Agent Skill Grading Report: using-claude-code-cli - Score 92/100 (A)

# 🏆 Agent Skill Grading Report

**Score:** 92/100 | **Grade:** A

## Quick Summary of Agent Skill Grades

### Pillar Scores for Agent Skill

| Pillar | Score | Max |
|--------|-------|-----|
| Spec Compliance | 12 | 15 |
| Progressive Disclosure | 27 | 30 |
| Ease of Use | 23 | 25 |
| Writing Style | 9 | 10 |
| Utility | 18 | 20 |
| Modifiers | +3 | ±15 |

### Issues Found: 3
- 🔴 High: 1
- 🟡 Medium: 0
- 🟢 Low: 2

## 📊 Full Grading Report for Agent Skill

# Skill Evaluation Report: using-claude-code-cli

**Links:**
- 📁 **GitHub:** [SpillwaveSolutions/using-claude-code-cli-agent-skill](https://github.com/SpillwaveSolutions/using-claude-code-cli-agent-skill/blob/main/SKILL.md)
- 🛒 **Marketplace:** [View on SkillzWave](https://skillzwave.ai/skill/spillwavesolutions__using-claude-code-cli-agent-skill__using-claude-code-cli-agent-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:** SKILL.md, README.md, references/json-extraction.md, references/subprocess-patterns.md, references/hooks-examples.md, references/cli-reference.md
**Grading Model:** Claude (default) (via claude)

---

## Overall Score: 92/100

| Pillar | Score | Max |
|--------|-------|-----|
| Progressive Disclosure Architecture | 27 | 30 |
| Ease of Use | 23 | 25 |
| Spec Compliance | 12 | 15 |
| Writing Style | 9 | 10 |
| Utility | 18 | 20 |
| Modifiers | +3 | ±15 |

**Grade: A**

---

## Executive Summary

This skill demonstrates excellent quality with a score of 92/100. Strongest area: **Ease of Use** (23/25). Address 1 high-severity issues for significant score improvement.

---

## Detailed Scores

### Progressive Disclosure Architecture (27/30)

| Criterion | Score | Max | Assessment |
|-----------|-------|-----|------------|
| Token Economy | 9 | 10 | SKILL.md is dense and practical with checklist, tables, and code samples; minor redundancy between SKILL.md and cli-reference.md flag tables |
| Layered Structure | 9 | 10 | Excellent separation: 213-line SKILL.md overview with 5 specialized reference files totaling ~1200 lines of deep technical content |
| Reference Depth | 5 | 5 | All references are exactly one level deep from SKILL.md; no nested reference chains |
| Navigation Signals | 4 | 5 | TOC in SKILL.md and all reference files; clear section headers; missing TOC in orchestrator_example.py (300+ lines) |

### Ease of Use (23/25)

| Criterion | Score | Max | Assessment |
|-----------|-------|-----|------------|
| Metadata Quality | 9 | 10 | Name follows conventions; description includes specific triggers like 'spawn claude subprocess' and '--allowedTools'; category and tags present |
| Discoverability | 6 | 6 | 12 specific triggers covering CLI flags, automation patterns, and use cases; excellent activation coverage |
| Terminology Consistency | 4 | 4 | Consistent use of 'invoke', 'subprocess', 'automation'; tools vs flags clearly distinguished throughout |
| Workflow Clarity | 4 | 5 | 8-step checklist with checkboxes; validation section with numbered steps; troubleshooting table; missing step numbers in some reference sections |

### Spec Compliance (12/15)

| Criterion | Score | Max | Assessment |
|-----------|-------|-----|------------|
| Frontmatter Validity | 5 | 5 | Valid YAML with required fields |
| Name Conventions | 1 | 4 | Reserved word used in name |
| Description Quality | 4 | 4 | Third-person with good trigger coverage |
| Optional Fields | 2 | 2 | Uses allowed-tools, license, metadata |

### Writing Style (9/10)

| Criterion | Score | Max | Assessment |
|-----------|-------|-----|------------|
| Voice And Tense | 4 | 4 | Imperative form throughout: 'Copy and track', 'Enable sandbox', 'Use --output-format json'; no second-person pronouns |
| Objectivity | 3 | 3 | Purely instructional with no marketing language; technical descriptions are neutral and factual |
| Conciseness | 2 | 3 | Generally dense but some redundancy: Core CLI Flags table in SKILL.md duplicates content in cli-reference.md |

### Utility (18/20)

| Criterion | Score | Max | Assessment |
|-----------|-------|-----|------------|
| Problem Solving Power | 7 | 8 | Addresses real gap in Claude Code automation from external orchestrators; covers sync/async/parallel patterns and fallback strategies |
| Degrees Of Freedom | 5 | 5 | Appropriate constraints: specifies when NOT to use skill; provides patterns rather than rigid recipes; allows tool/model customization |
| Feedback Loops | 3 | 4 | Validation section with 4 test commands; troubleshooting table; return code checking in all code examples |
| Examples And Templates | 3 | 3 | Complete orchestrator class; multiple pattern variations; input/output shown for JSON extraction; checklist template provided |

