when-analyzing-skill-gaps-use-skill-gap-analyzer

name	when-analyzing-skill-gaps-use-skill-gap-analyzer
description	Analyze skill library to identify coverage gaps, redundant overlaps, optimization opportunities, and provide recommendations for skill portfolio improvement Use when this capability is needed.
metadata	{"author":"dnyoussef"}

Skill Gap Analyzer

Purpose: Perform comprehensive analysis of skill library to identify missing capabilities, redundant functionality, optimization opportunities, and provide actionable recommendations for skill portfolio improvement.

When to Use This Skill

• When building a new skill library
• Quarterly skill portfolio reviews
• Before large refactoring efforts
• When considering new skill additions
• After major project pivots
• When optimizing resource allocation

Analysis Dimensions

1. Coverage Gap Analysis

• Domain coverage mapping
• Missing capability identification
• Use case scenario testing
• Workflow completeness assessment
• Integration point analysis

2. Redundancy Detection

• Duplicate functionality identification
• Overlapping capability mapping
• Consolidation opportunity analysis
• Version conflict detection
• Naming collision identification

3. Optimization Opportunities

• Under-utilized skill detection
• Over-complex skill identification
• Composability improvement suggestions
• Dependency optimization
• Performance bottleneck analysis

4. Usage Pattern Analysis

• Frequency metrics
• Co-occurrence patterns
• Success rate tracking
• Token efficiency measurement
• Agent utilization patterns

5. Recommendation Generation

• Prioritized action items
• Consolidation strategies
• New skill proposals
• Deprecation candidates
• Restructuring plans

Execution Process

Phase 1: Library Inventory

# Initialize analysis session
npx claude-flow@alpha hooks pre-task --description "Analyzing skill library gaps"

# Scan skill directories
find ~/.claude/skills -name "SKILL.md" -o -name "*.skill.md"

Inventory Script:

function inventorySkills(skillDirectory) {
  const inventory = {
    totalSkills: 0,
    categories: {},
    capabilities: {},
    agents: {},
    complexity: {},
    tags: {}
  };

  // Parse each SKILL.md file
  const skillFiles = findSkillFiles(skillDirectory);

  for (const file of skillFiles) {
    const metadata = parseYAMLFrontmatter(file);

    inventory.totalSkills++;

    // Categorize by path
    const category = extractCategory(file);
    inventory.categories[category] = (inventory.categories[category] || 0) + 1;

    // Track capabilities
    const capabilities = extractCapabilities(metadata.description);
    capabilities.forEach(cap => {
      inventory.capabilities[cap] = (inventory.capabilities[cap] || []);
      inventory.capabilities[cap].push(metadata.name);
    });

    // Track required agents
    if (metadata.agents_required) {
      metadata.agents_required.forEach(agent => {
        inventory.[agent] = (inventory.[agent] || ) + ;
      });
    }

    
    inventory.[metadata. || ] =
      (inventory.[metadata. || ] || ) + ;

    
     (metadata.) {
      metadata..( {
        inventory.[tag] = (inventory.[tag] || ) + ;
      });
    }
  }

   inventory;
}

 () {
  
   capabilities = [];

   verbs = description.() || [];

  capabilities.(...verbs.( v.()));

   [... (capabilities)]; 
}

Store Inventory:

npx claude-flow@alpha memory store --key "gap-analysis/inventory" --value "{
  \"totalSkills\": <count>,
  \"categories\": {...},
  \"capabilities\": {...},
  \"timestamp\": \"<ISO8601>\"
}"

Phase 2: Coverage Gap Detection

Domain Coverage Matrix:

function analyzeCoverageGaps(inventory, requiredDomains) {
  const gaps = [];

