create-apppaaaul 2.0.46 → 2.0.47

package/dist/templates/nextjs-ts-clean/project/.agents/skills/prompt-engineering-patterns/scripts/optimize-prompt.py

@@ -0,0 +1,279 @@
+#!/usr/bin/env python3
+"""
+Prompt Optimization Script
+
+Automatically test and optimize prompts using A/B testing and metrics tracking.
+"""
+
+import json
+import time
+from typing import List, Dict, Any
+from dataclasses import dataclass
+from concurrent.futures import ThreadPoolExecutor
+import numpy as np
+
+
+@dataclass
+class TestCase:
+    input: Dict[str, Any]
+    expected_output: str
+    metadata: Dict[str, Any] = None
+
+
+class PromptOptimizer:
+    def __init__(self, llm_client, test_suite: List[TestCase]):
+        self.client = llm_client
+        self.test_suite = test_suite
+        self.results_history = []
+        self.executor = ThreadPoolExecutor()
+
+    def shutdown(self):
+        """Shutdown the thread pool executor."""
+        self.executor.shutdown(wait=True)
+
+    def evaluate_prompt(self, prompt_template: str, test_cases: List[TestCase] = None) -> Dict[str, float]:
+        """Evaluate a prompt template against test cases in parallel."""
+        if test_cases is None:
+            test_cases = self.test_suite
+
+        metrics = {
+            'accuracy': [],
+            'latency': [],
+            'token_count': [],
+            'success_rate': []
+        }
+
+        def process_test_case(test_case):
+            start_time = time.time()
+
+            # Render prompt with test case inputs
+            prompt = prompt_template.format(**test_case.input)
+
+            # Get LLM response
+            response = self.client.complete(prompt)
+
+            # Measure latency
+            latency = time.time() - start_time
+
+            # Calculate individual metrics
+            token_count = len(prompt.split()) + len(response.split())
+            success = 1 if response else 0
+            accuracy = self.calculate_accuracy(response, test_case.expected_output)
+
+            return {
+                'latency': latency,
+                'token_count': token_count,
+                'success_rate': success,
+                'accuracy': accuracy
+            }
+
+        # Run test cases in parallel
+        results = list(self.executor.map(process_test_case, test_cases))
+
+        # Aggregate metrics
+        for result in results:
+            metrics['latency'].append(result['latency'])
+            metrics['token_count'].append(result['token_count'])
+            metrics['success_rate'].append(result['success_rate'])
+            metrics['accuracy'].append(result['accuracy'])
+
+        return {
+            'avg_accuracy': np.mean(metrics['accuracy']),
+            'avg_latency': np.mean(metrics['latency']),
+            'p95_latency': np.percentile(metrics['latency'], 95),
+            'avg_tokens': np.mean(metrics['token_count']),
+            'success_rate': np.mean(metrics['success_rate'])
+        }
+
+    def calculate_accuracy(self, response: str, expected: str) -> float:
+        """Calculate accuracy score between response and expected output."""
+        # Simple exact match
+        if response.strip().lower() == expected.strip().lower():
+            return 1.0
+
+        # Partial match using word overlap
+        response_words = set(response.lower().split())
+        expected_words = set(expected.lower().split())
+
+        if not expected_words:
+            return 0.0
+
+        overlap = len(response_words & expected_words)
+        return overlap / len(expected_words)
+
+    def optimize(self, base_prompt: str, max_iterations: int = 5) -> Dict[str, Any]:
+        """Iteratively optimize a prompt."""
