A powerful systematic framework to evaluate complex options, perform sensitivity analysis, and deliver objective, data-driven decisions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install decision-matrix
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-matrix 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 Matrix?
The Decision Matrix skill is designed to guide developers and teams through complex, multi-factor choices using a systematic and quantified evaluation framework. When facing hard decisions—such as comparing software vendors, assessing job offers, or selecting architecture patterns—intuition alone often falls short. By leveraging Openclaw Skills, this tool strips away emotional bias and applies mathematical precision to evaluate trade-offs, test underlying assumptions, and reach a fully defensible decision.
By organizing criteria, applying weightings, scoring options, and conducting stability testing, this skill delivers structured reports that help you clearly visualize your options. It is an essential addition to your repository of Openclaw Skills for anyone seeking to optimize their analytical workflows and elevate their decision-making process.
Decision Matrix Use Cases
- Selecting between multiple job offers or career paths by weighing salary, culture, and growth.
- Comparing different software packages, API vendors, or technological frameworks for a development project.
- Quantifying financial and lifestyle tradeoffs when deciding whether to rent or buy a home.
- Evaluating relocation options across factors like cost of living, commute times, and proximity to hubs.
- Making high-stakes purchasing decisions, such as selecting equipment or enterprise infrastructure.
How Decision Matrix Works
- Option Enumeration: The system prompts the user to input 3-5 alternative options for comparison, suggesting a pre-filter step if the list exceeds the maximum limit.
- Criteria Definition: Users define the evaluation dimensions (e.g., cost, speed, reliability) and specify whether a higher or lower score is preferred for each parameter.
- Criteria Weighting: Importance weights (ranging from 1 to 10) are assigned to each criterion, which are then normalized to a 100% total scale. Criteria rated above 9 are marked as critical dealbreakers.
- Performance Scoring: Each option is scored against every criterion on a scale of 1 to 10. Objective data is scaled automatically where applicable.
- Weighted Score Computation: The skill runs calculations using the formula WeightedScore = Sum of (Score * Weight) and generates a visual heatmap comparison.
- Sensitivity Analysis & Stress Testing: The tool dynamically varies criteria weights by +/- 20% to run stability stress-tests, pinpointing "tipping points" that could shift the leading rank.
- Differentiator Analysis: The algorithm identifies the "swing factors" (key criteria) that cause the most significant ranking divergence between the top options.
- Report Delivery: A comprehensive decision report is compiled, outlining the final recommendation, caveats, heatmap, and sensitivity analysis.
Decision Matrix Setup
To add this to your catalog of Openclaw Skills, register and run the CLI interface:
# Install or register the decision-matrix skill globally
openclaw skills register decision-matrix
# Run the evaluation directly via the CLI
decision-matrix evaluate --options "Offer A,Offer B,Offer C" --criteria "salary:8,growth:9,stability:6"
Configure default parameters inside your AI agent's configuration file:
{
"skills": [
"decision-matrix"
],
"options": {
"max_options": 5,
"normalize_weights": true
}
}
Decision Matrix Data Schema & Taxonomy
The Decision Matrix schema organizes evaluation parameters, score metrics, and sensitivity thresholds. Key outputs are stored in structured matrices or markdown tables for review:
| Field | Type | Description |
|---|---|---|
options |
Array of Strings | The alternative choices evaluated (e.g., ["A", "B", "C"]). |
criteria |
Map/Object | Map of criteria strings to integer weights (1-10) and polarity directions. |
scores |
Nested Map | Map of option -> criterion -> score (1-10). |
weighted_scores |
Map | Computed overall score per option. |
sensitivity_logs |
Object | Volatility flags, tipping point thresholds, and weight shifts (+/- 20%). |
A typical decision report payload is structured as follows:
- Summary: Recommended option and total weighted score.
- Heatmap: Matrix of criteria weights, individual scores, and totals.
- Sensitivity Logs: Stability indicator (stable / unstable) and tipping point conditions.
- Swing Factors: Top 1-2 criteria separating the leading options.
Decision Matrix Advanced Features
- Stability Auto-Flagging: Instantly marks a ranking as unstable if a small weight shift (+/- 20%) alters the top-ranked option.
- Dealbreaker Identification: Automatically flags criteria with weights greater than 9 to highlight non-negotiable thresholds.
- Objective Scaling Engine: Scales raw objective values (like monetary salaries, commute hours) automatically into the standard 1-10 scoring format.
- Interactive Tipping-Point Detection: Evaluates the precise threshold required to flip the positions of the top two options, exposing critical dependencies.
- Seamless Agent Orchestration: Easily integrates with other Openclaw Skills to dynamically fetch data (such as financial metrics or relocation data) before feeding them into the matrix.
SKILL.md
Loading
Related Openclaw Skills
find-skill4
An essential search and installation agent skill that discovers, verifies, and integrates new capabilities from the Openclaw Skills package repository.
Meal Prep Planner
An intelligent meal preparation and planning skill that transforms available fridge ingredients into structured weekly recipes, dietary nutrition guides, and sorted shopping lists.
Academic Paper Revision SOP
A comprehensive five-phase academic paper revision and polishing pipeline that parses reviewer comments, diagnoses structural issues, removes AI artifacts, and generates interactive reports.
Atomic Accidents - A History of Nuclear Meltdowns and Disasters
An AI-powered knowledge skill that delivers technical, deeply analyzed insights into history's most significant nuclear accidents, safety systems, and engineering failures.
Sales Forecast
An AI-powered sales forecasting assistant that utilizes Amazon Chronos-2 for zero-shot, multi-quantile probabilistic time-series forecasting without requiring any model training.
LYGO RESONANCE
A dual-engine creative skill that uses computer vision to transform any image or video into high-fidelity stereo WAV soundscapes and structured AI music briefs.
Featured*
