mem-search
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.
来源信息
- 仓库
- thedotmack/claude-mem
- 最近来源活动
- 2026年9月16日 00:45
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 94,104
- 分支
- 8,302
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- 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.
1. `search(query)` — index with IDs
2. `timeline(anchor=ID)` — nearby context
3. `get_observations(ids=[...])` — full details for those IDs only
4. `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.
The worker also live-writes a growing ID INDEX to `agents/<this-seat-uuid>/memory/log/zz-claude-mem-inject.md` (host Memory mid-attach). Use those IDs with `get_observations`. Thin seat diaries are filled from newest house observations. Disable with `CLAUDE_MEM_GROK_BOT_INJECT_ENABLED=false`.
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>`).
在 GitHub 查看