Merge pull request #14 from thibaultyou/feature/10-enhance-prompt-categorization

Enhance AI Prompt Analyzer and Update Automation Scripts

Author: thibaultyou

.github/prompts/ai_prompt_analyzer_and_output_generator/prompt.md

@@ -1,12 +1,49 @@
 You are an AI assistant tasked with analyzing an AI prompt and producing specific outputs related to it. The prompt will be provided to you, and you should generate the following:
 
 1. A directory name for storing the prompt
-2. A category in snake_case format
-3. A list of tags
-4. A one-line concise description
-5. A quick description
-6. A markdown link for referencing the prompt
-7. A list of variables that require user input
+2. A primary category from the predefined list
+3. Optional subcategories (up to 2)
+4. A list of tags
+5. A one-line concise description
+6. A quick description
+7. A markdown link for referencing the prompt
+8. A list of variables that require user input
+
+Here's the list of predefined top-level categories:
+
+TOP_LEVEL_CATEGORIES = [
+    "api_development",
+    "artificial_intelligence",
+    "backend_development",
+    "cloud_computing",
+    "code_analysis_and_review",
+    "code_generation_and_optimization",
+    "containerization_and_orchestration",
+    "data_management_and_analytics",
+    "database_design",
+    "debugging_and_error_handling",
+    "design_patterns",
+    "devops",
+    "documentation",
+    "frontend_development",
+    "full_stack_development",
+    "ide_and_development_tools",
+    "machine_learning",
+    "mobile_development",
+    "network_programming",
+    "performance_tuning",
+    "project_management",
+    "prompt_engineering",
+    "refactoring",
+    "scalability_and_system_design",
+    "security",
+    "software_architecture",
+    "testing_and_quality_assurance",
+    "user_experience_design",
+    "version_control",
+    "web_development",
+    "workflow_automation"
+]
 
 Here's the AI prompt you need to analyze:
 
@@ -24,10 +61,13 @@ Generate a directory name for the prompt using the following convention:
 - Remove any special characters
 - The directory name should be concise but descriptive, ideally not exceeding 50 characters
 
-2. Category:
-Determine a simple and clear category for the prompt, formatted in snake_case.
+2. Primary Category:
+Select the most appropriate primary category from the predefined list of top-level categories, formatted in snake_case.
 
-3. Tags:
+3. Subcategories:
+Determine up to two subcategories that further specify the prompt's focus. These should be more specific than the primary category and can be custom-created, formatted in snake_case.
+
+4. Tags:
 Create a list of 3-5 relevant tags for the prompt. These tags should:
 
 - Be single words or short phrases
@@ -36,36 +76,39 @@ Create a list of 3-5 relevant tags for the prompt. These tags should:
 - Accurately represent the main themes or applications of the prompt
 - Be useful for categorizing and searching for the prompt
 
-4. One-line description:
+5. One-line description:
 Write a concise, one-line description of the prompt that:
 
 - Captures the main purpose or function of the prompt
 - Is no longer than 100 characters
 - Starts with a verb in the present tense (e.g., "Creates," "Generates," "Analyzes")
 
-5. Quick description:
+6. Quick description:
 Provide a brief description of the prompt that:
 
 - Expands on the one-line description
 - Explains the key features or capabilities of the prompt
 - Is 2-3 sentences long
 - Gives the reader a clear understanding of what the prompt does
 
-6. Markdown link:
+7. Markdown link:
 Create a markdown link that can be used to reference the prompt:
 
 - Use the one-line description as the link text
 - Use the directory name as the link URL
 - Format it as: [One-line description](directory_name)
 
-7. User input variables:
+8. User input variables:
 List all variables in the prompt that require user input or replacement. These should be in the format {{VARIABLE_NAME}} and listed one per line.
 
