cortex-navigate-knowledge skill
✓ VerifiedTraverse a knowledge graph to trace entity relationships, explore causal chains, and navigate memory clusters.
- GitHub stars
- 76
- Files
- 1
- Last commit
- Nov 12, 2026
- License
- MIT
- Allowed tools
- —
What does the cortex-navigate-knowledge skill do?
cortex-navigate-knowledge is an agent skill. Traverse a knowledge graph to trace entity relationships, explore causal chains, and navigate memory clusters.
Summary generated from the skill's SKILL.md.
About the cortex-navigate-knowledge skill
Tracing connections between people, technologies, and concepts within a knowledge graph is what this skill enables. Developers and AI agents use it to follow causal chains, explore how memories are frequently accessed together, and navigate through fractal memory clusters. It is particularly useful when an agent needs to understand the web of relationships between entities or determine what caused a specific event.
An agent should load this skill when a user asks to explore connections, trace relationships, or drill down into specific topics. The tool provides several specialized functions, including get_causal_chain to follow typed relationships like dependencies, navigate_memory to find implicit links through co-access frequency, and recall_hierarchical to browse information from broad to specific levels. It also includes a detect_gaps function to identify isolated entities or sparse domains within the existing knowledge graph.
What an agent can do with it
- 1Identifying knowledge gapsFind areas where the knowledge graph is sparse or contains isolated entities.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the cortex-navigate-knowledge skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the cortex-navigate-knowledge skill in Plugin
/plugin marketplace add cdeust/Cortex /plugin install hypermnesia-mcp@cortex-plugins
Install the cortex-navigate-knowledge skill in Claude Code
~/.claude/skills/cortex-navigate-knowledge/SKILL.md
$ npx degit cdeust/Cortex/skills/cortex-navigate-knowledge ~/.claude/skills/cortex-navigate-knowledgeInstall the cortex-navigate-knowledge skill in Claude Code (project)
.claude/skills/cortex-navigate-knowledge/SKILL.md
$ npx degit cdeust/Cortex/skills/cortex-navigate-knowledge .claude/skills/cortex-navigate-knowledgeInstall the cortex-navigate-knowledge skill in Codex
~/.agents/skills/cortex-navigate-knowledge/SKILL.md
$ npx degit cdeust/Cortex/skills/cortex-navigate-knowledge ~/.agents/skills/cortex-navigate-knowledgeInstall the cortex-navigate-knowledge skill in Gemini CLI
~/.gemini/skills/cortex-navigate-knowledge/SKILL.md
$ npx degit cdeust/Cortex/skills/cortex-navigate-knowledge ~/.gemini/skills/cortex-navigate-knowledgeInstall the cortex-navigate-knowledge skill in Claude.ai
npx degit cdeust/Cortex/skills/cortex-navigate-knowledge cortex-navigate-knowledge && zip -r cortex-navigate-knowledge.zip cortex-navigate-knowledge # claude.ai → Customize → Skills → + → Create skill → Upload a skill → cortex-navigate-knowledge.zip
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablecdeust/cortex/skills/cortex-navigate-knowledge is public and reachablegithub.com/cdeust/cortex/tree/HEAD/skills/cortex-navigate-kn ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-12github.com/cdeust/cortex/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/cdeust/cortex/blob/HEAD/skills/cortex-navigate-kn ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/cdeust/cortex/blob/HEAD/skills/cortex-navigate-kn ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 102 linesgithub.com/cdeust/cortex/blob/HEAD/skills/cortex-navigate-kn ↗Pass
SKILL.md
View on GitHubNavigate Knowledge — Graph Exploration and Causal Chains
Keywords
knowledge graph, relationships, connections, causal chain, how are these related, what connects, drill down, explore, navigate, entity graph, trace, cause and effect, related to, linked to, co-access, cluster
Overview
Cortex maintains a knowledge graph of entities (people, technologies, concepts, files) and their relationships extracted from memories. This skill lets you traverse that graph — follow causal chains, explore co-access patterns, drill into fractal memory clusters, and understand how different pieces of knowledge connect.
Use this skill when: You need to understand relationships between concepts, trace cause-and-effect chains, or explore a topic area systematically.
Workflow
Step 1: Trace Causal Chains
Follow entity relationships through the knowledge graph:
cortex:get_causal_chain({
"entity": "PostgreSQL",
"direction": "both",
"max_depth": 3
})
Returns a chain of entities connected by typed relationships (causes, uses, depends_on, related_to, etc.). Direction can be "forward" (effects), "backward" (causes), or "both".
Step 2: Navigate Co-Access Paths
Find memories frequently accessed together using Successor Representation:
cortex:navigate_memory({
"memory_id": <starting_memory_id>,
"depth": 2,
"max_nodes": 20
})
Returns a graph of memories connected by co-access frequency — revealing implicit relationships that aren't in the explicit knowledge graph.
Step 3: Hierarchical Exploration
Browse memories through fractal clusters (L0 = broad, L1 = mid, L2 = specific):
cortex:recall_hierarchical({
"query": "authentication system",
"levels": 3
})
Then drill into any interesting cluster:
cortex:drill_down({
"cluster_id": "<cluster from hierarchical recall>",
"level": "L1"
})
Step 4: Detect Structural Gaps
Find disconnected or under-connected areas:
cortex:detect_gaps({
"domain": "<optional>"
})
Returns isolated entities, sparse domains, and temporal drift — areas where your knowledge graph has holes.
Use Cases
Understanding a new codebase:
- Recall hierarchical to get broad topic clusters
- Drill down into the most relevant cluster
- Navigate co-access paths from key memories
- Trace causal chains for core entities
Debugging with context:
- Recall memories about the error/module
- Get causal chain for the affected entity
- Navigate to co-accessed memories (past fixes, related patterns)
Architecture review:
- Get causal chains for key components
- Detect gaps in architectural documentation
- Assess coverage for each module
Tips
- Start broad, go narrow: Use hierarchical recall first, then drill down and navigate from specific memories
- Causal chains reveal architecture: The knowledge graph captures how components depend on each other — useful for impact analysis
- Co-access reveals workflow: Memories accessed together often represent a workflow or related concern, even if they're not explicitly linked
Files in this skill
1cortex-navigate-knowledge skill questions
How do I install the cortex-navigate-knowledge skill in Claude Code?
Run npx degit cdeust/Cortex/skills/cortex-navigate-knowledge ~/.claude/skills/cortex-navigate-knowledge. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the cortex-navigate-knowledge skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How can I find out what connects two different entities?
You can use the get_causal_chain tool to follow entity relationships through the knowledge graph, specifying the direction and maximum depth.
Can I find memories that are frequently accessed together?
Yes, you can use the navigate_memory tool to find memories connected by co-access frequency, which reveals implicit relationships.
How do I identify missing information in my knowledge graph?
You can use the detect_gaps tool to find isolated entities, sparse domains, and temporal drift where the knowledge graph has holes.