Compare for Openclaw

A systematic comparison engine that ensures objective decision-making through research parity and weighted criteria scoring.

ivangdavila
v1.0.0
Feb 12, 2026
2
1.5k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install compare

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install compare 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 Compare?

The Compare skill for Openclaw Skills provides a rigorous framework for evaluating multiple options without bias. It operates on the principle that a comparison is only as strong as its weakest-researched dimension, forcing the agent to achieve data parity before rendering a judgment.

By leveraging domain defaults and individual user preferences, this skill transforms subjective opinions into data-driven scores. It specifically addresses common analytical traps like unbalanced data depth or source quality discrepancies, making it an essential tool for high-stakes decision-making and technical evaluations within Openclaw Skills.

Compare Use Cases

  • Evaluating competing software libraries or frameworks during the development lifecycle.
  • Comparing hardware specifications for server deployments or local workstations.
  • Making complex purchasing decisions based on weighted user priorities and domain standards.
  • Benchmarking different AI models or API providers with research depth tracking.
  • Selecting service providers where criteria like cost, reliability, and support are weighted differently.

How Compare Works

  1. Define ranking criteria by loading domain defaults and overlaying user preferences from memory files.
  2. Establish research parity by ensuring each item is researched to an equivalent depth to avoid unbalanced data.
  3. Perform a confidence check to verify data recency and source quality across all items being compared.
  4. Calculate the final score using a weighted sum formula and provide a transparent breakdown of the math.
  5. Present the findings in a structured format including the winner, margin of victory, caveats, and conditional alternatives.

Compare Setup

To enable the Compare skill within your Openclaw Skills environment, ensure your domain and preference files are initialized in your skill directory.

# Initialize domain criteria and user preferences
touch domains.md preferences.md
# Ensure the Compare skill protocol is active in your agent configuration

Compare Data Schema & Taxonomy

The Compare skill utilizes several markdown-based data stores to maintain context and improve over time.

File Purpose
domains.md Stores default comparison criteria for specific industries or categories.
preferences.md Tracks user-specific weights and historical priorities to personalize results.
confidence.md Contains logic for calculating research depth and source reliability scores.
traps.md A reference of common logical fallacies to avoid during the research phase.

Compare Advanced Features

  • Weighted Criteria Scoring: Automatically calculates the winner based on importance levels totaling 100%.
  • Research Depth Tracking: Explicitly prevents scoring until all items have equivalent research footprints.
  • Dynamic Memory Integration: Automatically updates preferences.md based on which criteria the user focuses on most frequently.
  • Parity Failure Protocol: Declines to offer a recommendation if research parity is impossible or priorities are too vague, ensuring high-integrity output for Openclaw Skills.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*