  // Define comprehensive domain requirements
  const domains = {
    "Development": [
      "code-generation", "testing", "debugging", "refactoring",
      "documentation", "code-review", "architecture"
    ],
    "DevOps": [
      "deployment", "monitoring", "ci-cd", "infrastructure",
      "security", "scaling", "backup-recovery"
    ],
    "Project Management": [
      "planning", "estimation", "tracking", "reporting",
      "risk-management", "stakeholder-communication"
    ],
    "Data": [
      "data-analysis", "data-transformation", "data-validation",
      "data-migration", "data-visualization"
    ],
    "AI/ML": [
      "model-training", "inference", "optimization",
      "evaluation", "deployment", "monitoring"
    ],
    "Integration": [
      "api-integration", "webhook-handling", "event-processing",
      "message-queue", 
    ]
  };

  
   ( [domain, capabilities]  .(domains)) {
     coverage = capabilities.( {
       covered = inventory.[cap]?. > ;
       skills = inventory.[cap] || [];
       { : cap, covered, skills };
    });

     missingCaps = coverage.( !c.);

     (missingCaps. > ) {
      gaps.({
        : domain,
        : ((capabilities. - missingCaps.) / capabilities. * ).() + ,
        : missingCaps.( c.),
        : (domain, missingCaps., capabilities.)
      });
    }
  }

   gaps;
}

 () {
   coverageRatio =  - (missingCount / totalCount);
   domainImportance = {
    : ,
    : ,
    : ,
    : ,
    : ,
    : 
  };

   score = coverageRatio * (domainImportance[domain] || );

   (score < )  ;
   (score < )  ;
   (score < )  ;
   ;
}

Use Case Scenario Testing:

function testScenarioCoverage(inventory) {
  const scenarios = [
    {
      name: "Full-stack web app development",
      requiredCapabilities: [
        "code-generation", "testing", "database-design",
        "api-integration", "deployment", "monitoring"
      ]
    },
    {
      name: "ML model training and deployment",
      requiredCapabilities: [
        "data-analysis", "model-training", "evaluation",
        "optimization", "deployment", "monitoring"
      ]
    },
    {
      name: "GitHub workflow automation",
      requiredCapabilities: [
        "code-review", "testing", "ci-cd", "release-management",
        "issue-tracking", "documentation"
      ]
    },
    {
      name: "Prompt engineering and optimization",
      requiredCapabilities: [
        "prompt-analysis", "optimization", "testing",
        "documentation", "version-control"
      ]
    }
  ];

  const scenarioResults = scenarios.map(scenario => {
    const coverage = scenario.requiredCapabilities.map( ({
      : cap,
      : inventory.[cap]?. > ,
      : inventory.[cap] || []
    }));

     coveragePercent = (coverage.( c.). /
                            coverage. * ).();

     {
      : scenario.,
      : coveragePercent + ,
      : coverage.( !c.).( c.),
      : coverage.( c.)
    };
  });

   scenarioResults;
}

Phase 3: Redundancy Detection

Overlap Analysis:

function detectRedundancy(inventory) {
  const redundancies = [];

  // Find capabilities handled by multiple skills
  for (const [capability, skills] of Object.entries(inventory.capabilities)) {
    if (skills.length > 2) {
      // Analyze actual overlap
      const skillDetails = skills.map(name => loadSkillDetails(name));
      const overlap = analyzeOverlap(skillDetails);

      if (overlap.percentage > 70) {
        redundancies.push({
          capability: capability,
          skillCount: skills.length,
          skills: skills,
          overlapPercentage: overlap.percentage,
          recommendation: generateConsolidationRecommendation(skillDetails)
        });
      }
    }
  }

  // Find naming collisions
  const namePatterns = {};
  for (const [category, skillList] of Object.entries(inventory.categories)) {
    // Extract common patterns
    const patterns = skillList.map(extractNamePattern);
    
  }

   redundancies;
}

 () {
  
   descriptions = skills.( s.);
   commonWords = (descriptions);

  
   allWords =  (descriptions.( d.()));
   overlap = commonWords. / allWords. * ;

