Agent Skills › vectorize-io/hindsight › memory-reflect

memory-reflect

GitHub

基于历史记忆进行推理，回答关于决策、习惯及时间变化的问题。通过调用reflect工具检索并综合不同记忆库的信息，提供准确的历史判断，若信息不足则明确说明。

hindsight-integrations/grok-bot/skills/memory-reflect/SKILL.md vectorize-io/hindsight

触发场景

询问过去的决定或偏好查询特定主题的历史变化需要基于过往经验进行综合判断

安装

npx skills add vectorize-io/hindsight --skill memory-reflect -g -y

更多选项

非标准路径

npx skills add https://github.com/vectorize-io/hindsight/tree/main/hindsight-integrations/grok-bot/skills/memory-reflect -g -y

不安装直接使用

npx skills use vectorize-io/hindsight@memory-reflect

指定 Agent (Claude Code)

npx skills add vectorize-io/hindsight --skill memory-reflect -a claude-code -g -y

安装 repo 全部 skill

npx skills add vectorize-io/hindsight --all -g -y

预览 repo 内 skill

npx skills add vectorize-io/hindsight --list

SKILL.md

Frontmatter

{
    "name": "memory-reflect",
    "description": "Answer questions about history, habits and past decisions by reasoning over Hindsight memory. Use when asked what was decided about something, how something is usually done, what changed over time, or what is known about a topic."
}

Reason over memory

recall returns individual memories. reflect reads across them and answers the question, which is better for anything that needs a judgement over history.

Steps

Call reflect with the user's question on the bank most likely to hold the answer: grok-bot::shared for things about the user or the team, this Bot's bank for its own work, or one of the user's other banks for their work in other tools.
If the answer depends on more than one bank, reflect on each and combine the answers, saying which part came from where.
Give the answer directly. If memory is thin or contradictory, say so rather than filling the gap.