Anthropic-Cybersecurity-Skills/.github/workflows/validate-skills.yml

name: Validate SKILL.md files

on:
  push:
    paths:
      - 'skills/**'
  pull_request:
    paths:
      - 'skills/**'

jobs:
  validate:
    runs-on: ubuntu-latest
    name: Validate SKILL.md frontmatter
    steps:
      - uses: actions/checkout@v4

      - name: Validate SKILL.md frontmatter with Python
        run: |
          python3 << 'EOF'
          import os
          import re
          import sys

          REQUIRED_FIELDS = ['name', 'description', 'domain', 'subdomain', 'tags', 'version', 'author', 'license']
          errors = []
          checked = 0

          for root, dirs, files in os.walk('skills'):
              for file in files:
                  if file == 'SKILL.md':
                      path = os.path.join(root, file)
                      checked += 1
                      with open(path, 'r', encoding='utf-8') as f:
                          content = f.read()

                      # Check frontmatter exists
                      fm_match = re.match(r'^---\n(.*?)\n---', content, re.DOTALL)
                      if not fm_match:
                          errors.append(f"{path}: Missing YAML frontmatter")
                          continue

                      fm = fm_match.group(1)

                      # Check required fields
                      for field in REQUIRED_FIELDS:
                          if not re.search(rf'^{field}:', fm, re.MULTILINE):
                              errors.append(f"{path}: Missing required field '{field}'")

                      # Check name format (kebab-case)
                      name_match = re.search(r'^name:\s*(.+)$', fm, re.MULTILINE)
                      if name_match:
                          name = name_match.group(1).strip().strip('"')
                          if not re.match(r'^[a-z0-9-]+$', name):
                              errors.append(f"{path}: Name '{name}' must be kebab-case")
                          if len(name) > 64:
                              errors.append(f"{path}: Name '{name}' exceeds 64 characters")

          print(f"Checked {checked} SKILL.md files")

          if errors:
              print(f"\n{len(errors)} validation error(s):")
              for e in errors:
                  print(f"  ❌ {e}")
              sys.exit(1)
          else:
              print(f"✅ All {checked} skills valid")
          EOF

      - name: Check for duplicate skill names
        run: |
          python3 << 'EOF'
          import os
          import re
          from collections import Counter

          names = []
          for root, dirs, files in os.walk('skills'):
              for file in files:
                  if file == 'SKILL.md':
                      path = os.path.join(root, file)
                      with open(path, 'r', encoding='utf-8') as f:
                          content = f.read()
                      fm_match = re.match(r'^---\n(.*?)\n---', content, re.DOTALL)
                      if fm_match:
                          name_match = re.search(r'^name:\s*(.+)$', fm_match.group(1), re.MULTILINE)
                          if name_match:
                              names.append(name_match.group(1).strip().strip('"'))

          duplicates = [name for name, count in Counter(names).items() if count > 1]
          if duplicates:
              print(f"❌ Duplicate skill names found: {duplicates}")
              exit(1)
          print(f"✅ No duplicate names in {len(names)} skills")
          EOF

      - name: Report skill counts
        if: always()
        run: |
          echo "## Skill Database Stats" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          python3 << 'EOF'
          import os
          import re
          from collections import Counter

          subdomain_counts = Counter()
          total = 0
          for root, dirs, files in os.walk('skills'):
              for file in files:
                  if file == 'SKILL.md':
                      total += 1
                      path = os.path.join(root, file)
                      with open(path, 'r', encoding='utf-8') as f:
                          content = f.read()
                      fm_match = re.match(r'^---\n(.*?)\n---', content, re.DOTALL)
                      if fm_match:
                          sd_match = re.search(r'^subdomain:\s*(.+)$', fm_match.group(1), re.MULTILINE)
                          if sd_match:
                              subdomain_counts[sd_match.group(1).strip()] += 1

          print(f"**Total Skills: {total}**")
          print("")
          print("| Subdomain | Count |")
          print("|-----------|-------|")
          for sd, count in sorted(subdomain_counts.items(), key=lambda x: -x[1]):
              print(f"| {sd} | {count} |")
          EOF