New to Claude Skills? Learn how to install them →

Get Claude Skills
thedotmack on GitHub

Memory Search

Free

Efficiently retrieve past session data with ease.

by thedotmack90.3k stars on thedotmack/claude-mem
2 views
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Memory Search does

Memory Search is a specialized tool designed for users who need to access and analyze previous work across multiple sessions. This skill is particularly useful when users inquire about past solutions or decisions, such as asking, 'Did we already fix this?' or 'How did we solve X last time?'. By leveraging a persistent cross-session memory database, Memory Search allows users to quickly locate relevant information, making it easier to build on past efforts without redundancy.

The workflow consists of three key steps: search, timeline, and fetch. First, users initiate a search using the search MCP tool to retrieve a list of relevant entries identified by their IDs. This step is crucial as it provides an indexed view of past activities, allowing users to filter results based on specific queries, project names, and other parameters. This initial search is designed to be efficient, returning only essential information like timestamps and titles to minimize token usage.

Once users have identified interesting results, they can use the timeline MCP tool to gain context around those entries. This step interleaves observations, sessions, and prompts related to a specific observation, providing a comprehensive view of the surrounding events. Finally, the get_observations MCP tool allows users to fetch detailed information about selected observations, ensuring that they only retrieve the data they need, which saves both time and resources.

Memory Search is ideal for teams or individuals who frequently revisit past projects or discussions. It streamlines the process of recalling previous work, thus enhancing productivity and collaboration. However, it is important to note that this skill is not intended for real-time conversation contexts; it is specifically designed for referencing past interactions.

When to use it

Use Memory Search when you need to reference or retrieve information from past sessions, especially when users ask about previous solutions or events.

When not to use it

This tool is not suitable for real-time queries or current session discussions, as it focuses solely on historical data retrieval.

What you can build with it

Retrieve past bug fixes

Use Memory Search to quickly find details about bug fixes from previous sessions, ensuring you don't repeat past mistakes.

Understand previous project decisions

Access past discussions and decisions made during project sessions to inform current strategies and approaches.

Analyze trends over time

Examine how solutions and outcomes have evolved by reviewing past observations and sessions related to your projects.

How to install Memory Search

View source

1. Install with the skills CLI

npx skills add thedotmack/claude-mem/mem-search --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by thedotmack

Memory Search

Search past work across all sessions. Simple workflow: search -> filter -> fetch.

When to Use

Use when users ask about PREVIOUS sessions (not current conversation):

  • "Did we already fix this?"
  • "How did we solve X last time?"
  • "What happened last week?"

3-Layer Workflow (ALWAYS Follow)

NEVER fetch full details without filtering first. 10x token savings.

Step 1: Search - Get Index with IDs

Use the search MCP tool:

search(query="authentication", limit=20, project="my-project")

Returns: Table with IDs, timestamps, types, titles (~50-100 tokens/result)

| ID | Time | T | Title | Read |
|----|------|---|-------|------|
| #11131 | 3:48 PM | 🟣 | Added JWT authentication | ~75 |
| #10942 | 2:15 PM | 🔴 | Fixed auth token expiration | ~50 |

Parameters:

  • query (string) - Search term
  • limit (number) - Max results, default 20, max 100
  • project (string) - Project name filter
  • type (string, optional) - "observations", "sessions", or "prompts"
  • obs_type (string, optional) - Comma-separated: bugfix, feature, decision, discovery, change
  • dateStart (string, optional) - YYYY-MM-DD or epoch ms
  • dateEnd (string, optional) - YYYY-MM-DD or epoch ms
  • offset (number, optional) - Skip N results
  • orderBy (string, optional) - "date_desc" (default), "date_asc", "relevance"

Step 2: Timeline - Get Context Around Interesting Results

Use the timeline MCP tool:

timeline(anchor=11131, depth_before=3, depth_after=3, project="my-project")

Or find anchor automatically from query:

timeline(query="authentication", depth_before=3, depth_after=3, project="my-project")

Returns: depth_before + 1 + depth_after items in chronological order with observations, sessions, and prompts interleaved around the anchor.

Parameters:

  • anchor (number, optional) - Observation ID to center around
  • query (string, optional) - Find anchor automatically if anchor not provided
  • depth_before (number, optional) - Items before anchor, default 5, max 20
  • depth_after (number, optional) - Items after anchor, default 5, max 20
  • project (string) - Project name filter

Step 3: Fetch - Get Full Details ONLY for Filtered IDs

Review titles from Step 1 and context from Step 2. Pick relevant IDs. Discard the rest.

Use the get_observations MCP tool:

get_observations(ids=[11131, 10942])

ALWAYS use get_observations for 2+ observations - single request vs N requests.

Parameters:

  • ids (array of numbers, required) - Observation IDs to fetch
  • orderBy (string, optional) - "date_desc" (default), "date_asc"
  • limit (number, optional) - Max observations to return
  • project (string, optional) - Project name filter

Returns: Complete observation objects with title, subtitle, narrative, facts, concepts, files (~500-1000 tokens each)

Examples

Find recent bug fixes:

search(query="bug", type="observations", obs_type="bugfix", limit=20, project="my-project")

Find what happened last week:

search(type="observations", dateStart="2025-11-11", limit=20, project="my-project")

Understand context around a discovery:

timeline(anchor=11131, depth_before=5, depth_after=5, project="my-project")

Batch fetch details:

get_observations(ids=[11131, 10942, 10855], orderBy="date_desc")

Why This Workflow?

  • Search index: ~50-100 tokens per result
  • Full observation: ~500-1000 tokens each
  • Batch fetch: 1 HTTP request vs N individual requests
  • 10x token savings by filtering before fetching

Knowledge Agents

Want synthesized answers instead of raw records? Use /knowledge-agent to build a queryable corpus from your observation history. The knowledge agent reads all matching observations and answers questions conversationally.

Frequently asked questions about Memory Search

Similar skills

Canva Creator

Streamline your content campaign from brief to HubSpot.

Cowork Plugin Customization

Tailor your Claude Code plugin to fit your organization.

Impediment Prioritization

Rank and prioritize impediments effectively.

Chronicle

Streamline your Copilot session analysis and reporting.

Idea Refine

Transform vague ideas into actionable concepts.

App Store Optimization

Optimize your mobile app's visibility and performance.