An automated tool for extracting entities, events, and causal relationships from logs and memory files to build dynamic knowledge graphs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install causal-graph
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install causal-graph using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Causal Graph Auto-Builder?
The Causal Graph Auto-Builder is a sophisticated Openclaw Skills component designed to bridge the gap between raw activity logs and structured intelligence. By analyzing memory files and daily logs, it automatically identifies key entities—such as developers, projects, and tools—and maps the causal links between events. This reduces the manual overhead of maintaining a Knowledge Graph while providing a clear logic chain for AI agents to follow.
By leveraging this skill, developers can transform fragmented text into a queryable, visual, and semantically rich graph structure. It enables a deeper understanding of the 'why' behind system changes, making it an essential tool for projects requiring long-term memory and complex reasoning capabilities.
Causal Graph Auto-Builder Use Cases
- Automatically generating project dependency maps from development logs.
- Analyzing event causality to improve AI agent task completion rates.
- Visualizing long-term memory to identify patterns in project growth.
- Streamlining the maintenance of complex Knowledge Graphs for technical documentation.
How Causal Graph Auto-Builder Works
- Data Ingestion: The skill reads raw data from memory logs, long-term memory files, and issue trackers.
- Named Entity Recognition (NER): It extracts and categorizes people, projects, tools, and abstract concepts.
- Event Extraction: Identifies timestamped actions and specific occurrences within the text.
- Causal Inference: Analyzes the logical flow to determine relationships like 'causes', 'enables', or 'requires'.
- Deduplication: Merges different descriptions of the same entity into a single node.
- Graph Output: Generates a structured JSON file ready for visualization or querying.
Causal Graph Auto-Builder Setup
To integrate this functionality into your environment using Openclaw Skills, follow these steps:
# Build the causal graph from existing logs
node skills/causal-graph/build.mjs
# Query the graph for specific dependencies
node skills/causal-graph/query.mjs "AgentAwaken dependencies"
# Generate a visualization file
node skills/causal-graph/visualize.mjs > graph.html
Causal Graph Auto-Builder Data Schema & Taxonomy
The skill organizes data into a structured JSON schema consisting of Nodes and Edges. This allows for clear metadata taxonomy within Openclaw Skills.
Node Types
| Type | Description | Attributes |
|---|---|---|
| Entity | People, Projects, or Tools | id, type, label |
| Event | Timestamped actions | id, type, label, timestamp |
| Concept | Abstract ideas | id, type, label |
Edge Types
- causes: Indicates that one event directly results in another.
- enables: Indicates that an entity or event makes another possible.
- requires: Defines a dependency where one node relies on another.
- relates: Establishes a general association between nodes.
Causal Graph Auto-Builder Advanced Features
- Hybrid Extraction Engine: Combines fast Regex rule-matching with high-accuracy LLM analysis for optimal performance.
- Interactive Visualizations: Exports data to HTML for deep-dive analysis of causal pathways in the browser.
- Dashboard Integration: Seamlessly connects with the AgentAwaken Dashboard to highlight logic chains and project timelines.
- Confidence Scoring: Uses LLM-based verification to assign confidence levels to inferred causal relationships.
SKILL.md
Loading
Related Openclaw Skills
Agent ROS Bridge
A secure, universal communication bridge that enables AI agents to control ROS1 and ROS2 robotic systems with ease.
Fact Check
A systematic verification tool designed to validate claims, statistics, and statements against a hierarchy of trusted global sources.
Moltpad
A comprehensive tool for AI agents to write, publish, and collaborate on literary content within the Moltpad.space community.
Moltpad
A comprehensive skill enabling AI agents to interact with the Moltpad.space community as autonomous writers, critics, and collaborators.
Cross-Agent Memory Sharing Protocol
A standardized protocol for enabling collective intelligence by allowing multiple AI agents to share, sync, and inherit knowledge seamlessly.
Meme Signal Scanner
A real-time aggregator and scoring engine for meme coin signals across major decentralized exchanges and launchpads.
Featured*
