Mem Search

Search Session Memory

Search the persistent memory database for past coding observations, decisions, and context.

$ARGUMENTS

How It Works

This skill queries the SQLite FTS5 full-text search index at ~/.softspark/ai-toolkit/memory.db to find relevant observations from past sessions.

Instructions

1. Parse the search query from $ARGUMENTS. If empty, prompt the user for a query.

1. Initialize the database if it does not exist:

``bash python3 "$HOME/.softspark/ai-toolkit/hooks/../plugins/memory-pack/scripts/init_db.py" 2>/dev/null || true ``

1. Run the FTS5 search against the observations table:

``bash sqlite3 ~/.softspark/ai-toolkit/memory.db " SELECT o.id, o.session_id, o.tool_name, o.content, o.created_at, s.project_dir, s.summary FROM observations_fts fts JOIN observations o ON o.id = fts.rowid LEFT JOIN sessions s ON s.session_id = o.session_id WHERE observations_fts MATCH '' ORDER BY rank LIMIT 10; " ` Replace ` with the user's search terms. Escape single quotes by doubling them.

1. Progressive disclosure -- present results in two stages:

Stage 1: Summary view (show first) ```markdown ## Memory Search: ""

Found N results across M sessions.

| # | Session | Project | Tool | Time | Preview | |---|---------|---------|------|------|---------| | 1 | abc123 | /path | Edit | 2025-01-15 | First 80 chars... | ```

Stage 2: Detail view (on request) Show the full observation content, session summary, and related observations from the same session.

1. If no results found, suggest:

• Trying broader search terms
• Checking if memory-pack hooks are installed
• Running init-db.sh if the database is missing

Query Tips

• Use simple keywords: mem-search database migration
• FTS5 supports prefix matching: migrat* matches "migration", "migrate"
• Boolean operators: database AND NOT test
• Column filters: tool_name:Edit to search only Edit tool observations

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: softspark
• Source: softspark/ai-toolkit
• License: MIT
• Homepage: https://softspark.eu

Install and usage instructions live in the source repository linked above.