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

name, description

name	description
mem-search	Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

Memory Search

Search past work across all sessions. Simple workflow: search → get IDs → fetch details by ID.

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?"

The Workflow

ALWAYS follow this exact flow:

1. Search - Get an index of results with IDs
2. Timeline - Get context around top results to understand what was happening
3. Review - Look at titles/dates/context, pick relevant IDs
4. Fetch - Get full details ONLY for those IDs

Step 1: Search Everything

curl "http://localhost:37777/api/search?query=authentication&format=index&limit=40"

Required parameters:

• query - Search term
• format=index - ALWAYS start with index (lightweight)
• limit=40 - You can request large indexes as necessary

Returns:

1. [feature] Added JWT authentication
   Date: 11/17/2025, 3:48:45 PM
   ID: 11131

2. [bugfix] Fixed auth token expiration
   Date: 11/16/2025, 2:15:22 PM
   ID: 10942

Step 2: Get Timeline Context

You MUST understand "what was happening" around a result:

# Get timeline around an observation ID
curl "http://localhost:37777/api/timeline?anchor=11131&depth_before=3&depth_after=3"

# Or use query to find + get timeline in one step
curl "http://localhost:37777/api/timeline?query=authentication&depth_before=3&depth_after=3"

Returns exactly depth_before + 1 + depth_after items - observations, sessions, and prompts interleaved chronologically around the anchor.

When to use:

• User asks "what was happening when..."
• Need to understand sequence of events
• Want broader context around a specific observation

Step 3: Pick IDs

Review the index results (and timeline if used). Identify which IDs are actually relevant. Discard the rest.

Step 4: Fetch by ID

For each relevant ID, fetch full details:

# Fetch single observation
curl "http://localhost:37777/api/observation/11131"

# Fetch multiple observations in one request (more efficient)
curl -X POST "http://localhost:37777/api/observations/batch" \
  -H "Content-Type: application/json" \
  -d '{"ids": [11131, 10942, 10855]}'

# Fetch session
curl "http://localhost:37777/api/session/2005"

# Fetch prompt
curl "http://localhost:37777/api/prompt/5421"

Batch fetch options:

# With ordering and limit
curl -X POST "http://localhost:37777/api/observations/batch" \
  -H "Content-Type: application/json" \
  -d '{"ids": [11131, 10942], "orderBy": "date_desc", "limit": 10}'

ID formats:

• Observations: Just the number (11131)
• Sessions: Just the number (2005) from "S2005"
• Prompts: Just the number (5421)

When to use batch:

• Always use batch when fetching 2+ observations
• More efficient: one request vs multiple
• Returns all observations in a single response

Search Parameters

Basic:

• query - What to search for (required)
• format - "index" or "full" (always use "index" first)
• limit - How many results (default 5, max 100)

Filters (optional):

• type - Filter to "observations", "sessions", or "prompts"
• project - Filter by project name
• dateStart - Start date (YYYY-MM-DD or epoch timestamp)
• dateEnd - End date (YYYY-MM-DD or epoch timestamp)
• obs_type - Filter observations by type (comma-separated): bugfix, feature, decision, discovery, change

Examples

Find recent bug fixes:

curl "http://localhost:37777/api/search?query=bug&type=observations&obs_type=bugfix&format=index&limit=5"

Find what happened last week:

curl "http://localhost:37777/api/search?query=&type=observations&dateStart=2025-11-11&format=index&limit=10"

Search everything:

curl "http://localhost:37777/api/search?query=database+migration&format=index&limit=5"

Why This Workflow?

Token efficiency:

• Index format: ~50-100 tokens per result
• Full format: ~500-1000 tokens per result
• 10x difference - only fetch full when you know it's relevant

Clarity:

• See everything first
• Pick what matters
• Get details only for what you need

Error Handling

If search fails, tell the user the worker isn't available and suggest:

pm2 list  # Check if worker is running

---

Remember: ALWAYS search with format=index first. ALWAYS fetch by ID for details. The IDs are there for a reason - USE THEM.