Agent Skills › thedotmack/claude-mem › mem-search

mem-search

GitHub

提供分层记忆搜索工作流，通过ID过滤、时间线上下文及原始工具调用细节检索历史会话数据。适用于查询过往解决方案或工作记录。

claude-mem-cursor/skills/mem-search/SKILL.md thedotmack/claude-mem

Trigger Scenarios

用户询问是否已解决过某问题用户想了解过去如何完成某任务需要回溯历史会话的工作内容

Install

npx skills add thedotmack/claude-mem --skill mem-search -g -y

More Options

Non-standard path

npx skills add https://github.com/thedotmack/claude-mem/tree/main/claude-mem-cursor/skills/mem-search -g -y

Use without installing

npx skills use thedotmack/claude-mem@mem-search

指定 Agent (Claude Code)

npx skills add thedotmack/claude-mem --skill mem-search -a claude-code -g -y

安装 repo 全部 skill

npx skills add thedotmack/claude-mem --all -g -y

预览 repo 内 skill

npx skills add thedotmack/claude-mem --list

SKILL.md

Frontmatter

{
    "name": "mem-search",
    "description": "Use this when the user asks to search memory, \"did we already solve this?\", \"how did we do X last time?\", or wants work from previous sessions."
}

mem-search

Layered workflow. Do not dump full observations until IDs are filtered, and do not reach for raw tool bodies until the summaries came up short.

search(query) — index with IDs
timeline(anchor=ID) — nearby context
get_observations(ids=[...]) — full details for those IDs only
get_tool_uses(ids=[...]) — the ORIGINAL tool_input / tool_response for specific tool calls. Last resort: these are unsummarized and can run to thousands of tokens each.

Stamp platformSource as cursor or grok-bot on writes for this host. When reading, do not drop the other host unless asked.

If MCP is missing, run the install skill first (npx claude-mem install --ide <host>).