skills.rest
enigmaicon-eng
enigmaicon-engCOMMUNITY
Explore all skills by this author →
GitHub

mem-search

Search persistent memory entries and fetch full records for selected IDs.

1|Updated May 16, 2026
Search Tags:#knowledge management#token efficiency#memory search#cross-session context#timeline retrieval#search and filter#retrieval workflows
One-click install
npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill mem-search-enigmaicon-eng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mem-search
Source: https://github.com/enigmaicon-eng/AI-Enterprise-OS/tree/main/examples/claude-mem/plugin/skills/mem-search
Command: npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill mem-search-enigmaicon-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of not knowing whether a task, decision, or fix was already handled in earlier sessions, forcing you to recreate context and waste time.

Core Features & Use Cases

  • Cross-session memory search: Locate relevant prior items by querying a persistent memory index instead of relying on the current chat history.
  • Timeline-centered retrieval: Expand around an anchor result to understand surrounding context before pulling full records.
  • Filter-then-fetch workflow: Reduce tokens and noise by searching first, using a timeline to refine relevance, and fetching full details only for selected IDs.

Quick Start

Use the mem-search skill to search the memory database for prior work on authentication, then expand around the best matching result to decide which items to fetch in full.

Frequently Asked Questions about mem-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search cross-session memory to find out if we solved a problem before?▼

Cross-session memory search queries a persistent memory index using a three-layer workflow: search for candidate IDs, anchor on a timeline, and fetch full records only for selected filtered IDs to retrieve prior work efficiently.

What is the best way to reduce token usage when retrieving past session context?▼

To reduce token usage during memory search, apply a strict filter-then-fetch workflow that retrieves candidate IDs first, expands context via a timeline, and fetches complete records only for the final selected IDs.

How does timeline retrieval work for understanding past observations and prompts?▼

Timeline retrieval expands around an anchor result to map surrounding context, allowing you to review chronological observations and prompts before committing tokens to fetch full session records.

Can I use cross-session memory search without relying on current chat history?▼

Yes, cross-session memory search queries a persistent memory index directly, functioning independently of current chat history to locate relevant prior items across past sessions, observations, and prompts.

What are the limitations of the filter-then-fetch retrieval workflow?▼

The filter-then-fetch workflow requires strict adherence to its three-layer process; skipping the timeline anchoring phase or fetching full records before filtering candidate IDs will increase token consumption and reduce retrieval efficiency.

Related Skills

Explore More Data & Analytics Skills→
gyalamanch001agyalamanch001a

mem-search

Search persistent cross-session memory records to recover past work and decisions.

Community
Intermediate
0xBigBoss0xBigBoss
53

extract-transcripts

Extract Claude Code and Codex session JSONL transcripts into Markdown.

Community
Basic
PedroGiudicePedroGiudice
5

mem-search

Search past session observations stored in a local DuckDB memory store.

Community
Basic
the-open-agentthe-open-agent
5.5k

session-logs

Search, filter, and analyze stored chat session logs in JSONL files.

Official
Basic