/cortex-recall-global
Search and retrieve global memories — knowledge that applies across all projects. Use when the user asks 'what are our coding standards', 'what conventions do we follow', 'what's our infrastructure setup', 'do we have a rule about', 'what applies to all projects', 'shared
$ npx -y skills add cdeust/Cortex --skill cortex-recall-global --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/cortex-recall-global
Context preview
The summary Claude sees to decide when to auto-load this skill.
Search and retrieve global memories — knowledge that applies across all projects. Use when the user asks 'what are our coding standards', 'what conventions do we follow', 'what's our infrastructure setup', 'do we have a rule about', 'what applies to all projects', 'shared
SKILL.md
cortex-recall-global.SKILL.mdname: cortex-recall-global
description: "Search and retrieve global memories — knowledge that applies across all projects. Use when the user asks 'what are our coding standards', 'what conventions do we follow', 'what's our infrastructure setup', 'do we have a rule about', 'what applies to all projects', 'shared knowledge', 'global rules', or when you need cross-project context like architecture decisions, server configs, or team policies."
Recall Global — Retrieve Cross-Project Knowledge
Keywords
global, convention, standard, rule, infrastructure, policy, all projects, shared, universal, what's our rule, coding standard, architecture rule, team agreement, cross-project, server config, deployment
Overview
Retrieve global memories — knowledge stored as cross-project that's visible regardless of which project you're currently working in. Global memories include architecture rules, coding conventions, infrastructure facts, security policies, and team agreements.
**Note:** Regular `cortex:recall` already surfaces global memories automatically. This skill is for when you specifically want to focus on cross-project knowledge.
Workflow
Step 1: Recall Global Knowledge
Query with any domain — global memories appear alongside domain-specific results:
cortex:recall({
"query": "<topic to search for>",
"max_results": 10
})Global memories are included in results regardless of the current project domain.
Step 2: Filter to Global Only
To see only global cross-project knowledge, use the unified neural graph:
cortex:open_visualization()
Click the **Global** filter button (pink) to isolate all global memories.
Click the **Global** filter — global memories appear as pink nodes connected to all project domains.
Step 3: Explore by Category
Common global recall patterns:
**Architecture rules:**
cortex:recall({ "query": "architecture rules and principles" })**Infrastructure:**
cortex:recall({ "query": "server addresses and database connections" })**Coding conventions:**
cortex:recall({ "query": "coding standards and naming conventions" })**Security policies:**
cortex:recall({ "query": "security policies and credential management" })Step 4: Navigate Connections
After finding a global memory, explore what it connects to across projects:
cortex:navigate_memory({
"memory_id": <id>,
"depth": 2
})Global memories link to all domain hubs in the knowledge graph — following connections shows which projects reference similar concepts.
How Global Recall Works
Global memories have `is_global = TRUE` in the database. During recall, every retrieval signal (vector, FTS, trigram, heat, recency) includes the clause:
WHERE (domain = current_domain OR is_global = TRUE)
This means global memories compete on relevance alongside domain-specific ones — they're not artificially boosted, just not filtered out.
Tips
- **Global memories compete on merit**: They appear in results only when relevant to the query, not automatically at the top
- **Use the visualization**: The unified graph shows global memories (pink) with edges to every project — a visual map of shared knowledge
- **Rate for quality**: Use `cortex:rate_memory` on global memories that were helpful to improve future retrieval confidence
- **Assess coverage**: Use `cortex:assess_coverage` to see if any project domain is missing shared knowledge
Read more
name: cortex-recall-global description: "Search and retrieve global memories — knowledge that applies across all projects. Use when the user asks 'what are our coding standards', 'what conventions do we follow', 'what's our infrastructure setup', 'do we have a rule about', 'what applies to all projects', 'shared knowledge', 'global rules', or when you need cross-project context like architecture decisions, server configs, or team policies."
Recall Global — Retrieve Cross-Project Knowledge
Keywords
global, convention, standard, rule, infrastructure, policy, all projects, shared, universal, what's our rule, coding standard, architecture rule, team agreement, cross-project, server config, deployment
Overview
Retrieve global memories — knowledge stored as cross-project that's visible regardless of which project you're currently working in. Global memories include architecture rules, coding conventions, infrastructure facts, security policies, and team agreements.
**Note:** Regular `cortex:recall` already surfaces global memories automatically. This skill is for when you specifically want to focus on cross-project knowledge.
Workflow
Step 1: Recall Global Knowledge
Query with any domain — global memories appear alongside domain-specific results:
cortex:recall({
"query": "<topic to search for>",
"max_results": 10
})Global memories are included in results regardless of the current project domain.
Step 2: Filter to Global Only
To see only global cross-project knowledge, use the unified neural graph:
cortex:open_visualization()
Click the **Global** filter button (pink) to isolate all global memories.
Click the **Global** filter — global memories appear as pink nodes connected to all project domains.
Step 3: Explore by Category
Common global recall patterns:
**Architecture rules:**
cortex:recall({ "query": "architecture rules and principles" })**Infrastructure:**
cortex:recall({ "query": "server addresses and database connections" })**Coding conventions:**
cortex:recall({ "query": "coding standards and naming conventions" })**Security policies:**
cortex:recall({ "query": "security policies and credential management" })Step 4: Navigate Connections
After finding a global memory, explore what it connects to across projects:
cortex:navigate_memory({
"memory_id": <id>,
"depth": 2
})Global memories link to all domain hubs in the knowledge graph — following connections shows which projects reference similar concepts.
How Global Recall Works
Global memories have `is_global = TRUE` in the database. During recall, every retrieval signal (vector, FTS, trigram, heat, recency) includes the clause:
WHERE (domain = current_domain OR is_global = TRUE)
This means global memories compete on relevance alongside domain-specific ones — they're not artificially boosted, just not filtered out.
Tips
- **Global memories compete on merit**: They appear in results only when relevant to the query, not automatically at the top
- **Use the visualization**: The unified graph shows global memories (pink) with edges to every project — a visual map of shared knowledge
- **Rate for quality**: Use `cortex:rate_memory` on global memories that were helpful to improve future retrieval confidence
- **Assess coverage**: Use `cortex:assess_coverage` to see if any project domain is missing shared knowledge
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.
Repo: cdeust/Cortex
Other skills on hypermnesia-mcp.
- /cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this
Open skill - /cortex-consolidate
Run memory maintenance — decay old memories, compress stale content, consolidate episodic memories into semantic knowledge, and run sleep-like replay. Use when the user says 'clean up memories', 'consolidate', 'run maintenance', 'compress old memories', 'memory cleanup', or
Open skill - /cortex-debug-memory
Debug and fix memory system issues — validate memories, rate quality, manage protection, forget bad memories, and restore from checkpoints. Use when the user says 'fix memory', 'bad memory', 'wrong memory', 'delete this', 'protect this', 'this memory is wrong', 'memory quality',
Open skill - /cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find
Open skill - /cortex-import
Import memories from other AI memory systems into Cortex. Supports claude-mem (SQLite), Claude Desktop sessions, ChatGPT web export (JSON), Gemini Takeout (JSON), Cursor conversations, and Claude Code JSONL. Use when the user says 'import from claude-mem', 'migrate memories',
Open skill - /cortex-navigate-knowledge
Navigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters, and traverse co-access paths. Use when the user asks 'how are these related', 'what connects X to Y', 'show me the knowledge graph', 'trace the relationship', 'what
Open skill

