mcpField
R
recall

recall

github.com/parcadeiAgent workflows3.9k495 installsUpdated 40w ago
Repository

About recall

recall is a Claude Code skill that searches stored learnings from past sessions using semantic retrieval. It returns relevant entries with their type, confidence, and session context.

Key features

  1. 01Semantic search of stored learnings
  2. 02Returns top matching results
  3. 03Shows confidence and session context
  4. 04Supports vector-only or text-only search

Use cases

  1. 01Finding earlier solutions to TypeScript errors
  2. 02Reviewing prior hook development patterns
  3. 03Retrieving notes about installation

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/parcadei/continuous-claude-v3 --skill recall

After installing, type/recallin Claude Code to confirm it loaded.

Details

From the project README

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

  1. Runs semantic search against stored learnings (PostgreSQL + BGE embeddings)
  2. Returns top 5 results with full content
  3. 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>

Options

The user can specify options after the query:

  • --k N - Return N results (default: 5)
  • --vector-only - Use pure vector search (higher precision)
  • --text-only - Use text search only (faster)

Example: /recall hook patterns --k 10 --vector-only

Comments

Markdown supported