories before tasks
  4. Reflect on memories for deeper insights

实践

  • Memory management
  • Agent learning
  • Data structuring

先决条件

  • Hindsight embed CLI configured
  • LLM provider and API key

安装

npx skills add vectorize-io/hindsight

通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。

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

Learner Skill

99

Extract a learned skill from the current conversation

技能
Yeachan-Heo

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