How do I install the Mem Search skill?

Run npx skillmds add majiayu000/mem-search in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Mem Search safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Mem Search?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Mem Search free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Mem Search?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Mem Search by majiayu000 — Agent Skill

Name: Mem Search
Rating: 4.2 (5 reviews)
Author: majiayu000

Mem Search

This skill should be used when the user asks to "search memory", "what do you remember about X", "check claude-mem", "mem search", "find past observations", "what did we do last session", or wants prior-session context about a project, decision, file, or task. Searches the user's Claude-Mem (cmem.ai) memory.

majiayu000 0adee60 2 files · 3.6 KB Updated Sep 9, 2026 567 repo stars

File contents

Claude-Mem Search (Cowork)

Search the user's persistent Claude-Mem memory on cmem.ai. Memory contains timestamped observations synthesized from past sessions across all their agents (Claude Code, Cowork, Codex, and others).

How to search

Run the bundled CLI (no dependencies, uses the plugin's configured API key):

node "${CLAUDE_PLUGIN_ROOT}/scripts/cmem-hook.mjs" search "your query" --limit 20

Progressive search method

Follow claude-mem's Index → Timeline → Transcript discipline — cheap passes first, expensive detail only for confirmed hits:

Index pass — run 1–3 broad keyword searches (project names, file names, error strings, feature names). Skim titles/summaries only.
Narrow pass — re-search with the most specific terms found in step 1 (IDs, exact phrases) and a smaller --limit.
Answer — synthesize from the observations returned. Quote timestamps when the user asks "when".

Do not dump raw search output at the user; extract the relevant observations and answer in plain language.

Diagnostics

If searches return nothing or error:

node "${CLAUDE_PLUGIN_ROOT}/scripts/cmem-hook.mjs" status

Report the status output plainly: a MISSING api key means the plugin needs the user's cmem.ai key added to its configuration; a 404 on /api/hooks/context just means the newer Pro endpoint isn't deployed — search still works via /api/mcp.

Notes

Some filters (date ranges, type) may be silently ignored by the cloud API until MCP parity ships — prefer keyword narrowing over filter flags.
Never write secrets into search queries; queries are sent to cmem.ai.

---name: mem-searchdescription: This skill should be used when the user asks to "search memory", "what do you remember about X", "check claude-mem", "mem search", "find past observations", "what did we do last session", or wants prior-session context about a project, decision, file, or task. Searches the user's Claude-Mem (cmem.ai) memory.--- # Claude-Mem Search (Cowork) Search the user's persistent Claude-Mem memory on cmem.ai. Memory contains timestamped observations synthesized from past sessions across all their agents (Claude Code, Cowork, Codex, and others). ## How to search Run the bundled CLI (no dependencies, uses the plugin's configured API key): ```bash node "${CLAUDE_PLUGIN_ROOT}/scripts/cmem-hook.mjs" search "your query" --limit 20 ``` ## Progressive search method Follow claude-mem's Index → Timeline → Transcript discipline — cheap passes first, expensive detail only for confirmed hits: 1. **Index pass** — run 1–3 broad keyword searches (project names, file names, error strings, feature names). Skim titles/summaries only. 2. **Narrow pass** — re-search with the most specific terms found in step 1 (IDs, exact phrases) and a smaller `--limit`. 3. **Answer** — synthesize from the observations returned. Quote timestamps when the user asks "when". Do not dump raw search output at the user; extract the relevant observations and answer in plain language. ## Diagnostics If searches return nothing or error: ```bash node "${CLAUDE_PLUGIN_ROOT}/scripts/cmem-hook.mjs" status ``` Report the status output plainly: a MISSING api key means the plugin needs the user's cmem.ai key added to its configuration; a 404 on `/api/hooks/context` just means the newer Pro endpoint isn't deployed — search still works via `/api/mcp`. ## Notes - Some filters (date ranges, type) may be silently ignored by the cloud API until MCP parity ships — prefer keyword narrowing over filter flags. - Never write secrets into search queries; queries are sent to cmem.ai.

Frequently asked questions