+        current_prompt = base_prompt
+        best_prompt = base_prompt
+        best_score = 0
+        current_metrics = None
+
+        for iteration in range(max_iterations):
+            print(f"\nIteration {iteration + 1}/{max_iterations}")
+
+            # Evaluate current prompt
+            # Bolt Optimization: Avoid re-evaluating if we already have metrics from previous iteration
+            if current_metrics:
+                metrics = current_metrics
+            else:
+                metrics = self.evaluate_prompt(current_prompt)
+
+            print(f"Accuracy: {metrics['avg_accuracy']:.2f}, Latency: {metrics['avg_latency']:.2f}s")
+
+            # Track results
+            self.results_history.append({
+                'iteration': iteration,
+                'prompt': current_prompt,
+                'metrics': metrics
+            })
+
+            # Update best if improved
+            if metrics['avg_accuracy'] > best_score:
+                best_score = metrics['avg_accuracy']
+                best_prompt = current_prompt
+
+            # Stop if good enough
+            if metrics['avg_accuracy'] > 0.95:
+                print("Achieved target accuracy!")
+                break
+
+            # Generate variations for next iteration
+            variations = self.generate_variations(current_prompt, metrics)
+
+            # Test variations and pick best
+            best_variation = current_prompt
+            best_variation_score = metrics['avg_accuracy']
+            best_variation_metrics = metrics
+
+            for variation in variations:
+                var_metrics = self.evaluate_prompt(variation)
+                if var_metrics['avg_accuracy'] > best_variation_score:
+                    best_variation_score = var_metrics['avg_accuracy']
+                    best_variation = variation
+                    best_variation_metrics = var_metrics
+
+            current_prompt = best_variation
+            current_metrics = best_variation_metrics
+
+        return {
+            'best_prompt': best_prompt,
+            'best_score': best_score,
+            'history': self.results_history
+        }
+
+    def generate_variations(self, prompt: str, current_metrics: Dict) -> List[str]:
+        """Generate prompt variations to test."""
+        variations = []
+
+        # Variation 1: Add explicit format instruction
+        variations.append(prompt + "\n\nProvide your answer in a clear, concise format.")
+
+        # Variation 2: Add step-by-step instruction
+        variations.append("Let's solve this step by step.\n\n" + prompt)
+
+        # Variation 3: Add verification step
+        variations.append(prompt + "\n\nVerify your answer before responding.")
+
+        # Variation 4: Make more concise
+        concise = self.make_concise(prompt)
+        if concise != prompt:
+            variations.append(concise)
+
+        # Variation 5: Add examples (if none present)
+        if "example" not in prompt.lower():
+            variations.append(self.add_examples(prompt))
+
+        return variations[:3]  # Return top 3 variations
+
+    def make_concise(self, prompt: str) -> str:
+        """Remove redundant words to make prompt more concise."""
+        replacements = [
+            ("in order to", "to"),
+            ("due to the fact that", "because"),
+            ("at this point in time", "now"),
+            ("in the event that", "if"),
+        ]
+
+        result = prompt
+        for old, new in replacements:
+            result = result.replace(old, new)
+
+        return result
+
+    def add_examples(self, prompt: str) -> str:
+        """Add example section to prompt."""
+        return f"""{prompt}
+
+Example:
+Input: Sample input
+Output: Sample output
+"""
+
+    def compare_prompts(self, prompt_a: str, prompt_b: str) -> Dict[str, Any]:
+        """A/B test two prompts."""
+        print("Testing Prompt A...")
+        metrics_a = self.evaluate_prompt(prompt_a)
+
+        print("Testing Prompt B...")
+        metrics_b = self.evaluate_prompt(prompt_b)
+
+        return {
+            'prompt_a_metrics': metrics_a,
+            'prompt_b_metrics': metrics_b,
+            'winner': 'A' if metrics_a['avg_accuracy'] > metrics_b['avg_accuracy'] else 'B',
+            'improvement': abs(metrics_a['avg_accuracy'] - metrics_b['avg_accuracy'])
+        }
+
+    def export_results(self, filename: str):
+        """Export optimization results to JSON."""
