Uses semantic search to retrieve context and information from previous coding sessions.

Install

mkdir -p .claude/skills/recall && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7830" && unzip -o skill.zip -d .claude/skills/recall && rm skill.zip

Installs to .claude/skills/recall

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Query the memory system for relevant learnings from past sessions
65 charsno explicit “when” trigger
Beginner

Key capabilities

  • Query past session learnings
  • Perform semantic search
  • Retrieve debugging insights
  • Check installation patterns

How it works

The skill runs a semantic search against a vector database of past session learnings to retrieve contextually relevant information.

Inputs & outputs

You give it
Query string
You get back
Relevant past learnings

When to use recall

  • Retrieve past debugging insights
  • Recall previous installation patterns
  • Check project-specific learning history

About this skill

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

When not to use it

  • When the information is not stored in the memory system

Prerequisites

PostgreSQLBGE embeddings

Limitations

  • Depends on stored memory
  • Limited to past session data

How it compares

It use semantic understanding of past interactions rather than simple keyword matching.

Compared to similar skills

recall side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
recall (this skill)16moReviewBeginner
huntly-knowledge-base15moNo flagsIntermediate
braindump75moNo flagsBeginner
super-search102moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry