Agent Skill Grading Report: test-skill - Score 6/100 (F)

# ❌ Agent Skill Grading Report

**Score:** 6/100 | **Grade:** F

## Quick Summary of Agent Skill Grades

### Pillar Scores for Agent Skill

| Pillar | Score | Max |
|--------|-------|-----|
| Spec Compliance | 0 | 15 |
| Progressive Disclosure | 3 | 30 |
| Ease of Use | 4 | 25 |
| Writing Style | 2 | 10 |
| Utility | 0 | 20 |
| Modifiers | -3 | ±15 |

### Issues Found: 7
- 🔴 High: 7
- 🟡 Medium: 0
- 🟢 Low: 0

## 📊 Full Grading Report for Agent Skill

# Skill Evaluation Report: test-skill

**Links:**
- 📁 **GitHub:** [SpillwaveSolutions/skilz-cli](https://github.com/SpillwaveSolutions/skilz-cli/blob/main/.gemini/skills/test-skill/SKILL.md)
- 🛒 **Marketplace:** [View on SkillzWave](https://skillzwave.ai/skill/spillwavesolutions__skilz-cli__test-skill__SKILL/)
- 📤 **Submit Skill:** [Submit to SkillzWave](https://skillzwave.ai/submit/) - Skills are ranked, graded, and scanned for security
- 📊 **Tracking:** [All Graded Skills](https://github.com/SpillwaveSolutions/skill_improver/issues)

**Evaluated:** 2026-01-12
**Files Reviewed:** .gemini/skills/test-skill/SKILL.md
**Grading Model:** Claude (default) (via claude)

---

## Overall Score: 6/100

| Pillar | Score | Max |
|--------|-------|-----|
| Progressive Disclosure Architecture | 3 | 30 |
| Ease of Use | 4 | 25 |
| Spec Compliance | 0 | 15 |
| Writing Style | 2 | 10 |
| Utility | 0 | 20 |
| Modifiers | -3 | ±15 |

**Grade: F**

---

## Executive Summary

This skill needs improvement, scoring 6/100. Strongest area: **Writing Style** (2/10). Primary focus area: **Utility** (0/20). Address 7 high-severity issues for significant score improvement.

---

## Detailed Scores

### Progressive Disclosure Architecture (3/30)

| Criterion | Score | Max | Assessment |
|-----------|-------|-----|------------|
| Token Economy | 2 | 10 | Minimal tokens but provides zero value - concise to the point of being non-functional |
| Layered Structure | 1 | 10 | No layered structure exists; single file with no content hierarchy |
| Reference Depth | 0 | 5 | No reference files present; no progressive disclosure architecture |
| Navigation Signals | 0 | 5 | No headers, no TOC, no navigation aids in 2-line file |

### Ease of Use (4/25)

| Criterion | Score | Max | Assessment |
|-----------|-------|-----|------------|
| Metadata Quality | 3 | 10 | Name follows conventions but description is completely generic with no specificity |
| Discoverability | 0 | 6 | No trigger terms defined; 'Test skill' provides no activation context |
| Terminology Consistency | 1 | 4 | No terminology to evaluate; trivially consistent but empty |
| Workflow Clarity | 0 | 5 | No workflow, no steps, no instructions of any kind |

### Spec Compliance (0/15)

| Criterion | Score | Max | Assessment |
|-----------|-------|-----|------------|
| Frontmatter Validity | 0 | 5 | No frontmatter found |
| Name Conventions | 0 | 4 | No frontmatter to check name |
| Description Quality | 0 | 4 | No frontmatter to check description |
| Optional Fields | 0 | 2 | No frontmatter |

### Writing Style (2/10)

| Criterion | Score | Max | Assessment |
|-----------|-------|-----|------------|
| Voice And Tense | 1 | 4 | No instructional content to evaluate voice; neutral but absent |
| Objectivity | 1 | 3 | No marketing language present; purely empty rather than instructional |
| Conciseness | 0 | 3 | Beyond concise - vacuous; no content density because no content |

### Utility (0/20)

| Criterion | Score | Max | Assessment |
|-----------|-------|-----|------------|
| Problem Solving Power | 0 | 8 | Addresses no capability gaps; provides no functionality whatsoever |
| Degrees Of Freedom | 0 | 5 | No constraints or guidance; skill is a placeholder with no implementation |
| Feedback Loops | 0 | 4 | No validation steps, no run→check→fix patterns defined |
| Examples And Templates | 0 | 3 | No examples, no templates, no input/output pairs |

