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

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.agents[agent] = (inventory.agents[agent] || 0) + 1;
      });
    }

    // Track complexity
    inventory.complexity[metadata.complexity || 'UNKNOWN'] =
      (inventory.complexity[metadata.complexity || 'UNKNOWN'] || 0) + 1;

    // Track tags
    if (metadata.tags) {
      metadata.tags.forEach(tag => {
        inventory.tags[tag] = (inventory.tags[tag] || 0) + 1;
      });
    }
  }

  return inventory;
}

function extractCapabilities(description) {
  // Extract action verbs and key nouns
  const capabilities = [];

  const verbs = description.match(/\b(analyz|creat|generat|optimiz|manag|coordinat|orchestrat|deploy|monitor|test|review|document|integrat|automat|validat|secur|perform|debug|refactor|migrat|transform)\w+/gi) || [];

  capabilities.push(...verbs.map(v => v.toLowerCase()));

  return [...new Set(capabilities)]; // Deduplicate
}

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", "service-mesh"
    ]
  };

  // Check coverage for each domain
  for (const [domain, capabilities] of Object.entries(domains)) {
    const coverage = capabilities.map(cap => {
      const covered = inventory.capabilities[cap]?.length > 0;
      const skills = inventory.capabilities[cap] || [];
      return { capability: cap, covered, skills };
    });

    const missingCaps = coverage.filter(c => !c.covered);

    if (missingCaps.length > 0) {
      gaps.push({
        domain: domain,
        coverage: ((capabilities.length - missingCaps.length) / capabilities.length * 100).toFixed(1) + "%",
        missingCapabilities: missingCaps.map(c => c.capability),
        priority: calculatePriority(domain, missingCaps.length, capabilities.length)
      });
    }
  }

  return gaps;
}

function calculatePriority(domain, missingCount, totalCount) {
  const coverageRatio = 1 - (missingCount / totalCount);
  const domainImportance = {
    "Development": 1.0,
    "DevOps": 0.9,
    "Project Management": 0.7,
    "Data": 0.8,
    "AI/ML": 0.8,
    "Integration": 0.9
  };

  const score = coverageRatio * (domainImportance[domain] || 0.5);

  if (score < 0.3) return "critical";
  if (score < 0.6) return "high";
  if (score < 0.8) return "medium";
  return "low";
}

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 => ({
      capability: cap,
      covered: inventory.capabilities[cap]?.length > 0,
      skills: inventory.capabilities[cap] || []
    }));

    const coveragePercent = (coverage.filter(c => c.covered).length /
                            coverage.length * 100).toFixed(1);

    return {
      scenario: scenario.name,
      coverage: coveragePercent + "%",
      missing: coverage.filter(c => !c.covered).map(c => c.capability),
      canExecute: coverage.every(c => c.covered)
    };
  });

  return 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 overl