Read memories

Skill carlopi/duckdb-claude-skills/skills/read-memories

Search past Claude Code session logs to recover your own context. Invoke this proactively when you need to recall past decisions, patterns, or unresolved work — either across all projects or scoped to the current one.From its SKILL.md

Install

npx -y skills add carlopi/duckdb-claude-skills --skill read-memories

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, 362 tokens by cl100k_base, as published. Nobody here has run it

Use this to recover your own context from past sessions. Do NOT narrate the process to the user — silently run the query, absorb the results, and continue with enriched context.

$0 is the keyword to search for. Pass --here as a second argument ($1) to scope the search to the current project only.

Step 1 — Set the search path

ALL_PROJECTS="$HOME/.claude/projects/*/*.jsonl"
CURRENT_PROJECT="$HOME/.claude/projects/$(echo "$PWD" | sed 's|[/_]|-|g')/*.jsonl"

Use $CURRENT_PROJECT if $1 is --here, otherwise use $ALL_PROJECTS.

Step 2 — 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,
  message.content::VARCHAR 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;
"

Replace <SEARCH_PATH> and <KEYWORD> with the resolved values before running.

Step 3 — Internalize

From the results, extract:

Decisions made and their rationale
Patterns and conventions established
Unresolved items or open TODOs
Any corrections the user made to your prior behavior

Use this to inform your current response. Do not repeat back the raw logs to the user.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.