feat: Implement skill description improvement and evaluation scripts

- Added `improve_description.py` to enhance skill descriptions based on evaluation results using Claude.
- Introduced `run_eval.py` to assess whether skill descriptions trigger correctly for a set of queries.
- Created `run_loop.py` to combine evaluation and improvement in a loop, tracking history and optimizing descriptions iteratively.
- Developed `utils.py` for shared utility functions, including parsing SKILL.md files.
- Enhanced the overall workflow for skill description optimization, supporting train/test splits to prevent overfitting.

skills/skill-creator/scripts/package_skill.py

@@ -10,10 +10,33 @@ Example:
     python utils/package_skill.py skills/public/my-skill ./dist
 """
 
+import fnmatch
 import sys
 import zipfile
 from pathlib import Path
-from quick_validate import validate_skill
+from scripts.quick_validate import validate_skill
+
+# Patterns to exclude when packaging skills.
+EXCLUDE_DIRS = {"__pycache__", "node_modules"}
+EXCLUDE_GLOBS = {"*.pyc"}
+EXCLUDE_FILES = {".DS_Store"}
+# Directories excluded only at the skill root (not when nested deeper).
+ROOT_EXCLUDE_DIRS = {"evals"}
+
+
+def should_exclude(rel_path: Path) -> bool:
+    """Check if a path should be excluded from packaging."""
+    parts = rel_path.parts
+    if any(part in EXCLUDE_DIRS for part in parts):
+        return True
+    # rel_path is relative to skill_path.parent, so parts[0] is the skill
+    # folder name and parts[1] (if present) is the first subdir.
+    if len(parts) > 1 and parts[1] in ROOT_EXCLUDE_DIRS:
+        return True
+    name = rel_path.name
+    if name in EXCLUDE_FILES:
+        return True
+    return any(fnmatch.fnmatch(name, pat) for pat in EXCLUDE_GLOBS)
 
 
 def package_skill(skill_path, output_dir=None):
@@ -66,13 +89,16 @@ def package_skill(skill_path, output_dir=None):
     # Create the .skill file (zip format)
     try:
         with zipfile.ZipFile(skill_filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
-            # Walk through the skill directory
+            # Walk through the skill directory, excluding build artifacts
             for file_path in skill_path.rglob('*'):
-                if file_path.is_file():
-                    # Calculate the relative path within the zip
-                    arcname = file_path.relative_to(skill_path.parent)
-                    zipf.write(file_path, arcname)
-                    print(f"  Added: {arcname}")
+                if not file_path.is_file():
+                    continue
+                arcname = file_path.relative_to(skill_path.parent)
+                if should_exclude(arcname):
+                    print(f"  Skipped: {arcname}")
+                    continue
+                zipf.write(file_path, arcname)
+                print(f"  Added: {arcname}")
 
         print(f"\n✅ Successfully packaged skill to: {skill_filename}")
         return skill_filename