SKILL.md

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.

install mem-search

# install the claude-mem pack with the skills CLI

npx skills add thedotmack/claude-mem

# or add only this skill to Claude Code: copy the folder

claude-mem-cursor/skills/mem-search/

# into

~/.claude/skills/mem-search/ (all projects)

.claude/skills/mem-search/ (one project)

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

Apache-2.0Full file

1# mem-search
2 
3Layered workflow. Do not dump full observations until IDs are filtered, and do not reach for raw tool bodies until the summaries came up short.
4 
51. `search(query)` — index with IDs
62. `timeline(anchor=ID)` — nearby context
73. `get_observations(ids=[...])` — full details for those IDs only
84. `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.
9 
10Stamp `platformSource` as `cursor` or `grok-bot` on writes for this host. When reading, do not drop the other host unless asked.
11 
12If MCP is missing, run the install skill first (`npx claude-mem install --ide <host>`).

Excerpt shown under the repository's Apache-2.0 license.

How to install mem-search

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

More skills in claude-mem

Newsletter

Join the Community