+        with open(filename, 'w') as f:
+            json.dump(self.results_history, f, indent=2)
+
+
+def main():
+    # Example usage
+    test_suite = [
+        TestCase(
+            input={'text': 'This movie was amazing!'},
+            expected_output='Positive'
+        ),
+        TestCase(
+            input={'text': 'Worst purchase ever.'},
+            expected_output='Negative'
+        ),
+        TestCase(
+            input={'text': 'It was okay, nothing special.'},
+            expected_output='Neutral'
+        )
+    ]
+
+    # Mock LLM client for demonstration
+    class MockLLMClient:
+        def complete(self, prompt):
+            # Simulate LLM response
+            if 'amazing' in prompt:
+                return 'Positive'
+            elif 'worst' in prompt.lower():
+                return 'Negative'
+            else:
+                return 'Neutral'
+
+    optimizer = PromptOptimizer(MockLLMClient(), test_suite)
+
+    try:
+        base_prompt = "Classify the sentiment of: {text}\nSentiment:"
+
+        results = optimizer.optimize(base_prompt)
+
+        print("\n" + "="*50)
+        print("Optimization Complete!")
+        print(f"Best Accuracy: {results['best_score']:.2f}")
+        print(f"Best Prompt:\n{results['best_prompt']}")
+
+        optimizer.export_results('optimization_results.json')
+    finally:
+        optimizer.shutdown()
+
+
+if __name__ == '__main__':
+    main()

package/dist/templates/nextjs-ts-clean/project/.agents/skills/seo-audit/SKILL.md

@@ -0,0 +1,410 @@
+---
+name: seo-audit
+description: When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," or "SEO health check." For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup.
+metadata:
+  version: 1.0.0
+---
+
+# SEO Audit
+
+You are an expert in search engine optimization. Your goal is to identify SEO issues and provide actionable recommendations to improve organic search performance.
+
+## Initial Assessment
+
+**Check for product marketing context first:**
+If `.claude/product-marketing-context.md` exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
+
+Before auditing, understand:
+
+1. **Site Context**
+   - What type of site? (SaaS, e-commerce, blog, etc.)
+   - What's the primary business goal for SEO?
+   - What keywords/topics are priorities?
+
+2. **Current State**
+   - Any known issues or concerns?
+   - Current organic traffic level?
+   - Recent changes or migrations?
+
+3. **Scope**
+   - Full site audit or specific pages?
+   - Technical + on-page, or one focus area?
+   - Access to Search Console / analytics?
+
+---
+
+## Audit Framework
+
+### ⚠️ Important: Schema Markup Detection Limitation
+
+**`web_fetch` and `curl` cannot reliably detect structured data / schema markup.**
+
+Many CMS plugins (AIOSEO, Yoast, RankMath) inject JSON-LD via client-side JavaScript — it won't appear in static HTML or `web_fetch` output (which strips `<script>` tags during conversion).
+
+**To accurately check for schema markup, use one of these methods:**
+1. **Browser tool** — render the page and run: `document.querySelectorAll('script[type="application/ld+json"]')`
+2. **Google Rich Results Test** — https://search.google.com/test/rich-results
+3. **Screaming Frog export** — if the client provides one, use it (SF renders JavaScript)
+
+**Never report "no schema found" based solely on `web_fetch` or `curl`.** This has led to false audit findings in production.
+
+### Priority Order
+1. **Crawlability & Indexation** (can Google find and index it?)
+2. **Technical Foundations** (is the site fast and functional?)
+3. **On-Page Optimization** (is content optimized?)
+4. **Content Quality** (does it deserve to rank?)
+5. **Authority & Links** (does it have credibility?)
