A local-first skill that records the structural evolution of ideas, branches, and pivots in your conversations as a browsable JSON tree.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install decision-topology
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 decision-topology 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 Decision Topology?
Decision Topology is a specialized addition to the collection of Openclaw Skills designed to act as a git log for your thinking. It captures the branching logic of a conversation—recording when ideas are proposed, rejected, or merged—without ever sending data to the cloud. By maintaining a local JSON tree of your decision-making process, it allows you to revisit the reasoning behind every pivot and insight. This skill ensures that the architectural shifts in your brainstorming sessions are preserved as structured data, making it easier to audit past logic or resume complex explorations.
As part of the ecosystem of Openclaw Skills, it prioritizes privacy and structural integrity over simple text logging. The skill operates with zero network access and zero external dependencies, using Node.js built-ins to manage data securely on your local disk. It is an essential tool for developers and researchers who need to track the provenance of their conclusions without compromising data sovereignty.
Decision Topology Use Cases
- Tracking the why behind design pivots during complex software architectural discussions.
- Mapping out branching options during brainstorming or project planning sessions.
- Recording rejected ideas and their specific pushback reasons to avoid circular reasoning in future sessions.
- Synthesizing insights from multiple dead-end branches into a single, cohesive direction.
- Linking related concepts across different conversation trees to build a personal knowledge graph.
How Decision Topology Works
- The skill monitors the conversation for meaningful structural shifts, such as new proposals or redirections, rather than transcribing every sentence.
- When a new direction or rejection occurs, it initializes a local JSON tree file with a descriptive topic slug and a timestamp.
- Nodes are added via a secure Node.js script that accepts JSON arguments through stdin, ensuring no shell injection risks from user content.
- Each node captures the type (proposal, pivot, merge), a short summary, reasoning, and optional keyword concepts for indexing.
- Users can query the topology using natural language to render the tree, view killed branches, or export the structure to formats like Mermaid for visualization.
Decision Topology Setup
To integrate this into your environment of Openclaw Skills, ensure Node.js is installed and follow these steps:
# Define the storage directory (Optional)
export TOPOLOGY_TREES_DIR="./my-trees"
# The skill uses the following script path
# {baseDir}/scripts/topology.js
# Initialize a new tree for a topic
echo '{"topic": "api-design-exploration"}' | node scripts/topology.js init
# Add a node to an existing tree
echo '{"file": "2026-02-24-api-design.json", "parent_id": "root", "type": "proposal", "summary": "RESTful implementation", "reasoning": "Standard approach for public consumption"}' | node scripts/topology.js add-node
Decision Topology Data Schema & Taxonomy
The skill organizes data locally within a dedicated directory using a structured JSON schema. This ensures all Openclaw Skills data remains accessible and human-readable.
- Tree Files (.json): Individual files representing specific conversations (e.g.,
2026-02-24-topic-slug.json). - Concept Index (concepts.json): A reverse-index mapping keywords to nodes across all saved trees for cross-thread discovery.
- Companion Files (.md): Markdown summaries of trees featuring wikilinks to related explorations.
| Field | Description |
|---|---|
node_id |
6-character hex ID for tree-local uniqueness. |
summary |
Truncated description of the idea (max 200 chars). |
reasoning |
Contextual logic for the shift or rejection (max 300 chars). |
concepts |
Array of keyword tags used for automatic cross-tree linking. |
type |
Classification: root, proposal, pivot, or merge. |
Decision Topology Advanced Features
- Cross-Tree Analysis: Automatically identifies recurring themes and concepts across separate sessions to build a cohesive knowledge base.
- Branch Killing & Forking: Explicitly records why paths were abandoned and allows re-exploring or forking from any historical node.
- Mermaid Export: Generates visual flowcharts of your decision topology to be used in external documentation or presentations.
- Path Containment: Strict security guardrails that prevent directory traversal and ensure all data remains within the local trees directory.
- Zero-Knowledge Storage: Implements hard length limits on text fields to ensure only structural logic is saved without capturing sensitive verbatim transcripts.
- Natural Language Interface: Users can interact with their data using phrases like "show me what we explored" rather than memorizing CLI commands.
SKILL.md
Loading
Related Openclaw Skills
Research Library
A local-first multimedia research library designed to capture, organize, and search hardware project knowledge with intelligent weighting.
RAG Eval
A diagnostic tool for evaluating the accuracy and retrieval quality of RAG pipelines using Ragas metrics.
OpenClawBrain
A self-regulating, learned memory graph that enables AI agents to evolve through autonomous feedback and policy-gradient routing.
Ahrefs MCP
A professional-grade SEO integration that connects Ahrefs data to your AI agent via the Model Context Protocol.
Home Assistant CLI
An advanced command-line interface for Home Assistant providing deep control over smart devices, event monitoring, and history tracking.
Sphero Mini Control
A Python-based automation skill to control Sphero Mini robot balls through Bluetooth Low Energy across multiple platforms.
METADATA
Featured*
