From engram
Search and recall memories. Auto-triggered when a topic relates to past discussions or the user asks about previous context.
npx claudepluginhub legacybridge-tech/claude-plugins --plugin engramThis skill uses the workspace's default tool permissions.
Search and retrieve relevant memories from the memory files.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
Search and retrieve relevant memories from the memory files.
This skill is auto-triggered by the Engram hook instructions. Use it when:
Do NOT guess or assume — search memory files first, then respond with confidence.
Read .claude/memory-settings.json to get the configured file names.
From the current conversation context, identify:
Execute searches across all three files simultaneously:
### YYYY-MM-DD entries and their contentCombine findings from all files into a coherent response:
Integrate recalled memories naturally into your response. Examples:
Good: "Based on our previous discussion, you decided to use PostgreSQL for this project. You also mentioned preferring connection pooling via PgBouncer."
Bad: "I searched memory_conversations.md and found an entry from 2025-01-15 that mentions PostgreSQL. I also found in memory_longterm.md under Architecture Decisions..."
The user should feel like you genuinely remember, not like you're reading from a database.