   { : overlap, : .(commonWords) };
}

Phase 4: Optimization Opportunities

Researcher Agent Task:

# Spawn researcher agent for optimization analysis
# Agent instructions:
# 1. Analyze usage patterns from memory
# 2. Identify under-utilized skills (low frequency)
# 3. Identify over-complex skills (high token cost, low success rate)
# 4. Suggest composability improvements
# 5. Recommend dependency optimizations
# 6. Store findings in memory

npx claude-flow@alpha memory store --key "gap-analysis/optimization" --value "{
  \"underutilized\": [...],
  \"overcomplicated\": [...],
  \"composability\": [...],
  \"dependencies\": [...]
}"

Optimization Detection:

function identifyOptimizations(inventory, usageMetrics) {
  const optimizations = [];

  // Under-utilized skills
  const underutilized = usageMetrics.filter(m =>
    m.frequency < 0.05 && // Less than 5% usage
    m.lastUsed > 90 // Days since last use
  ).map(m => ({
    skill: m.name,
    frequency: m.frequency,
    lastUsed: m.lastUsed + " days ago",
    recommendation: "Review for deprecation or promotion"
  }));

  optimizations.push({
    type: "under-utilized",
    count: underutilized.length,
    skills: underutilized
  });

  // Over-complex skills
  const overcomplex = usageMetrics.filter(m =>
    m.avgTokens > 5000 && // High token usage
    m.successRate < 0.7 // Low success rate
  ).map(m => ({
    skill: m.name,
    avgTokens: m.,
    : (m. * ).() + ,
    : 
  }));

  optimizations.({
    : ,
    : overcomplex.,
    : overcomplex
  });

  
   composable = (inventory);
  optimizations.({
    : ,
    : composable.,
    : composable
  });

   optimizations;
}

Phase 5: Recommendation Generation

Report Format:

## Skill Gap Analysis Report
**Date:** <timestamp>
**Total Skills Analyzed:** <count>
**Analysis Duration:** <time>

---

## Executive Summary

### Coverage
- Overall coverage: <percentage>%
- Critical gaps: <count>
- High-priority gaps: <count>

### Redundancy
- Duplicate functionality: <count> instances
- Consolidation opportunities: <count>
- Potential savings: <tokens/storage>

### Optimization
- Under-utilized skills: <count>
- Over-complex skills: <count>
- Composability improvements: <count>

---

## Coverage Gaps

### Critical Priority
1. **Domain:** [name]
   - Coverage: [percentage]%
   - Missing capabilities:
     - [capability 1]
 [capability 2]
 Recommended action: Create skill "[proposed-name]"
 Impact: [high/medium/low]


...

---




  [name]
 Handled by: [skill1], [skill2], [skill3]
 Overlap: [percentage]%
 Recommendation: Consolidate into "[new-skill-name]"
 Estimated savings: [tokens] tokens, [storage] MB

---




| Skill | Frequency | Last Used | Recommendation |
|-------|-----------|-----------|----------------|
| [name] | [%] | [days] ago | [action] |


| Skill | Avg Tokens | Success Rate | Recommendation |
|-------|------------|--------------|----------------|
| [name] | [count] | [%] | [action] |


  [description]
 Current approach: [details]
 Improved approach: [details]
 Benefits: [list]

---



| Scenario | Coverage | Missing | Can Execute? |
|----------|----------|---------|--------------|
| Full-stack web app | [%] | [list] | [yes/no] |
| ML deployment | [%] | [list] | [yes/no] |
| GitHub automation | [%] | [list] | [yes/no] |

---




 [ ] Create skill: [name] - [justification]
 [ ] Consolidate: [skills] → [new-skill]
 [ ] Deprecate: [skill] - [reason]


 [ ] Optimize: [skill] - [changes]
 [ ] Document: [skill] - [missing-docs]
 [ ] Test: [scenario] - [coverage-improvement]