+
+---
+
+## Technical SEO Audit
+
+### Crawlability
+
+**Robots.txt**
+- Check for unintentional blocks
+- Verify important pages allowed
+- Check sitemap reference
+
+**XML Sitemap**
+- Exists and accessible
+- Submitted to Search Console
+- Contains only canonical, indexable URLs
+- Updated regularly
+- Proper formatting
+
+**Site Architecture**
+- Important pages within 3 clicks of homepage
+- Logical hierarchy
+- Internal linking structure
+- No orphan pages
+
+**Crawl Budget Issues** (for large sites)
+- Parameterized URLs under control
+- Faceted navigation handled properly
+- Infinite scroll with pagination fallback
+- Session IDs not in URLs
+
+### Indexation
+
+**Index Status**
+- site:domain.com check
+- Search Console coverage report
+- Compare indexed vs. expected
+
+**Indexation Issues**
+- Noindex tags on important pages
+- Canonicals pointing wrong direction
+- Redirect chains/loops
+- Soft 404s
+- Duplicate content without canonicals
+
+**Canonicalization**
+- All pages have canonical tags
+- Self-referencing canonicals on unique pages
+- HTTP → HTTPS canonicals
+- www vs. non-www consistency
+- Trailing slash consistency
+
+### Site Speed & Core Web Vitals
+
+**Core Web Vitals**
+- LCP (Largest Contentful Paint): < 2.5s
+- INP (Interaction to Next Paint): < 200ms
+- CLS (Cumulative Layout Shift): < 0.1
+
+**Speed Factors**
+- Server response time (TTFB)
+- Image optimization
+- JavaScript execution
+- CSS delivery
+- Caching headers
+- CDN usage
+- Font loading
+
+**Tools**
+- PageSpeed Insights
+- WebPageTest
+- Chrome DevTools
+- Search Console Core Web Vitals report
+
+### Mobile-Friendliness
+
+- Responsive design (not separate m. site)
+- Tap target sizes
+- Viewport configured
+- No horizontal scroll
+- Same content as desktop
+- Mobile-first indexing readiness
+
+### Security & HTTPS
+
+- HTTPS across entire site
+- Valid SSL certificate
+- No mixed content
+- HTTP → HTTPS redirects
+- HSTS header (bonus)
+
+### URL Structure
+
+- Readable, descriptive URLs
+- Keywords in URLs where natural
+- Consistent structure
+- No unnecessary parameters
+- Lowercase and hyphen-separated
+
+---
+
+## On-Page SEO Audit
+
+### Title Tags
+
+**Check for:**
+- Unique titles for each page
+- Primary keyword near beginning
+- 50-60 characters (visible in SERP)
+- Compelling and click-worthy
+- Brand name placement (end, usually)
+
+**Common issues:**
+- Duplicate titles
+- Too long (truncated)
+- Too short (wasted opportunity)
+- Keyword stuffing
+- Missing entirely
+
+### Meta Descriptions
+
+**Check for:**
+- Unique descriptions per page
+- 150-160 characters
+- Includes primary keyword
+- Clear value proposition
+- Call to action
+
+**Common issues:**
+- Duplicate descriptions
+- Auto-generated garbage
+- Too long/short
+- No compelling reason to click
+
+### Heading Structure
+
+**Check for:**
+- One H1 per page
+- H1 contains primary keyword
+- Logical hierarchy (H1 → H2 → H3)
+- Headings describe content
+- Not just for styling
+
+**Common issues:**
+- Multiple H1s
+- Skip levels (H1 → H3)
+- Headings used for styling only
+- No H1 on page
+
+### Content Optimization
+
+**Primary Page Content**
+- Keyword in first 100 words
+- Related keywords naturally used
+- Sufficient depth/length for topic
+- Answers search intent
+- Better than competitors
+
+**Thin Content Issues**
+- Pages with little unique content
+- Tag/category pages with no value
+- Doorway pages
+- Duplicate or near-duplicate content
+
+### Image Optimization
+
+**Check for:**
+- Descriptive file names
+- Alt text on all images
+- Alt text describes image
+- Compressed file sizes
+- Modern formats (WebP)
+- Lazy loading implemented
+- Responsive images
+
+### Internal Linking
+
+**Check for:**
+- Important pages well-linked
+- Descriptive anchor text
+- Logical link relationships
+- No broken internal links
+- Reasonable link count per page
+
+**Common issues:**
+- Orphan pages (no internal links)
+- Over-optimized anchor text
+- Important pages buried
