Recall

This queries a PostgreSQL database with BGE embeddings to surface relevant learnings from previous sessions. You run it when you need to remember how you solved something before, like a specific hook pattern or how you handled a TypeScript error. It returns the top 5 results by default with full content, confidence levels, and session context. The system uses semantic search, so you're not hunting through logs or relying on exact keyword matches. You can tune it with vector-only mode for precision or text-only for speed. Not user-invocable, so it's meant for Claude to reference automatically rather than something you'd call directly. Honestly most useful once you've built up enough session history for the recall to matter.

skills.sh installs: 495
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill recall --agent claude-code

Installs into .claude/skills of the current project.

Files

Recall - Semantic Memory Retrieval

Query the memory system for relevant learnings from past sessions.

Usage

/recall <query>

Examples

/recall hook development patterns
/recall wizard installation
/recall TypeScript errors

What It Does

Runs semantic search against stored learnings (PostgreSQL + BGE embeddings)
Returns top 5 results with full content
Shows learning type, confidence, and session context

Execution

When this skill is invoked, run:

cd $CLAUDE_OPC_DIR && PYTHONPATH=. uv run python scripts/core/recall_learnings.py --query "<ARGS>" --k 5

Where <ARGS> is the query provided by the user.

Output Format

Present results as:

## Memory Recall: "<query>"

### 1. [TYPE] (confidence: high, id: abc123)
<full content>

### 2. [TYPE] (confidence: medium, id: def456)
<full content>