skills.rest
hiddink-ai
hiddink-aiOFFICIAL
Explore all skills by this author →
GitHub

memory-save

Save session context with tasks, decisions, and code changes to claude-mem.

1|Updated May 21, 2026
Search Tags:#workflow#documentation#context#memory#persistence#session
One-click install
npx skills add https://github.com/hiddink-ai/hiddink-harness --skill memory-save-hiddink-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-save
Source: https://github.com/hiddink-ai/hiddink-harness/tree/main/templates/skills/memory-save
Command: npx skills add https://github.com/hiddink-ai/hiddink-harness --skill memory-save-hiddink-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the issue of context loss during long-running AI sessions by providing a structured way to save tasks, decisions, and code changes to a persistent memory store.

Core Features & Use Cases

  • Context Snapshotting: Automatically aggregates completed tasks, key decisions, and open items into a structured memory object.
  • Custom Metadata: Allows users to attach specific tags to memories for easier retrieval and categorization.
  • Use Case: Use this at the end of a complex refactoring session to ensure that the rationale behind architectural decisions and the status of pending items are preserved for future development cycles.

Quick Start

Invoke the memory-save skill to capture the current session context and store it in the memory database.

Frequently Asked Questions about memory-save

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I save AI session context for long-term project continuity?▼

To save AI session context for long-term project continuity, you aggregate completed tasks, key decisions, and open items into a structured memory object. This prevents context loss during long-running AI sessions by indexing session data.

What is the best way to persist architectural decisions and code changes from a refactoring session?▼

The best way to persist architectural decisions and code changes from a refactoring session is to snapshot the context into a persistent memory store. This allows you to attach custom metadata tags for easier retrieval and categorization of the saved items.

Does saving session memory require integration with a specific storage system?▼

Yes, saving session memory requires integration with the claude-mem storage system. This integration is necessary to perform document addition and metadata tagging when indexing your session data for future context compaction.

How do I retrieve past tasks and open items after losing my AI session context?▼

You retrieve past tasks and open items by querying a persistent memory store where previous session contexts were indexed. Saving your session compacts context data, ensuring future development cycles can access the rationale behind past decisions.

Can I attach custom tags to saved memories for easier categorization?▼

Yes, you can attach custom metadata tags to saved memories for easier retrieval and categorization. This feature allows you to specifically label session snapshots, making it simpler to filter and locate context from previous development cycles.

Related Skills

Explore More Software Engineering Skills→
markus41markus41
1

vectordb

Manage vector embeddings for semantic search across Pinecone, Weaviate, Chroma, and pgvector.

Community
Intermediate
justStevejustSteve

ReasoningBank with AgentDB

Store, retrieve, and reason over experiential memories using AgentDB.

Community
Advanced
aaron-he-zhuaaron-he-zhu
142

memory-management

Manage two-layer memory with hot cache and cold storage for SEO projects.

Community
Basic
AribSudiaAribSudia
2

arib-session-end

Update project memory files and synchronize code changes to remote repositories.

Community
Advanced