### Modifiers Applied (+3)

**Penalties:** reserved_words_in_name (-5), deeply_nested_references (-2)
**Bonuses:** self_documenting_scripts (+2), copy_paste_checklists (+2), grep_friendly_structure (+1), exemplary_examples (+2), explicit_scope_boundaries (+1), trigger_phrases_4plus (+1), gerund_style_name (+1)

---

## Critical Issues (Top 3)

### Issue 1: Name convention violations

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

**Problem:** Reserved word used in name

**Current:**
```
name: using-claude-code-cli
```

**Suggested Rewrite:**
```
name: using-claude-code-cli-agent-skill
```

**Impact:** +3 points

---

### Issue 1: Duplicate CLI flags table

**Severity:** Low
**Location:** SKILL.md:Core CLI Flags
**Pillar Affected:** Writing Style

**Problem:** Core CLI Flags table in SKILL.md duplicates 7 flags already covered in cli-reference.md, consuming tokens unnecessarily

**Current:**
```
Full table with Flag, Purpose, Example columns for 7 flags
```

**Suggested Rewrite:**
```
Keep only 3 essential flags (-p, --allowedTools, --add-dir) with 'See cli-reference.md for all flags'
```

**Impact:** +1 point conciseness

---

### Issue 2: Missing orchestrator docstring TOC

**Severity:** Low
**Location:** references/orchestrator_example.py
**Pillar Affected:** PDA

**Problem:** 316-line Python file lacks class-level docstring with method overview; navigation requires scrolling

**Current:**
```
Single-line module docstring only
```

**Suggested Rewrite:**
```
Add class docstring listing key methods: build_command, invoke_sync, invoke_async, invoke_parallel
```

**Impact:** +1 point navigation signals

---

## General Recommendations

1. Address 1 high-severity issues first
2. Add trigger phrases to description for discoverability
3. Add table of contents for files over 100 lines

---

## 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/using-claude-code-cli-agent-skill](https://github.com/SpillwaveSolutions/using-claude-code-cli-agent-skill/blob/main/SKILL.md)*

