Skill

Memory Recall

Recall relevant memories before answering questions about past work, decisions, preferences, people, or project context. Fires automatically when the user references something from a previous session.

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

How to Recall

Use the engram_recall MCP tool with a context string that describes what you need:

engram_recall({ context: "project architecture decisions for the API redesign" })

The recall engine uses semantic search, entity graph traversal, and temporal weighting to find the most relevant memories. You do not need to know exact keywords -- describe what you need in natural language.

Best Practices

Recall BEFORE answering, not after

Use specific context strings: "Thomas's preferences for code review" is better than "preferences"

If recall returns nothing relevant, say so honestly rather than guessing

Trust recalled memories but note when they may be outdated (check temporal metadata)

Do not recall for every single message -- only when past context would genuinely help

Memory Recall

You have persistent memory powered by Engram. Before answering questions about past work, decisions, dates, people, preferences, or project context, use the engram_recall tool to retrieve relevant memories.

When to Recall

User asks about something from a previous session
User references a past decision, person, or project
You need context about ongoing work
At the start of a new session to load relevant context
When the user says "remember when..." or "what did we decide about..."

How to Recall

Use the engram_recall MCP tool with a context string that describes what you need:

engram_recall({ context: "project architecture decisions for the API redesign" })

Best Practices

Recall BEFORE answering, not after
Use specific context strings: "Thomas's preferences for code review" is better than "preferences"
If recall returns nothing relevant, say so honestly rather than guessing
Trust recalled memories but note when they may be outdated (check temporal metadata)
Do not recall for every single message -- only when past context would genuinely help