+- Excessive footer/sidebar links
+
+### Keyword Targeting
+
+**Per Page**
+- Clear primary keyword target
+- Title, H1, URL aligned
+- Content satisfies search intent
+- Not competing with other pages (cannibalization)
+
+**Site-Wide**
+- Keyword mapping document
+- No major gaps in coverage
+- No keyword cannibalization
+- Logical topical clusters
+
+---
+
+## Content Quality Assessment
+
+### E-E-A-T Signals
+
+**Experience**
+- First-hand experience demonstrated
+- Original insights/data
+- Real examples and case studies
+
+**Expertise**
+- Author credentials visible
+- Accurate, detailed information
+- Properly sourced claims
+
+**Authoritativeness**
+- Recognized in the space
+- Cited by others
+- Industry credentials
+
+**Trustworthiness**
+- Accurate information
+- Transparent about business
+- Contact information available
+- Privacy policy, terms
+- Secure site (HTTPS)
+
+### Content Depth
+
+- Comprehensive coverage of topic
+- Answers follow-up questions
+- Better than top-ranking competitors
+- Updated and current
+
+### User Engagement Signals
+
+- Time on page
+- Bounce rate in context
+- Pages per session
+- Return visits
+
+---
+
+## Common Issues by Site Type
+
+### SaaS/Product Sites
+- Product pages lack content depth
+- Blog not integrated with product pages
+- Missing comparison/alternative pages
+- Feature pages thin on content
+- No glossary/educational content
+
+### E-commerce
+- Thin category pages
+- Duplicate product descriptions
+- Missing product schema
+- Faceted navigation creating duplicates
+- Out-of-stock pages mishandled
+
+### Content/Blog Sites
+- Outdated content not refreshed
+- Keyword cannibalization
+- No topical clustering
+- Poor internal linking
+- Missing author pages
+
+### Local Business
+- Inconsistent NAP
+- Missing local schema
+- No Google Business Profile optimization
+- Missing location pages
+- No local content
+
+---
+
+## Output Format
+
+### Audit Report Structure
+
+**Executive Summary**
+- Overall health assessment
+- Top 3-5 priority issues
+- Quick wins identified
+
+**Technical SEO Findings**
+For each issue:
+- **Issue**: What's wrong
+- **Impact**: SEO impact (High/Medium/Low)
+- **Evidence**: How you found it
+- **Fix**: Specific recommendation
+- **Priority**: 1-5 or High/Medium/Low
+
+**On-Page SEO Findings**
+Same format as above
+
+**Content Findings**
+Same format as above
+
+**Prioritized Action Plan**
+1. Critical fixes (blocking indexation/ranking)
+2. High-impact improvements
+3. Quick wins (easy, immediate benefit)
+4. Long-term recommendations
+
+---
+
+## References
+
+- [AI Writing Detection](references/ai-writing-detection.md): Common AI writing patterns to avoid (em dashes, overused phrases, filler words)
+- [AEO & GEO Patterns](references/aeo-geo-patterns.md): Content patterns optimized for answer engines and AI citation
+
+---
+
+## Tools Referenced
+
+**Free Tools**
+- Google Search Console (essential)
+- Google PageSpeed Insights
+- Bing Webmaster Tools
+- Rich Results Test (**use this for schema validation — it renders JavaScript**)
+- Mobile-Friendly Test
+- Schema Validator
+
+> **Note on schema detection:** `web_fetch` strips `<script>` tags (including JSON-LD) and cannot detect JS-injected schema. Always use the browser tool, Rich Results Test, or Screaming Frog for schema checks. See the warning at the top of the Audit Framework section.
+
+**Paid Tools** (if available)
+- Screaming Frog
+- Ahrefs / Semrush
+- Sitebulb
+- ContentKing
+
+---
+
+## Task-Specific Questions
+
+1. What pages/keywords matter most?
+2. Do you have Search Console access?
+3. Any recent changes or migrations?
+4. Who are your top organic competitors?
+5. What's your current organic traffic baseline?
+
+---
+
+## Related Skills
+
+- **programmatic-seo**: For building SEO pages at scale
+- **schema-markup**: For implementing structured data
+- **page-cro**: For optimizing pages for conversion (not just ranking)
+- **analytics-tracking**: For measuring SEO performance