## JSON Output

```json
{
  "skill_name": "using-claude-code-cli",
  "evaluated_at": "2026-01-12T20:51:36.167836",
  "files_reviewed": [
    "SKILL.md",
    "README.md",
    "references/json-extraction.md",
    "references/subprocess-patterns.md",
    "references/hooks-examples.md",
    "references/cli-reference.md"
  ],
  "scores": {
    "spec_compliance": {
      "total": 12,
      "max": 15,
      "breakdown": {
        "frontmatter_validity": {
          "score": 5,
          "max": 5,
          "assessment": "Valid YAML with required fields"
        },
        "name_conventions": {
          "score": 1,
          "max": 4,
          "assessment": "Reserved word used in name"
        },
        "description_quality": {
          "score": 4,
          "max": 4,
          "assessment": "Third-person with good trigger coverage"
        },
        "optional_fields": {
          "score": 2,
          "max": 2,
          "assessment": "Uses allowed-tools, license, metadata"
        }
      }
    },
    "pda": {
      "total": 27,
      "max": 30,
      "breakdown": {
        "token_economy": {
          "score": 9,
          "max": 10,
          "assessment": "SKILL.md is dense and practical with checklist, tables, and code samples; minor redundancy between SKILL.md and cli-reference.md flag tables"
        },
        "layered_structure": {
          "score": 9,
          "max": 10,
          "assessment": "Excellent separation: 213-line SKILL.md overview with 5 specialized reference files totaling ~1200 lines of deep technical content"
        },
        "reference_depth": {
          "score": 5,
          "max": 5,
          "assessment": "All references are exactly one level deep from SKILL.md; no nested reference chains"
        },
        "navigation_signals": {
          "score": 4,
          "max": 5,
          "assessment": "TOC in SKILL.md and all reference files; clear section headers; missing TOC in orchestrator_example.py (300+ lines)"
        }
      }
    },
    "ease_of_use": {
      "total": 23,
      "max": 25,
      "breakdown": {
        "metadata_quality": {
          "score": 9,
          "max": 10,
          "assessment": "Name follows conventions; description includes specific triggers like 'spawn claude subprocess' and '--allowedTools'; category and tags present"
        },
        "discoverability": {
          "score": 6,
          "max": 6,
          "assessment": "12 specific triggers covering CLI flags, automation patterns, and use cases; excellent activation coverage"
        },
        "terminology_consistency": {
          "score": 4,
          "max": 4,
          "assessment": "Consistent use of 'invoke', 'subprocess', 'automation'; tools vs flags clearly distinguished throughout"
        },
        "workflow_clarity": {
          "score": 4,
          "max": 5,
          "assessment": "8-step checklist with checkboxes; validation section with numbered steps; troubleshooting table; missing step numbers in some reference sections"
        }
      }
    },
    "writing_style": {
      "total": 9,
      "max": 10,
      "breakdown": {
        "voice_and_tense": {
          "score": 4,
          "max": 4,
          "assessment": "Imperative form throughout: 'Copy and track', 'Enable sandbox', 'Use --output-format json'; no second-person pronouns"
        },
        "objectivity": {
          "score": 3,
          "max": 3,
          "assessment": "Purely instructional with no marketing language; technical descriptions are neutral and factual"
        },
        "conciseness": {
          "score": 2,
          "max": 3,
          "assessment": "Generally dense but some redundancy: Core CLI Flags table in SKILL.md duplicates content in cli-reference.md"
        }
      }
    },
    "utility": {
      "total": 18,
      "max": 20,
      "breakdown": {
        "problem_solving_power": {
          "score": 7,
          "max": 8,
          "assessment": "Addresses real gap in Claude Code automation from external orchestrators; covers sync/async/parallel patterns and fallback strategies"
        },
        "degrees_of_freedom": {
          "score": 5,
          "max": 5,
          "assessment": "Appropriate constraints: specifies when NOT to use skill; provides patterns rather than rigid recipes; allows tool/model customization"
        },
        "feedback_loops": {
          "score": 3,
          "max": 4,
          "assessment": "Validation section with 4 test commands; troubleshooting table; return code checking in all code examples"
        },
        "examples_and_templates": {
          "score": 3,
          "max": 3,
          "assessment": "Complete orchestrator class; multiple pattern variations; input/output shown for JSON extraction; checklist template provided"
        }
      }
    }
  },
  "modifiers": {
    "penalties": [
      {
        "name": "reserved_words_in_name",
        "points": -5
      },
      {
        "name": "deeply_nested_references",
        "points": -2
      }
    ],
    "bonuses": [
      {
        "name": "self_documenting_scripts",
        "points": 2
      },
      {
        "name": "copy_paste_checklists",
        "points": 2
      },
      {
        "name": "grep_friendly_structure",
        "points": 1
      },
      {
        "name": "exemplary_examples",
        "points": 2
      },
      {
        "name": "explicit_scope_boundaries",
        "points": 1
      },
      {
        "name": "trigger_phrases_4plus",
        "points": 1
      },
      {
        "name": "gerund_style_name",
        "points": 1
      }
    ],
    "net": 3
  },
  "final_score": 92,
  "grade": "A",
  "critical_issues": [
    {
      "rank": 1,
      "title": "Name convention violations",
      "severity": "High",
      "location": "SKILL.md:frontmatter:name",
      "pillar": "spec_compliance",
      "problem": "Reserved word used in name",
      "current": "name: using-claude-code-cli",
      "suggested": "name: using-claude-code-cli-agent-skill",
      "impact": "+3 points"
    },
    {
      "rank": 1,
      "title": "Duplicate CLI flags table",
      "severity": "Low",
      "location": "SKILL.md:Core CLI Flags",
      "pillar": "Writing Style",
      "problem": "Core CLI Flags table in SKILL.md duplicates 7 flags already covered in cli-reference.md, consuming tokens unnecessarily",
      "current": "Full table with Flag, Purpose, Example columns for 7 flags",
      "suggested": "Keep only 3 essential flags (-p, --allowedTools, --add-dir) with 'See cli-reference.md for all flags'",
      "impact": "+1 point conciseness"
    },
    {
      "rank": 2,
      "title": "Missing orchestrator docstring TOC",
      "severity": "Low",
      "location": "references/orchestrator_example.py",
      "pillar": "PDA",
      "problem": "316-line Python file lacks class-level docstring with method overview; navigation requires scrolling",
      "current": "Single-line module docstring only",
      "suggested": "Add class docstring listing key methods: build_command, invoke_sync, invoke_async, invoke_parallel",
      "impact": "+1 point navigation signals"
    }
  ],
  "recommendations": [
    "Address 1 high-severity issues first",
    "Add trigger phrases to description for discoverability",
    "Add table of contents for files over 100 lines"
  ],
  "code_quality": null,
  "grading_model": "Claude (default)",
  "grading_provider": "claude"
}
```

**Links:**
- 📁 **GitHub:** [spillwavesolutions/using-claude-code-cli-agent-skill](https://github.com/spillwavesolutions/using-claude-code-cli-agent-skill/blob/main/SKILL.md)
- 🛒 **Marketplace:** [View on SkillzWave](https://skillzwave.ai/skill/spillwavesolutions__using-claude-code-cli-agent-skill__using-claude-code-cli-agent-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/using-claude-code-cli-agent-skill

