客观原则评价技能

客观原则评价技能 - Evaluate products, ideas, or designs using objective principles from three design classics. Based on Tony Fadell's Build (painkiller vs vitamin),...

Security Scan

This instruction-only skill is internally consistent with its stated purpose (an objective design/product evaluator) and requests no installs, credentials, or system access.

Purpose & Capability

The name/description match the SKILL.md: it provides a three-lens evaluation framework (Fadell/Norman/Rams). There are no unrelated requirements (no credentials, binaries, or config paths) that would be disproportionate to an evaluator skill.

Instruction Scope

SKILL.md contains only evaluation questions, scoring rules, usage patterns, and an example output format. It does not instruct the agent to read files, access environment variables, call external endpoints, or collect unrelated system data.

Install Mechanism

No install spec and no code files — the skill is instruction-only, which minimizes disk/network installation risk.

Credentials

The skill declares no environment variables, credentials, or config paths. Nothing requested is disproportionate to a product/design evaluation task.

Persistence & Privilege

always is false and the skill is user-invocable; it does not request persistent or elevated presence. Autonomous invocation is allowed by default but not combined with other risky factors here.

Assessment

This skill appears low-risk: it is an instruction-only evaluator that asks the model to apply three design frameworks and produces a structured verdict. Before installing, note that (1) it has no external access or credentials so it cannot exfiltrate secrets, (2) outputs depend on the model's knowledge and prompts you give it—check for hallucinations or unjustified claims, and (3) when using it, supply only the product information you want evaluated (avoid pasting sensitive data). If you need stricter control, disable autonomous invocation or review outputs before acting on them.

Objective Evaluator - 客观原则评价技能

基于三本经典设计著作的客观评价框架：

• Tony Fadell《Build》 - 止痛药 vs 维生素
• Don Norman《设计心理学》 - 设计的三个层次
• Dieter Rams《设计十诫》 - 红旗警告

Evaluate any product, idea, or design through three complementary lenses:

Evaluate any product, idea, or design through three complementary lenses:

🔧 Tool (Painkiller vs Vitamin)

Based on Tony Fadell - Build

Ask:

• Does it solve a real physical/information pain point?
• If it breaks tomorrow, does the workflow stop?
• Is it a painkiller (essential) or vitamin (nice-to-have)?

Scoring:

• ✅ Tool - Solves real pain, workflow depends on it
• ⚠️ Edge Tool - Painkiller for some, vitamin for others
• ❌ Not a Tool - No real pain point addressed

🎨 Toy (Three Levels of Design)

Based on Don Norman - Design of Everyday Things

Evaluate across three levels:

Level	Question	What to check
Visceral	Does it bring immediate pleasure/aesthetic satisfaction?	First impression, visual appeal, emotional response
Behavioral	Is the affordance natural? Does it work as expected?	Usability, feedback, control, error prevention
Reflective	Does it create long-term attachment/identity?	Personal meaning, self-image, long-term satisfaction

Scoring:

• ✅ Strong Toy - Delivers on 2+ levels effectively
• ⚠️ Weak Toy - Delivers on 1 level only
• ❌ Not a Toy - No emotional or experiential value

🚩 Trash (Red Flags)

Based on Dieter Rams - Ten Principles of Good Design

Check for these deal-breakers:

Red Flag	Description	Example
Physics Violation	Violates physical laws or logical impossibility	Perpetual motion, impossible chemistry
Marketing Fiction	Creates pseudo-demand through manipulation	"You need this" when you don't
Dishonest Design	Deceives users about function or origin	Fake buttons, hidden costs, dark patterns
Planned Obsolescence	Designed to fail unnecessarily	Non-replaceable batteries, software locks

Scoring:

• 🚩 Trash - Any red flag present
• ⚠️ Yellow Flag - Borderline marketing stretch
• ✅ Clean - No red flags

📊 Final Verdict

Synthesize into clear classification:

┌─────────────────────────────────────────┐
│  TOOL + Strong Toy + Clean  →  KEEP ✅  │
│  TOY (only) + Clean         →  MAYBE ⚠️ │
│  Any + Trash flag           →  REJECT 🚮 │
└─────────────────────────────────────────┘

🎯 Usage Pattern

When evaluating something:

1. Run the three audits independently
2. Note tensions (e.g., strong Tool but weak Toy = industrial equipment)
3. Identify user segments (Tool for pros, Toy for consumers)
4. Deliver verdict with nuance about who it's for

💡 Key Insights to Surface

• Business model cleverness - How do they make money vs what they sell?
• Identity play - Are they selling functionality or self-image?
• Marketing vs Reality - Where does the story diverge from truth?
• Segment dependency - Different answers for different users

Example Output Format

## [Product Name] - T3 Audit

### 🔧 Tool Assessment
| Question | Answer |
|----------|--------|
| Real pain point? | ✅ Yes - ... |
| Workflow critical? | ⚠️ Partial - ... |

**Verdict:** Edge Tool (pros yes, casual users no)

### 🎨 Toy Assessment  
| Level | Score | Notes |
|-------|-------|-------|
| Visceral | ✅ | Beautiful industrial design |
| Behavioral | ⚠️ | Learning curve exists |
| Reflective | ✅ | "Pro user" identity |

**Verdict:** Strong Toy

### 🚩 Trash Check
- Physics violation? ❌ No
- Marketing fiction? ⚠️ Yellow flag - ...
- Dishonest design? ❌ No

### 📊 Final Verdict
**Segment-dependent:** TOOL for professionals, TOY for enthusiasts