Stats
Actions
Tags
From synix
Persistently stores and retrieves cross-session context via MCP server. Search prior work, ingest meeting notes, and get synthesized summaries of identity, projects, and priorities.
How this skill is triggered — by the user, by Claude, or both
Slash command
/synix:memoryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You have access to persistent cross-session memory via the `synix` MCP server. This memory survives across conversations and is shared across all projects.
You have access to persistent cross-session memory via the synix MCP server. This memory survives across conversations and is shared across all projects.
Call search(query) with a descriptive query. Results include episodes (session summaries), research threads, and synthesized context.
Call ingest(bucket, content, filename):
bucket="documents" — notes, specs, memos, analysisbucket="reports" — structured reports, summariesUse descriptive filenames: call-receipt-benjamin-2026-04-03.md, decision-architecture-reset.md
Call get_context() to retrieve the full synthesized context document. This is a living summary of identity, current work, priorities, and recent activity. Use this when you need the big picture.
Call list_buckets() to see all configured ingestion endpoints.
npx claudepluginhub marklubin/synix --plugin synixPROACTIVELY query Forgetful MCP (mcp__forgetful__* tools) when starting work on any project, when user references past decisions or patterns, when implementing features that may have been solved before, or when needing context about preferences. Save important decisions, patterns, and architectural insights to memory.
Full-text search and management of past work, memories, project history, and session notes with token-efficient browsing.
Guides efficient use of context-mem MCP tools: compress large outputs, search before re-reading files, persist knowledge across sessions, and manage token budget.