 Present your final output in the following format:
 
 <output>
 title: [Prompt's main topic or purpose]
-category: [Your determined category in snake_case]
+primary_category: [Your selected primary category]
+subcategories:
+  - [Subcategory 1]
+  - [Subcategory 2]
 directory: [Your generated directory name]
 tags:
   - [Tag 1]

.github/scripts/generate_metadata.py

@@ -43,7 +43,7 @@ def generate_metadata(prompt_content):
     logger.info("Sending request to Anthropic API")
     message = client.messages.create(
         model="claude-3-5-sonnet-20240620",
-        max_tokens=1000,
+        max_tokens=2500,
         messages=[
             {
                 "role": "user",
@@ -76,7 +76,13 @@ def generate_metadata(prompt_content):
     return metadata
 
 def should_update_metadata(prompt_file, metadata_file):
-    """Check if metadata should be updated based on content hash."""
+    """Check if metadata should be updated based on content hash or force flag."""
+    force_regenerate = os.environ.get('FORCE_REGENERATE', 'false').lower() == 'true'
+    
+    if force_regenerate:
+        logger.info("Forcing metadata regeneration due to system prompt changes.")
+        return True, None
+
     # Generate hash of the prompt file content
     with open(prompt_file, 'rb') as f:
         prompt_content = f.read()
@@ -200,7 +206,7 @@ def update_prompt_metadata():
                             shutil.rmtree(item_path)
                         else:
                             os.rename(item_path, new_dir_path)
-                        item_path = new_dir_path  # Update item_path for the new location
+                        item_path = new_dir_path
 
                     # Save updated metadata
                     metadata_path = os.path.join(item_path, 'metadata.yml')

.github/scripts/update_views.py

@@ -66,23 +66,27 @@ def update_views():
             logger.info(f"Wrote view content to {view_path}")
 
             # Organize prompts by category for the README
-            category = format_category(metadata.get('category', 'Uncategorized'))
-            if category not in categories:
-                categories[category] = []
+            primary_category = metadata.get('primary_category', 'uncategorized')
+            if primary_category not in categories:
+                categories[primary_category] = []
 
-            categories[category].append({
+            categories[primary_category].append({
                 'title': metadata.get('title', 'Untitled'),
                 'description': metadata.get('one_line_description', 'No description'),
-                'path': f'prompts/{prompt_dir}/view.md'
+                'path': f'prompts/{prompt_dir}/view.md',
+                'subcategories': metadata.get('subcategories', [])
             })
-            logger.info(f"Added prompt to category: {category}")
+            logger.info(f"Added prompt to category: {primary_category}")
+
+    # Remove empty categories
+    categories = {k: v for k, v in categories.items() if v}
 
     # Sort categories alphabetically
     sorted_categories = dict(sorted(categories.items()))
 
     # Generate README content using the template and write to file
     logger.info("Generating README content")
-    readme_content = readme_template.render(categories=sorted_categories)
+    readme_content = readme_template.render(categories=sorted_categories, format_category=format_category)
     readme_path = 'README.md'
     with open(readme_path, 'w') as f:
         f.write(readme_content)

.github/templates/readme_template.md

@@ -6,7 +6,7 @@ Welcome to the **Prompt Library**. This repository contains a collection of AI p
 
 {% for category, prompts in categories.items() %}
 
-### {{ category }}
+### {{ format_category(category) }}
 
 {% for prompt in prompts %}
 

.github/templates/view_template.md

@@ -27,3 +27,15 @@
 
 - {{ tag }}
 {% endfor %}
+
+### 📚 Category
+
+Primary Category: {{ metadata.primary_category }}
+
+{% if metadata.subcategories %}
+Subcategories:
+{% for subcategory in metadata.subcategories %}
+
+- {{ subcategory }}
+{% endfor %}
+{% endif %}

.github/workflows/update_views.yml

@@ -14,22 +14,39 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 2
+
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
           python-version: "3.12.6"
           cache: "pip"
           cache-dependency-path: ".github/scripts/requirements.txt"
+
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
           pip install -r .github/scripts/requirements.txt
+
+      - name: Check for system prompt changes
+        id: check_changes
+        run: |
+          if git diff --name-only HEAD^ HEAD | grep -q ".github/prompts/ai_prompt_analyzer_and_output_generator/"; then
+            echo "FORCE_REGENERATE=true" >> $GITHUB_ENV
+          else
+            echo "FORCE_REGENERATE=false" >> $GITHUB_ENV
+          fi
+
       - name: Generate metadata
         env:
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          FORCE_REGENERATE: ${{ env.FORCE_REGENERATE }}
         run: python .github/scripts/generate_metadata.py
+
       - name: Update views
         run: python .github/scripts/update_views.py
+
       - name: Commit changes
         run: |
           git config --local user.name "github-actions[bot]"