 [ ] Refactor: [domain] - [architecture]
 [ ] Integrate: [external-tool] - [capability]
 [ ] Research: [emerging-technology] - [potential]

---



| Metric | Current | Target | Gap |
|--------|---------|--------|-----|
| Total skills | [count] | - | - |
| Domain coverage | [%] | 90% | [%] |
| Redundancy rate | [%] | <10% | [%] |
| Avg complexity | [level] | MEDIUM | - |
| Under-utilization | [%] | <5% | [%] |

Concrete Example: Real Analysis

Input: Skill Library (Fragment)

Inventory:

• Total skills: 47
• Categories: development (15), github (12), optimization (8), testing (5), meta-tools (3), misc (4)
• Capabilities mapped: 127
• Agents used: 18 distinct types

Analysis Output

Coverage Gaps Detected:

{
  "domain": "Data Engineering",
  "coverage": "23.1%",
  "missingCapabilities": [
    "data-transformation",
    "data-validation",
    "data-migration",
    "data-visualization",
    "etl-pipeline"
  ],
  "priority": "high",
  "recommendation": "Create 'data-engineering-workflow' skill"
}

Redundancy Detected:

{
  "capability": "code-review",
  "skillCount": 4,
  "skills": [
    "code-review-assistant",
    "github-code-review",
    "pr-review-automation",
    "code-quality-checker"
  ],
  "overlapPercentage": 78,
  "recommendation": "Consolidate into unified 'code-review-orchestrator' with specialized sub-skills"
}

Optimization Opportunities:

{
  "type": "under-utilized",
  "skills": [
    {
      "skill": "legacy-converter",
      "frequency": 0.02,
      "lastUsed": "127 days ago",
      "recommendation": "Archive or promote with use-case documentation"
    }
  ]
},
{
  "type": "over-complex",
  "skills": [
    {
      "skill": "full-stack-architect",
      "avgTokens": 8743,
      "successRate": "64.3%",
      "recommendation": "Break into: backend-architect, frontend-architect, database-architect"
    }
  ]
}

Recommendations:

1. Critical: Create data engineering skill (coverage: 23% → 85%)
2. High: Consolidate 4 code review skills (save ~15K tokens, reduce confusion)
3. Medium: Break full-stack-architect into 3 focused skills
4. Low: Archive legacy-converter or add promotion documentation

Expected Impact:

• Coverage improvement: 67% → 89%
• Redundancy reduction: 18% → 7%
• Avg token efficiency: +32%
• Maintenance overhead: -40%

Integration with Development Workflow

Quarterly Review Process

# 1. Run gap analysis
npx claude-flow@alpha hooks pre-task --description "Quarterly skill gap analysis"

# 2. Spawn researcher agent for analysis
# Agent performs comprehensive inventory and analysis

# 3. Review recommendations
npx claude-flow@alpha memory retrieve --key "gap-analysis/recommendations"

# 4. Create action plan
# Prioritize and schedule improvements

# 5. Track progress
npx claude-flow@alpha hooks post-task --task-id "gap-analysis-q1-2025"

Continuous Monitoring

# Track skill usage
npx claude-flow@alpha hooks post-task --skill-used "[name]"

# Aggregate metrics monthly
npx claude-flow@alpha memory aggregate --pattern "skills/usage/*" --period "monthly"

Success Metrics

• Domain coverage: >85%
• Redundancy rate: <10%
• Under-utilization: <5%
• Scenario execution: 100% of core scenarios
• Optimization adoption: >80% of recommendations implemented

Related Skills

• when-optimizing-prompts-use-prompt-optimization-analyzer - Optimize individual skills
• when-managing-token-budget-use-token-budget-advisor - Budget impact analysis
• skill-forge - Create new skills based on recommendations

Notes

• Run quarterly or after major changes
• Involve team in recommendation review
• Track recommendation adoption rate
• Update analysis criteria as needs evolve
• Share findings across teams

---

Converted and distributed by TomeVault — claim your Tome and manage your conversions.