Optimize your skills and tiles: review SKILL.md quality, generate eval scenarios, run evals, compare across models, diagnose gaps, and re-run until scores improve.
88
94%
Does it follow best practices?
Impact
88%
1.07xAverage score across 24 eval scenarios
Passed
No known issues
import ast
def validate_python(code: str) -> bool:
"""Validate Python code syntax"""
try:
ast.parse(code)
return True
except SyntaxError as e:
print(f"✗ Syntax error: {e}")
return False
# Example
code = '''
import requests
response = requests.get("https://api.example.com/users")
response.raise_for_status()
data = response.json()
'''
validate_python(code) # Returns True# Validate gh command flags
validate_gh_flag() {
local flag="$1"
gh pr create --help | grep -q "$flag" && echo "✓ Valid" || echo "✗ Invalid"
}
validate_gh_flag "--title" # ✓ Valid
validate_gh_flag "--reviewers" # ✗ Invalid (should be --reviewer)# Check if referenced files exist
SKILL_DIR="$(dirname path/to/SKILL.md)"
for link in $(grep -oE '\[[^]]*\]\(([^)]+)\)' SKILL.md | cut -d'(' -f2 | cut -d')' -f1); do
if [[ ! -f "$SKILL_DIR/$link" ]]; then
echo "✗ Broken reference: $link"
fi
done# Validate JavaScript syntax (requires Node.js)
validate_js() {
local file="$1"
node --check "$file" 2>&1 && echo "✓ Valid" || echo "✗ Syntax error"
}| Issue | Example | Fix |
|---|---|---|
| Invalid flag | gh pr create --reviewers | Use --reviewer (singular) |
| Missing file | [See GUIDE.md](GUIDE.md) | Create file or remove link |
| Python syntax | response = requests.get(url | Add closing ) |
| Broken command | gh repo create --public --confirm | --confirm was removed in gh 2.0; command is now non-interactive by default |
## [Action]
Current: [Dimension] X/3 ([Category]: Y%)
Impact: +Z% overall ([Dimension] X→Y)
Before: [current text]
After: [improved text]
Why: [Explain dimension weight and why this helps routing/clarity/etc]evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
skills
compare-skill-model-performance
optimize-skill-instructions
references
optimize-skill-performance
optimize-skill-performance-and-instructions