### Modifiers Applied (-3)

**Penalties:** missing_required_field (-3)
**Bonuses:** None

---

## Critical Issues (Top 7)

### Issue 1: Invalid or incomplete frontmatter

**Severity:** High
**Location:** SKILL.md:frontmatter
**Pillar Affected:** spec_compliance

**Problem:** No frontmatter found

**Current:**
```
(no frontmatter)
```

**Suggested Rewrite:**
```
---
name: test-skill
description: Describe what this skill does. Use when asked to "...", "...", or "...".
---
```

**Impact:** +5 points

---

### Issue 1: Skill is a placeholder

**Severity:** High
**Location:** SKILL.md:entire file
**Pillar Affected:** Utility

**Problem:** Skill contains only metadata with no actual instructions or functionality

**Current:**
```
name: test-skill
description: Test skill
```

**Suggested Rewrite:**
```
Add purpose statement, workflow steps, examples, and reference files defining actual skill behavior
```

**Impact:** +60 points

---

### Issue 2: Name convention violations

**Severity:** High
**Location:** SKILL.md:frontmatter:name
**Pillar Affected:** spec_compliance

**Problem:** No frontmatter to check name

**Current:**
```
(no name)
```

**Suggested Rewrite:**
```
name: test-skill
```

**Impact:** +4 points

---

### Issue 2: Generic non-descriptive description

**Severity:** High
**Location:** SKILL.md:description
**Pillar Affected:** Ease of Use

**Problem:** Description 'Test skill' provides no information about what the skill does or when to use it

**Current:**
```
description: Test skill
```

**Suggested Rewrite:**
```
description: Validates X by performing Y. Use when 'testing Z', 'verifying W', or 'checking Q'.
```

**Impact:** +8 points

---

### Issue 3: Description needs trigger phrases

**Severity:** High
**Location:** SKILL.md:frontmatter:description
**Pillar Affected:** spec_compliance

**Problem:** No frontmatter to check description

**Current:**
```
(no description)
```

**Suggested Rewrite:**
```
description: Performs test skill operations. Use when asked to "test skill", "run test skill", or "test skill help".
```

**Impact:** +4 points

---

### Issue 3: No trigger terms

**Severity:** High
**Location:** SKILL.md:description
**Pillar Affected:** Ease of Use

**Problem:** No trigger phrases defined - skill cannot be discovered or activated appropriately

**Current:**
```
No triggers present
```

**Suggested Rewrite:**
```
Add specific trigger terms in description: 'Use when X', 'Triggers on Y, Z, W'
```

**Impact:** +6 points

---

### Issue 4: Missing reference architecture

**Severity:** High
**Location:** SKILL.md + references/
**Pillar Affected:** PDA

**Problem:** No progressive disclosure structure - no reference files to contain detailed instructions

**Current:**
```
No references/ directory or files
```

**Suggested Rewrite:**
```
Create references/ directory with detailed guides, templates, and examples
```

**Impact:** +10 points

---

## General Recommendations

1. Focus on improving Spec Compliance (currently 0/15)
2. Focus on improving Pda (currently 3/30)
3. Focus on improving Ease Of Use (currently 4/25)
4. Focus on improving Writing Style (currently 2/10)
5. Focus on improving Utility (currently 0/20)

---

## Grade Scale

| Grade | Score | Description |
|-------|-------|-------------|
| A | 90-100 | Production-ready |
| B | 80-89 | Good, minor work |
| C | 70-79 | Adequate, gaps |
| D | 60-69 | Needs work |
| F | <60 | Major revision |

---

---

## About This Report

This evaluation uses the [Claude Skills Best Practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices).

**Powered by:**
- [SkillzWave](https://skillzwave.ai) - Claude Skills Marketplace
- [SpillWave](https://spillwave.com) - AI Solutions

*Report generated for [SpillwaveSolutions/skilz-cli](https://github.com/SpillwaveSolutions/skilz-cli/blob/main/.gemini/skills/test-skill/SKILL.md)*

