How do I install the Memora skill?

Run npx skillmds@latest add agentic-box/memora-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Memora safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Memora?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Memora free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Memora?

agentic-box (@agentic-box) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Memora by agentic-box — Agent Skill

Name: Memora
Author: agentic-box

File contents

Memora - Persistent Semantic Memory

Memora is the persistent memory system for this environment. Use memora MCP tools to store, search, and organize knowledge across sessions.

When to Use

Session start: Relevant memories are auto-injected via hook
Storing decisions: Use memory_create to save architectural decisions, patterns, preferences
Finding context: Use memory_hybrid_search to find relevant past work
Tracking work: Use memory_create_todo / memory_create_issue for task tracking
Organizing knowledge: Use memory_hierarchy to browse organized memories

Core Tools

Creating Memories

memory_create - Store a new memory (auto-deduplicates, suggests hierarchy)
memory_create_todo - Create a TODO with priority (high/medium/low)
memory_create_issue - Create an issue with severity (critical/major/minor)
memory_create_section - Create organizational headers
memory_create_batch - Bulk create multiple memories

Searching

memory_hybrid_search - Best search: combines keyword + semantic (use this by default)
memory_semantic_search - Pure vector similarity search
memory_list - List/filter by tags, dates, metadata
memory_list_compact - Lightweight listing (id, preview, tags only)

Organizing

memory_hierarchy - View memories in section/subsection tree
memory_tags - List allowed tags
memory_tag_hierarchy - View tag namespace tree
memory_link - Create typed relationships between memories
memory_clusters - Detect related memory clusters

Maintenance

memory_find_duplicates - Find and review potential duplicates (LLM-powered)
memory_merge - Merge two memories together
memory_insights - Get activity summary, stale items, patterns
memory_stats - Database statistics
memory_boost - Increase a memory's importance ranking

Visualization

Knowledge graph available at http://localhost:8765 when running
memory_export_graph - Export as interactive HTML file

Tag Conventions

Use hierarchical tags with / separators:

memora/knowledge - General knowledge
memora/todos - Task items
memora/issues - Bug/issue tracking
memora/auto-capture - Auto-captured content
memora/sections - Organizational headers
project-name/topic - Project-specific tags

Best Practices

Search before creating - avoid duplicates
Use metadata for structured data (section, subsection, project)
Tag consistently - use hierarchical tags
Boost important memories - they rank higher in searches
Use hybrid search as default - it combines keyword + semantic
Review insights periodically - find stale items and consolidation opportunities

Auto-Capture

When MEMORA_AUTO_CAPTURE=true is set, the PostToolUse hook automatically captures:

Git commits (appended to per-project commit log)
Test results (failures become issues)
Web research (GitHub repos, documentation)
Documentation edits (README, CHANGELOG, etc.)

---name: memora-2description: Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.---# Memora - Persistent Semantic MemoryMemora is the persistent memory system for this environment. Use memora MCP tools to store, search, and organize knowledge across sessions.## When to Use- **Session start**: Relevant memories are auto-injected via hook- **Storing decisions**: Use `memory_create` to save architectural decisions, patterns, preferences- **Finding context**: Use `memory_hybrid_search` to find relevant past work- **Tracking work**: Use `memory_create_todo` / `memory_create_issue` for task tracking- **Organizing knowledge**: Use `memory_hierarchy` to browse organized memories## Core Tools### Creating Memories- `memory_create` - Store a new memory (auto-deduplicates, suggests hierarchy)- `memory_create_todo` - Create a TODO with priority (high/medium/low)- `memory_create_issue` - Create an issue with severity (critical/major/minor)- `memory_create_section` - Create organizational headers- `memory_create_batch` - Bulk create multiple memories### Searching- `memory_hybrid_search` - Best search: combines keyword + semantic (use this by default)- `memory_semantic_search` - Pure vector similarity search- `memory_list` - List/filter by tags, dates, metadata- `memory_list_compact` - Lightweight listing (id, preview, tags only)### Organizing- `memory_hierarchy` - View memories in section/subsection tree- `memory_tags` - List allowed tags- `memory_tag_hierarchy` - View tag namespace tree- `memory_link` - Create typed relationships between memories- `memory_clusters` - Detect related memory clusters### Maintenance- `memory_find_duplicates` - Find and review potential duplicates (LLM-powered)- `memory_merge` - Merge two memories together- `memory_insights` - Get activity summary, stale items, patterns- `memory_stats` - Database statistics- `memory_boost` - Increase a memory's importance ranking### Visualization- Knowledge graph available at http://localhost:8765 when running- `memory_export_graph` - Export as interactive HTML file## Tag ConventionsUse hierarchical tags with `/` separators:- `memora/knowledge` - General knowledge- `memora/todos` - Task items- `memora/issues` - Bug/issue tracking- `memora/auto-capture` - Auto-captured content- `memora/sections` - Organizational headers- `project-name/topic` - Project-specific tags## Best Practices1. **Search before creating** - avoid duplicates2. **Use metadata** for structured data (`section`, `subsection`, `project`)3. **Tag consistently** - use hierarchical tags4. **Boost important memories** - they rank higher in searches5. **Use hybrid search** as default - it combines keyword + semantic6. **Review insights periodically** - find stale items and consolidation opportunities## Auto-CaptureWhen `MEMORA_AUTO_CAPTURE=true` is set, the PostToolUse hook automatically captures:- Git commits (appended to per-project commit log)- Test results (failures become issues)- Web research (GitHub repos, documentation)- Documentation edits (README, CHANGELOG, etc.)

Frequently asked questions

Memora