Skill

Memory Consolidation

Run memory consolidation to distill episodic memories into semantic knowledge. Use at the end of long sessions or when memory quality needs maintenance.

From engram

Install

Run in your terminal

npx claudepluginhub anthropics/claude-plugins-community --plugin engram

Tool Access

This skill uses the workspace's default tool permissions.

Skill Content

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

138.6k

claude-opus-4-5-migration

2 files

Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.

claude-opus-4-5-migration

83.2k

evaluation-methodology

1 file

Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.

plugin-eval

32.9k

Stats

Stars0

Forks0

Last CommitMar 13, 2026

Actions

View Source View Plugin View on GitHub View README

Best Practices

Consolidation is automatic in most setups (fires on session end via hooks)

Manual consolidation is useful after intensive work sessions

Report what was consolidated: "I consolidated 12 episodes into 3 insights about the API redesign"

Do not consolidate too frequently -- let episodes accumulate for better pattern detection

Memory Consolidation

Consolidation distills raw episodic memories (individual conversations, events) into higher-level semantic knowledge (patterns, insights, generalized facts). This keeps your memory lean and high-signal over time.

When to Consolidate

At the end of a long or productive session
When the user asks you to "organize your memories" or "consolidate"
Periodically (every few hours of active use)
You do NOT need to consolidate after every interaction

How It Works

engram_consolidate()

The consolidation engine:

Finds clusters of related episodic memories
Extracts patterns and generalized knowledge
Creates semantic memories that summarize the patterns
Detects and resolves contradictions between memories
Discovers entity relationships

Best Practices

Consolidation is automatic in most setups (fires on session end via hooks)
Manual consolidation is useful after intensive work sessions
Report what was consolidated: "I consolidated 12 episodes into 3 insights about the API redesign"
Do not consolidate too frequently -- let episodes accumulate for better pattern detection