## JSON Output

```json
{
  "skill_name": "test-skill",
  "evaluated_at": "2026-01-12T20:48:59.092313",
  "files_reviewed": [
    ".gemini/skills/test-skill/SKILL.md"
  ],
  "scores": {
    "spec_compliance": {
      "total": 0,
      "max": 15,
      "breakdown": {
        "frontmatter_validity": {
          "score": 0,
          "max": 5,
          "assessment": "No frontmatter found"
        },
        "name_conventions": {
          "score": 0,
          "max": 4,
          "assessment": "No frontmatter to check name"
        },
        "description_quality": {
          "score": 0,
          "max": 4,
          "assessment": "No frontmatter to check description"
        },
        "optional_fields": {
          "score": 0,
          "max": 2,
          "assessment": "No frontmatter"
        }
      }
    },
    "pda": {
      "total": 3,
      "max": 30,
      "breakdown": {
        "token_economy": {
          "score": 2,
          "max": 10,
          "assessment": "Minimal tokens but provides zero value - concise to the point of being non-functional"
        },
        "layered_structure": {
          "score": 1,
          "max": 10,
          "assessment": "No layered structure exists; single file with no content hierarchy"
        },
        "reference_depth": {
          "score": 0,
          "max": 5,
          "assessment": "No reference files present; no progressive disclosure architecture"
        },
        "navigation_signals": {
          "score": 0,
          "max": 5,
          "assessment": "No headers, no TOC, no navigation aids in 2-line file"
        }
      }
    },
    "ease_of_use": {
      "total": 4,
      "max": 25,
      "breakdown": {
        "metadata_quality": {
          "score": 3,
          "max": 10,
          "assessment": "Name follows conventions but description is completely generic with no specificity"
        },
        "discoverability": {
          "score": 0,
          "max": 6,
          "assessment": "No trigger terms defined; 'Test skill' provides no activation context"
        },
        "terminology_consistency": {
          "score": 1,
          "max": 4,
          "assessment": "No terminology to evaluate; trivially consistent but empty"
        },
        "workflow_clarity": {
          "score": 0,
          "max": 5,
          "assessment": "No workflow, no steps, no instructions of any kind"
        }
      }
    },
    "writing_style": {
      "total": 2,
      "max": 10,
      "breakdown": {
        "voice_and_tense": {
          "score": 1,
          "max": 4,
          "assessment": "No instructional content to evaluate voice; neutral but absent"
        },
        "objectivity": {
          "score": 1,
          "max": 3,
          "assessment": "No marketing language present; purely empty rather than instructional"
        },
        "conciseness": {
          "score": 0,
          "max": 3,
          "assessment": "Beyond concise - vacuous; no content density because no content"
        }
      }
    },
    "utility": {
      "total": 0,
      "max": 20,
      "breakdown": {
        "problem_solving_power": {
          "score": 0,
          "max": 8,
          "assessment": "Addresses no capability gaps; provides no functionality whatsoever"
        },
        "degrees_of_freedom": {
          "score": 0,
          "max": 5,
          "assessment": "No constraints or guidance; skill is a placeholder with no implementation"
        },
        "feedback_loops": {
          "score": 0,
          "max": 4,
          "assessment": "No validation steps, no run\u2192check\u2192fix patterns defined"
        },
        "examples_and_templates": {
          "score": 0,
          "max": 3,
          "assessment": "No examples, no templates, no input/output pairs"
        }
      }
    }
  },
  "modifiers": {
    "penalties": [
      {
        "name": "missing_required_field",
        "points": -3
      }
    ],
    "bonuses": [],
    "net": -3
  },
  "final_score": 6,
  "grade": "F",
  "critical_issues": [
    {
      "rank": 1,
      "title": "Invalid or incomplete frontmatter",
      "severity": "High",
      "location": "SKILL.md:frontmatter",
      "pillar": "spec_compliance",
      "problem": "No frontmatter found",
      "current": "(no frontmatter)",
      "suggested": "---\nname: test-skill\ndescription: Describe what this skill does. Use when asked to \"...\", \"...\", or \"...\".\n---",
      "impact": "+5 points"
    },
    {
      "rank": 1,
      "title": "Skill is a placeholder",
      "severity": "High",
      "location": "SKILL.md:entire file",
      "pillar": "Utility",
      "problem": "Skill contains only metadata with no actual instructions or functionality",
      "current": "name: test-skill\ndescription: Test skill",
      "suggested": "Add purpose statement, workflow steps, examples, and reference files defining actual skill behavior",
      "impact": "+60 points"
    },
    {
      "rank": 2,
      "title": "Name convention violations",
      "severity": "High",
      "location": "SKILL.md:frontmatter:name",
      "pillar": "spec_compliance",
      "problem": "No frontmatter to check name",
      "current": "(no name)",
      "suggested": "name: test-skill",
      "impact": "+4 points"
    },
    {
      "rank": 2,
      "title": "Generic non-descriptive description",
      "severity": "High",
      "location": "SKILL.md:description",
      "pillar": "Ease of Use",
      "problem": "Description 'Test skill' provides no information about what the skill does or when to use it",
      "current": "description: Test skill",
      "suggested": "description: Validates X by performing Y. Use when 'testing Z', 'verifying W', or 'checking Q'.",
      "impact": "+8 points"
    },
    {
      "rank": 3,
      "title": "Description needs trigger phrases",
      "severity": "High",
      "location": "SKILL.md:frontmatter:description",
      "pillar": "spec_compliance",
      "problem": "No frontmatter to check description",
      "current": "(no description)",
      "suggested": "description: Performs test skill operations. Use when asked to \"test skill\", \"run test skill\", or \"test skill help\".",
      "impact": "+4 points"
    },
    {
      "rank": 3,
      "title": "No trigger terms",
      "severity": "High",
      "location": "SKILL.md:description",
      "pillar": "Ease of Use",
      "problem": "No trigger phrases defined - skill cannot be discovered or activated appropriately",
      "current": "No triggers present",
      "suggested": "Add specific trigger terms in description: 'Use when X', 'Triggers on Y, Z, W'",
      "impact": "+6 points"
    },
    {
      "rank": 4,
      "title": "Missing reference architecture",
      "severity": "High",
      "location": "SKILL.md + references/",
      "pillar": "PDA",
      "problem": "No progressive disclosure structure - no reference files to contain detailed instructions",
      "current": "No references/ directory or files",
      "suggested": "Create references/ directory with detailed guides, templates, and examples",
      "impact": "+10 points"
    }
  ],
  "recommendations": [
    "Focus on improving Spec Compliance (currently 0/15)",
    "Focus on improving Pda (currently 3/30)",
    "Focus on improving Ease Of Use (currently 4/25)",
    "Focus on improving Writing Style (currently 2/10)",
    "Focus on improving Utility (currently 0/20)"
  ],
  "code_quality": null,
  "grading_model": "Claude (default)",
  "grading_provider": "claude"
}
```

