A sophisticated auditing skill that evaluates products and designs using the classic principles of Tony Fadell, Don Norman, and Dieter Rams.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install objective-evaluator
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 objective-evaluator 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 Objective Evaluator?
The Objective Evaluator is a comprehensive analysis tool designed for Openclaw Skills that applies high-level design philosophy to modern product critiques. It moves beyond subjective opinion by utilizing a structured T3 (Tool, Toy, Trash) framework derived from three design bibles: Build by Tony Fadell, The Design of Everyday Things by Don Norman, and the Ten Principles of Good Design by Dieter Rams.
This skill is engineered to help developers and product owners determine the true value of a feature or service. By analyzing whether a product is a "painkiller" or a "vitamin," assessing its visceral and behavioral impact, and checking for ethical red flags, the Objective Evaluator provides a clear, actionable verdict for any project or design concept.
Objective Evaluator Use Cases
- Vetting new software tools and libraries to determine if they are essential painkillers for your workflow.
- Conducting design audits on prototypes to ensure they meet visceral and behavioral usability standards.
- Evaluating competitor products to identify marketing fiction and dishonest design patterns.
- Assessing product-market fit for startup ideas by identifying target user segments and identity plays.
- Reviewing hardware or physical product designs for sustainability and logical consistency.
How Objective Evaluator Works
- The user provides a product name, design concept, or service for review using triggers like "evaluate" or "audit."
- The skill performs a Tool Audit to check if the subject solves a real pain point or if it is merely a non-essential vitamin.
- It conducts a Toy Assessment across three levels—Visceral, Behavioral, and Reflective—to gauge emotional and functional satisfaction.
- A Trash Check is executed to identify deal-breaking red flags such as physics violations, dishonest design, or planned obsolescence.
- The results are synthesized into a final T3 Audit report with a clear Keep, Maybe, or Reject verdict based on user segments.
Objective Evaluator Setup
To integrate this skill into your Openclaw Skills library, include the objective-evaluator definition in your agent's skill path. No external dependencies are required as the logic is self-contained within the framework.
# Example of enabling the skill in your local environment
mcp-install objective-evaluator
Once installed, you can trigger an evaluation by asking: "Analyze this product design using the T3 framework."
Objective Evaluator Data Schema & Taxonomy
The skill generates structured evaluation data categorized by the T3 taxonomy. This allows for standardized comparisons across different Openclaw Skills audits.
| Component | Evaluated Metrics | Scoring Output |
|---|---|---|
| Tool (Fadell) | Pain point relief, Workflow dependency | Tool / Edge Tool / Not a Tool |
| Toy (Norman) | Visceral, Behavioral, Reflective design | Strong Toy / Weak Toy / Not a Toy |
| Trash (Rams) | Marketing fiction, Dishonest design, Physics | Clean / Yellow Flag / Trash |
| Verdict | Segment-specific recommendation | Keep / Maybe / Reject |
Objective Evaluator Advanced Features
- Multi-lens synthesis that identifies tensions between utility and emotional appeal.
- Segment-dependent logic that provides different verdicts for professional versus casual users.
- Identification of identity plays and business model cleverness to reveal how products truly monetize.
- Comprehensive red-flag detection based on Dieter Rams' principles to ensure ethical design compliance.
SKILL.md
Loading
Related Openclaw Skills
MBTI Persona
A sophisticated configuration skill that maps the 16 Myers-Briggs personality types to your AI agent to customize communication and decision-making styles.
Hypii Hyperliquid Trading Agent
An AI-powered trading agent for Hyperliquid perpetual futures featuring automated strategies and integrated micropayments.
Stable Browser CDP
A high-stability browser automation layer using Chrome DevTools Protocol to replace unreliable extension-based relays.
Percept Voice Command
A voice-interface skill that enables ambient wake word detection and command execution for OpenClaw agents.
AgentPin
A domain-anchored cryptographic identity protocol for AI agents and verifiable credentials integrated with Openclaw Skills.
SchemaPin
A cryptographic security framework for signing and verifying AI tool schemas to prevent tampering and man-in-the-middle attacks.
Featured*