README.md

@@ -6,71 +6,65 @@ Welcome to the **Prompt Library**. This repository contains a collection of AI p
 
 
 
-### Code Documentation
+### Artificial Intelligence
 
 
 
-- [AI Code Repository Documentation Generator](prompts/ai_code_repository_documentation_generator/view.md) - Analyzes code repositories and generates comprehensive documentation autonomously
-
+- [God Tier Assistant Generator](prompts/god_tier_assistant_generator/view.md) - Generates innovative ideas for specialized AI assistants based on given topics
 
 
+- [AI Application Idea Generator](prompts/ai_application_idea_generator/view.md) - Generates diverse and innovative AI application ideas for specific domains
 
-### Code Improvement
 
 
 
-- [Code Refactoring AI Assistant](prompts/code_refactoring_ai_assistant/view.md) - Analyzes, refactors, and tests code to improve quality, readability, and performance
+### Documentation
 
 
 
+- [AI Code Documentation Generator](prompts/ai_code_documentation_generator/view.md) - Analyzes code repositories and generates comprehensive documentation
 
-### Idea Generation
 
 
 
-- [God Tier Assistant Generator](prompts/god_tier_assistant_generator/view.md) - Generates innovative ideas for specialized AI assistants based on given topics
+### Full Stack Development
 
 
-- [AI Topic Idea Generator](prompts/ai_topic_idea_generator/view.md) - Generates innovative AI application ideas for specific domains and constraints
 
+- [Advanced AI Software Development Assistant](prompts/advanced_ai_software_development_assistant/view.md) - Provides comprehensive guidance and support throughout the software development lifecycle
 
 
 
-### Issue Management
 
-
-
-- [GitHub Issue Creator](prompts/github_issue_creator_from_user_input/view.md) - Creates well-structured GitHub Issues from user input and project context
+### Project Management
 
 
 
+- [Software Specification Generator](prompts/software_specification_generator/view.md) - Generates comprehensive software specifications based on user requirements
 
-### Product Management
 
-
-
-- [Software Specification Generator](prompts/software_specification_generator/view.md) - Creates comprehensive software specifications based on user requirements and interactive review
+- [GitHub Issue Creator](prompts/github_issue_creator_from_user_input/view.md) - Creates well-structured GitHub Issues from user input and project context
 
 
 
 
-### Software Development
+### Refactoring
 
 
 
-- [AI Software Development Assistant](prompts/ai_software_development_assistant/view.md) - Provides expert guidance and support throughout the software development lifecycle
+- [Code Refactoring AI Assistant](prompts/code_refactoring_ai_assistant/view.md) - Analyzes, refactors, and tests code to improve quality, readability, and performance
 
 
-- [GitHub Pull Request Generator](prompts/github_pull_request_generator/view.md) - Generates comprehensive and well-structured GitHub pull requests based on change details and project context
 
 
+### Version Control
 
 
-### Version Control
 
+- [Git Commit Message Writer](prompts/git_commit_message_writer/view.md) - Generates concise, informative git commit messages following Conventional Commits with emojis
 
 
-- [Git Commit Message Writer](prompts/git_commit_message_writer/view.md) - Generates concise, informative git commit messages with emojis following Conventional Commits
+- [GitHub Pull Request Generator](prompts/github_pull_request_generator/view.md) - Generates comprehensive and well-structured GitHub pull requests
 
 
 

prompts/advanced_ai_software_development_assistant/metadata.yml

@@ -0,0 +1,22 @@
+title: Advanced AI Software Development Assistant
+primary_category: full_stack_development
+subcategories:
+- software_lifecycle_management
+- development_workflow_optimization
+directory: advanced_ai_software_development_assistant
+tags:
+- software_development
+- code_generation
+- best_practices
+- debugging
+- documentation
+one_line_description: Provides comprehensive guidance and support throughout the software
+  development lifecycle
+description: This AI assistant offers expert guidance, code suggestions, and workflow
+  optimization for software developers across the entire development lifecycle. It
+  covers various aspects including coding, debugging, documentation, and best practices
+  in multiple programming languages and frameworks.
+variables:
+- '{{USER_REQUEST}}'
+- '{{CONTEXT}}'
+content_hash: None