feat(skill-creator): enhance HTML documentation and improve benchmark packaging validation

EvoScientist/skills/skill-creator/assets/eval_review.html

@@ -4,6 +4,7 @@
   <meta charset="UTF-8">
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   <title>Eval Set Review - __SKILL_NAME_PLACEHOLDER__</title>
+  <!-- Fonts loaded from CDN; falls back to system fonts offline -->
   <link rel="preconnect" href="https://fonts.googleapis.com">
   <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
   <link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">

EvoScientist/skills/skill-creator/eval-viewer/viewer.html

@@ -4,6 +4,7 @@
   <meta charset="UTF-8">
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   <title>Eval Review</title>
+  <!-- Fonts and SheetJS loaded from CDN; page degrades gracefully offline -->
   <link rel="preconnect" href="https://fonts.googleapis.com">
   <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
   <link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
@@ -826,8 +827,17 @@
       }
     }
 
-    // ---- XLSX rendering via SheetJS ----
+    // ---- XLSX rendering via SheetJS (degrades to download link if CDN unavailable) ----
     function renderXlsx(container, b64Data) {
+      if (typeof XLSX === "undefined") {
+        const a = document.createElement("a");
+        a.className = "download-link";
+        a.href = "data:application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;base64," + b64Data;
+        a.download = "spreadsheet.xlsx";
+        a.textContent = "Download .xlsx (SheetJS unavailable offline)";
+        container.appendChild(a);
+        return;
+      }
       try {
         const raw = Uint8Array.from(atob(b64Data), c => c.charCodeAt(0));
         const wb = XLSX.read(raw, { type: "array" });

EvoScientist/skills/skill-creator/scripts/aggregate_benchmark.py

@@ -268,10 +268,9 @@ def generate_benchmark(benchmark_dir: Path, skill_name: str = "", skill_path: st
             "analyzer_model": "<model-name>",
             "timestamp": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
             "evals_run": eval_ids,
-            "runs_per_configuration": min(
-                (len(runs) for runs in results.values() if runs),
-                default=0,
-            )
+            "runs_per_configuration": {
+                config: len(runs) for config, runs in results.items() if runs
+            }
         },
         "runs": runs,
         "run_summary": run_summary,
@@ -281,6 +280,19 @@ def generate_benchmark(benchmark_dir: Path, skill_name: str = "", skill_path: st
     return benchmark
 
 
+def _format_runs_per_config(rpc) -> str:
+    """Format runs_per_configuration for display (handles both int and dict)."""
+    if isinstance(rpc, int):
+        return f"{rpc} runs each"
+    if isinstance(rpc, dict):
+        counts = sorted(set(rpc.values()))
+        if len(counts) == 1:
+            return f"{counts[0]} runs each"
+        parts = [f"{config}: {n}" for config, n in rpc.items()]
+        return ", ".join(parts)
+    return str(rpc)
+
+
 def generate_markdown(benchmark: dict) -> str:
     """Generate human-readable benchmark.md from benchmark data."""
     metadata = benchmark["metadata"]
@@ -298,7 +310,7 @@ def generate_markdown(benchmark: dict) -> str:
         "",
         f"**Model**: {metadata['executor_model']}",
         f"**Date**: {metadata['timestamp']}",
-        f"**Evals**: {', '.join(map(str, metadata['evals_run']))} ({metadata['runs_per_configuration']} runs each per configuration)",
+        f"**Evals**: {', '.join(map(str, metadata['evals_run']))} ({_format_runs_per_config(metadata['runs_per_configuration'])} per configuration)",
         "",
         "## Summary",
         "",

EvoScientist/skills/skill-creator/scripts/package_skill.py

@@ -71,9 +71,9 @@ def package_skill(skill_path, output_dir=None):
         print(f"❌ Error: SKILL.md not found in {skill_path}")
         return None
 
-    # Run validation before packaging
+    # Run validation before packaging (strict mode catches TODO placeholders)
     print("🔍 Validating skill...")
-    valid, message = validate_skill(skill_path)
+    valid, message = validate_skill(skill_path, strict=True)
     if not valid:
         print(f"❌ Validation failed: {message}")
         print("   Please fix the validation errors before packaging.")
@@ -113,22 +113,21 @@ def package_skill(skill_path, output_dir=None):
 
 
 def main():
-    if len(sys.argv) < 2:
-        print("Usage: python utils/package_skill.py <path/to/skill-folder> [output-directory]")
-        print("\nExample:")
-        print("  python utils/package_skill.py skills/public/my-skill")
-        print("  python utils/package_skill.py skills/public/my-skill ./dist")
-        sys.exit(1)
+    import argparse
+    parser = argparse.ArgumentParser(
+        description="Package a skill folder into a distributable .skill file"
+    )
+    parser.add_argument("skill_path", help="Path to the skill folder")
+    parser.add_argument("output_dir", nargs="?", default=None,
+                        help="Output directory for the .skill file (default: current directory)")
+    args = parser.parse_args()
 
-    skill_path = sys.argv[1]
-    output_dir = sys.argv[2] if len(sys.argv) > 2 else None
-
-    print(f"📦 Packaging skill: {skill_path}")
-    if output_dir:
-        print(f"   Output directory: {output_dir}")
+    print(f"📦 Packaging skill: {args.skill_path}")
+    if args.output_dir:
+        print(f"   Output directory: {args.output_dir}")
     print()
 
-    result = package_skill(skill_path, output_dir)
+    result = package_skill(args.skill_path, args.output_dir)
 
     if result:
         sys.exit(0)