# Or from the SkillzWave marketplace
skilz install spillwavesolutions__using-claude-code-cli-agent-skill__using-claude-code-cli-agent-skill
```

### Claude Code

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

Install to current project only:
```bash
skilz install -g https://github.com/spillwavesolutions/using-claude-code-cli-agent-skill --project
```

### OpenCode

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

```bash

# OpenCode
skilz install https://github.com/spillwavesolutions/using-claude-code-cli-agent-skill --agent opencode

```

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


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

```

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


### Install from Skillzwave Marketplace
```bash
skilz install spillwavesolutions__using-claude-code-cli-agent-skill__using-claude-code-cli-agent-skill --project
```

See this site [skill Listing](https://skillzwave.ai/skill/spillwavesolutions__using-claude-code-cli-agent-skill__using-claude-code-cli-agent-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__using-claude-code-cli-agent-skill__using-claude-code-cli-agent-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/using-claude-code-cli-agent-skill](https://github.com/spillwavesolutions/using-claude-code-cli-agent-skill/blob/main/SKILL.md)*

Pillar	Score	Max
Spec Compliance	12	15
Progressive Disclosure	27	30
Ease of Use	23	25
Writing Style	9	10
Utility	18	20
Modifiers	+3	±15

Pillar	Score	Max
Progressive Disclosure Architecture	27	30
Ease of Use	23	25
Spec Compliance	12	15
Writing Style	9	10
Utility	18	20
Modifiers	+3	±15

Criterion	Score	Max	Assessment
Token Economy	9	10	SKILL.md is dense and practical with checklist, tables, and code samples; minor redundancy between SKILL.md and cli-reference.md flag tables
Layered Structure	9	10	Excellent separation: 213-line SKILL.md overview with 5 specialized reference files totaling ~1200 lines of deep technical content
Reference Depth	5	5	All references are exactly one level deep from SKILL.md; no nested reference chains
Navigation Signals	4	5	TOC in SKILL.md and all reference files; clear section headers; missing TOC in orchestrator_example.py (300+ lines)

Criterion	Score	Max	Assessment
Metadata Quality	9	10	Name follows conventions; description includes specific triggers like 'spawn claude subprocess' and '--allowedTools'; category and tags present
Discoverability	6	6	12 specific triggers covering CLI flags, automation patterns, and use cases; excellent activation coverage
Terminology Consistency	4	4	Consistent use of 'invoke', 'subprocess', 'automation'; tools vs flags clearly distinguished throughout
Workflow Clarity	4	5	8-step checklist with checkboxes; validation section with numbered steps; troubleshooting table; missing step numbers in some reference sections

Criterion	Score	Max	Assessment
Frontmatter Validity	5	5	Valid YAML with required fields
Name Conventions	1	4	Reserved word used in name
Description Quality	4	4	Third-person with good trigger coverage
Optional Fields	2	2	Uses allowed-tools, license, metadata

Criterion	Score	Max	Assessment
Voice And Tense	4	4	Imperative form throughout: 'Copy and track', 'Enable sandbox', 'Use --output-format json'; no second-person pronouns
Objectivity	3	3	Purely instructional with no marketing language; technical descriptions are neutral and factual
Conciseness	2	3	Generally dense but some redundancy: Core CLI Flags table in SKILL.md duplicates content in cli-reference.md

Criterion	Score	Max	Assessment
Problem Solving Power	7	8	Addresses real gap in Claude Code automation from external orchestrators; covers sync/async/parallel patterns and fallback strategies
Degrees Of Freedom	5	5	Appropriate constraints: specifies when NOT to use skill; provides patterns rather than rigid recipes; allows tool/model customization
Feedback Loops	3	4	Validation section with 4 test commands; troubleshooting table; return code checking in all code examples
Examples And Templates	3	3	Complete orchestrator class; multiple pattern variations; input/output shown for JSON extraction; checklist template provided

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: using-claude-code-cli - Score 92/100 (A) #17

Description

🏆 Agent Skill Grading Report

Quick Summary of Agent Skill Grades

Pillar Scores for Agent Skill

Issues Found: 3

📊 Full Grading Report for Agent Skill

Skill Evaluation Report: using-claude-code-cli

Overall Score: 92/100

Executive Summary

Detailed Scores

Progressive Disclosure Architecture (27/30)

Ease of Use (23/25)

Spec Compliance (12/15)

Writing Style (9/10)

Utility (18/20)

Modifiers Applied (+3)

Critical Issues (Top 3)

Issue 1: Name convention violations

Issue 1: Duplicate CLI flags table

Issue 2: Missing orchestrator docstring TOC

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

Fields

Projects

Milestone

Relationships

Development

Issue actions