**Links:**
- 📁 **GitHub:** [spillwavesolutions/skilz-cli](https://github.com/spillwavesolutions/skilz-cli/blob/main/SKILL.md)
- 🛒 **Marketplace:** [View on SkillzWave](https://skillzwave.ai/skill/spillwavesolutions__skilz-cli__test-skill__SKILL/)
- 📤 **Submit Skill:** [Submit to SkillzWave](https://skillzwave.ai/submit/) - Skills are ranked, graded, and scanned for security
- 📊 **Tracking:** [All Graded Skills](https://github.com/SpillwaveSolutions/skill_improver/issues)

---

## 📦 Recommended: Add Universal Installer Instructions

Consider adding these installation instructions to your README.md to help users install this skill across 14+ AI coding agents:

```markdown
## Installing with Skilz (Universal Installer)

The recommended way to install this skill across different AI coding agents is using the **skilz** universal installer.

### Install Skilz

```bash
pip install skilz
```

This skill supports [Agent Skill Standard](https://agentskills.io/) which means it supports 14 plus coding agents including Claude Code, OpenAI Codex, Cursor and Gemini.


### Git URL Options

```

# Install for Claude Code (your home directory)
skilz install -g https://github.com/spillwavesolutions/skilz-cli

# Or from the SkillzWave marketplace
skilz install spillwavesolutions__skilz-cli__test-skill
```

### Claude Code

Install to user home (available in all projects):
```bash
skilz install -g https://github.com/spillwavesolutions/skilz-cli
```

Install to current project only:
```bash
skilz install -g https://github.com/spillwavesolutions/skilz-cli --project
```

### OpenCode

Install for [OpenCode](https://opencode.ai):

```bash

# OpenCode
skilz install https://github.com/spillwavesolutions/skilz-cli --agent opencode

```

Install for Codex and Gemini too
```
# Gemini CLI
skilz install https://github.com/spillwavesolutions/skilz-cli --agent gemini


