Add GitHub Actions CI for SKILL.md validation and index updates

.github/workflows/update-index.yml

@@ -0,0 +1,90 @@
+name: Update marketplace index
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'skills/**'
+
+jobs:
+  update-index:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Regenerate index.json
+        run: |
+          python3 << 'EOF'
+          import os, json, re
+          from datetime import datetime, timezone
+          from collections import Counter
+
+          skills_dir = "skills"
+          skills = []
+          subdomain_counts = Counter()
+          tag_counter = Counter()
+
+          for skill_name in sorted(os.listdir(skills_dir)):
+              skill_md = os.path.join(skills_dir, skill_name, "SKILL.md")
+              if not os.path.isfile(skill_md):
+                  continue
+              with open(skill_md, "r", encoding="utf-8") as f:
+                  content = f.read()
+              fm_match = re.match(r"^---\n(.*?)\n---", content, re.DOTALL)
+              if not fm_match:
+                  continue
+              fm = fm_match.group(1)
+              def get_field(field, text):
+                  m = re.search(rf"^{field}:\s*(.+)$", text, re.MULTILINE)
+                  return m.group(1).strip().strip('"') if m else ""
+              def get_tags(text):
+                  m = re.search(r"^tags:\s*\[(.+)\]", text, re.MULTILINE)
+                  return [t.strip() for t in m.group(1).split(",")] if m else []
+
+              tags = get_tags(fm)
+              subdomain = get_field("subdomain", fm)
+              subdomain_counts[subdomain] += 1
+              for t in tags:
+                  tag_counter[t] += 1
+
+              skills.append({
+                  "name": get_field("name", fm),
+                  "description": get_field("description", fm),
+                  "domain": "cybersecurity",
+                  "subdomain": subdomain,
+                  "tags": tags,
+                  "version": get_field("version", fm) or "1.0",
+                  "author": "mukul975",
+                  "license": "Apache-2.0",
+                  "path": f"skills/{skill_name}"
+              })
+
+          top_tags = sorted(tag_counter.items(), key=lambda x: -x[1])[:20]
+          index = {
+              "version": "1.0.0",
+              "generated_at": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
+              "repository": "https://github.com/mukul975/Anthropic-Cybersecurity-Skills",
+              "total_skills": len(skills),
+              "total_domains": 1,
+              "total_subdomains": len(subdomain_counts),
+              "domain_stats": {"cybersecurity": len(skills)},
+              "subdomain_stats": dict(subdomain_counts),
+              "top_tags": [{"tag": t, "count": c} for t, c in top_tags],
+              "skills": skills
+          }
+
+          with open("index.json", "w", encoding="utf-8") as f:
+              json.dump(index, f, indent=2)
+
+          print(f"Updated index.json: {len(skills)} skills, {len(subdomain_counts)} subdomains")
+          EOF
+
+      - name: Commit updated index
+        run: |
+          git config user.name "mukul975"
+          git config user.email "mukul975@users.noreply.github.com"
+          git add index.json
+          git diff --staged --quiet || git commit -m "chore: auto-update index.json"
+          git push

.github/workflows/validate-skills.yml

@@ -0,0 +1,128 @@
+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