Skill

read-memories

Searches past Claude Code session logs to recall decisions, patterns, or unresolved work. Useful when users reference prior conversations, say 'do you remember', or need historical context.

Bash

developer-tools

npx claudepluginhub duckdb/duckdb-skills --plugin duckdb-skills

Tool Access

This skill is limited to using the following tools:

Bash

Preview

Search past session logs silently — do NOT narrate the process. Absorb the results and continue with enriched context.

SKILL.md

Similar Skills

read-memories

Searches past Claude Code session logs for keywords to recover context like decisions, data paths, CRS info, model configs, and unresolved work across projects or scoped to current one.

2 tools

geoai-skills

remind

Searches Claude Code conversation history in Scribe DB (SQLite FTS5) or JSONL files to recall past discussions, decisions, code snippets, and context from prior sessions.

1 file

bopen-tools

echo

307

Recalls details from past Claude Code sessions using semantic vector search in LanceDB, SQLite keyword search, and recent session queries. Activates on 'recall', 'remember', 'last session', 'continue from'.

3 files

memstack

Stats

Stars412

Forks21

Last CommitMar 30, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

duckdb :memory: -c " SELECT regexp_extract(filename, 'projects/([^/]+)/', 1) AS project, strftime(timestamp::TIMESTAMPTZ, '%Y-%m-%d %H:%M') AS ts, message.role AS role, left(message.content::VARCHAR, 500) AS content FROM read_ndjson('<SEARCH_PATH>', auto_detect=true, ignore_errors=true, filename=true) WHERE message::VARCHAR ILIKE '%<KEYWORD>%' AND message.role IS NOT NULL ORDER BY timestamp LIMIT 40; "

Search past session logs silently — do NOT narrate the process. Absorb the results and continue with enriched context.

$0 is the keyword. Pass --here as $1 to scope to the current project only.

Step 1 — Query

duckdb :memory: -c "
SELECT
  regexp_extract(filename, 'projects/([^/]+)/', 1) AS project,
  strftime(timestamp::TIMESTAMPTZ, '%Y-%m-%d %H:%M') AS ts,
  message.role AS role,
  left(message.content::VARCHAR, 500) AS content
FROM read_ndjson('<SEARCH_PATH>', auto_detect=true, ignore_errors=true, filename=true)
WHERE message::VARCHAR ILIKE '%<KEYWORD>%'
  AND message.role IS NOT NULL
ORDER BY timestamp
LIMIT 40;
"

Search paths:

All projects: $HOME/.claude/projects/*/*.jsonl
Current only (--here): $HOME/.claude/projects/$(echo "$PWD" | sed 's|[/_]|-|g')/*.jsonl

Replace <SEARCH_PATH> and <KEYWORD> before running.

Step 2 — Internalize

From the results, extract decisions, patterns, unresolved TODOs, and user corrections. Use this to inform your current response — do not repeat raw logs to the user.