# OpenAI Codex
skilz install https://github.com/spillwavesolutions/skilz-cli --agent codex

```

Project-level install:
```bash
skilz install https://github.com/spillwavesolutions/skilz-cli --project --agent codex
```


### Install from Skillzwave Marketplace
```bash
skilz install spillwavesolutions__skilz-cli__test-skill --project
```

See this site [skill Listing](https://skillzwave.ai/skill/spillwavesolutions__skilz-cli__test-skill__SKILL/) to see how to install this exact skill to 14+ different coding agents.


### Other Supported Agents

Skilz supports 20+ coding agents including Claude Code, OpenAI Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, Windsurf, Qwen Code, Aidr, and more.

See the [skill on SkillzWave](https://skillzwave.ai/skill/spillwavesolutions__skilz-cli__test-skill__SKILL/) for agent-specific install commands, or check the [skilz-cli docs](https://github.com/SpillwaveSolutions/skilz-cli).


[SkillzWave](https://skillzwave.ai) is a skill marketplace for AI agents. [SpillWave](https://spillwave.com) (where I work) builds AI agent tools.
```

---

## About This Report

This evaluation uses the [Claude Skills Best Practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices).

**Powered by:**
- [SkillzWave](https://skillzwave.ai) - Claude Skills Marketplace
- [SpillWave](https://spillwave.com) - AI Solutions

*Report generated for [spillwavesolutions/skilz-cli](https://github.com/spillwavesolutions/skilz-cli/blob/main/SKILL.md)*

Pillar	Score	Max
Spec Compliance	0	15
Progressive Disclosure	3	30
Ease of Use	4	25
Writing Style	2	10
Utility	0	20
Modifiers	-3	±15

Pillar	Score	Max
Progressive Disclosure Architecture	3	30
Ease of Use	4	25
Spec Compliance	0	15
Writing Style	2	10
Utility	0	20
Modifiers	-3	±15

Criterion	Score	Max	Assessment
Token Economy	2	10	Minimal tokens but provides zero value - concise to the point of being non-functional
Layered Structure	1	10	No layered structure exists; single file with no content hierarchy
Reference Depth	0	5	No reference files present; no progressive disclosure architecture
Navigation Signals	0	5	No headers, no TOC, no navigation aids in 2-line file

Criterion	Score	Max	Assessment
Metadata Quality	3	10	Name follows conventions but description is completely generic with no specificity
Discoverability	0	6	No trigger terms defined; 'Test skill' provides no activation context
Terminology Consistency	1	4	No terminology to evaluate; trivially consistent but empty
Workflow Clarity	0	5	No workflow, no steps, no instructions of any kind

Criterion	Max	Assessment
Frontmatter Validity	5	No frontmatter found
Name Conventions	4	No frontmatter to check name
Description Quality	4	No frontmatter to check description
Optional Fields	2	No frontmatter

Criterion	Score	Max	Assessment
Voice And Tense	1	4	No instructional content to evaluate voice; neutral but absent
Objectivity	1	3	No marketing language present; purely empty rather than instructional
Conciseness	0	3	Beyond concise - vacuous; no content density because no content

Criterion	Max	Assessment
Problem Solving Power	8	Addresses no capability gaps; provides no functionality whatsoever
Degrees Of Freedom	5	No constraints or guidance; skill is a placeholder with no implementation
Feedback Loops	4	No validation steps, no run→check→fix patterns defined
Examples And Templates	3	No examples, no templates, no input/output pairs

Grade	Score	Description
A	90-100	Production-ready
B	80-89	Good, minor work
C	70-79	Adequate, gaps
D	60-69	Needs work
F	<60	Major revision

Agent Skill Grading Report: test-skill - Score 6/100 (F) #41

Description

❌ Agent Skill Grading Report

Quick Summary of Agent Skill Grades

Pillar Scores for Agent Skill

Issues Found: 7

📊 Full Grading Report for Agent Skill

Skill Evaluation Report: test-skill

Overall Score: 6/100

Executive Summary

Detailed Scores

Progressive Disclosure Architecture (3/30)

Ease of Use (4/25)

Spec Compliance (0/15)

Writing Style (2/10)

Utility (0/20)

Modifiers Applied (-3)

Critical Issues (Top 7)

Issue 1: Invalid or incomplete frontmatter

Issue 1: Skill is a placeholder

Issue 2: Name convention violations

Issue 2: Generic non-descriptive description

Issue 3: Description needs trigger phrases

Issue 3: No trigger terms

Issue 4: Missing reference architecture

General Recommendations

Grade Scale

About This Report

JSON Output

📦 Recommended: Add Universal Installer Instructions

Git URL Options

Claude Code

OpenCode

Install from Skillzwave Marketplace

Other Supported Agents

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions