Read memories

Skill stackql/stackql-skills/skills/read-memories

Claude Code plugin for querying cloud infrastructure and SaaS APIs using SQL with StackQL

Install

npx -y skills add stackql/stackql-skills --skill read-memories

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

One thing to look at

0 stars0 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.

What its author says it does

Copied from the file, not written here

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.

SKILL.md

1.7 KB, 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

Use grep to search through the JSONL session logs:

grep -r -l "<KEYWORD>" <SEARCH_PATH> 2>/dev/null

Then for each matching file, extract relevant context:

grep -i "<KEYWORD>" <FILE> | head -40

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

Step 3 - Handle large result sets

If Step 2 returns more than 40 matches or the output is very large, narrow down:

Add more specific search terms
Scope to the current project with --here
Filter by date if relevant

Step 4 - 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.