This commit implements the complete LLM Usage Guides system for the Tendril project, establishing reusable prompt documents for AI-assisted workflows. ## What Was Implemented ### 1. Core Guide Documents **docs/PROMPTS/LLM-Usage-Guide.md** - Comprehensive LLM execution instructions: - Recognizing prompt documents (naming convention, structure, location) - Step-by-step execution process (5 phases: recognize, gather info, execute, handle errors, validate) - Information gathering requirements and best practices - Error handling procedures and common error patterns - Validation steps (pre-execution, during execution, post-execution) - Providing feedback (progress updates, error reporting, completion summaries) - Best practices for execution, communication, and quality - Special instructions for Tendril-specific context - Troubleshooting guide for common prompt execution issues - Customized for Tendril project structure and Gitea platform **docs/PROMPTS/Prompt-Creation-Guide.md** - Guide for creating effective prompts: - Naming convention (NN-Descriptive-Name-Prompt.md format) - Complete prompt structure template with all required sections - Best practices for writing effective instructions - Information gathering guidelines - Error handling documentation standards - Testing procedures for new prompts - Common patterns (status check, search, sync patterns) - Decision criteria for when to create new prompts - Update procedures for existing prompts - Comprehensive checklist for new prompts - Examples customized for Tendril project - References to Gitea-specific workflows and features ### 2. Initial Prompt Documents **docs/PROMPTS/00-Project-Status-Check-Prompt.md** - Project status overview: - Purpose: Check current status of all project phases - Reads all phase blueprints in tendril/phases/ - Extracts phase status, deliverables, milestones - Organizes by status (Complete, In Progress, Planned) - Provides comprehensive status summary with counts - Highlights issues or blockers - Error handling for missing files, invalid formats - Validation checklist for completion - Customized for Tendril phase structure **docs/PROMPTS/01-KB-Content-Search-Prompt.md** - KB system search: - Purpose: Search KB system for relevant content - Supports multiple search types: topics, tags, phase relevance, keywords - Uses kb/_index.md for efficient searching - Reads matching KB files and extracts metadata - Presents organized search results with summaries - Handles missing index, invalid criteria, empty results - Provides helpful suggestions for refining searches - Customized for Tendril KB structure and categories **docs/PROMPTS/02-Phase-Documentation-Sync-Prompt.md** - Phase documentation synchronization: - Purpose: Ensure phase documentation consistency - Reads all four phase documents (blueprint, tasks, decisions, changelog) - Compares and identifies discrepancies - Syncs tasks.md with blueprint deliverables and Definition of Done - Updates changelog.md with sync entry - Reviews decisions.md for missing ADRs - Verifies consistency across all documents - Follows Cursor rules for phase documentation synchronization - Error handling for missing files, format issues, unresolvable discrepancies - Customized for Tendril phase structure and documentation system ## Why This Implementation ### Standardized AI Workflows LLM Usage Guides enable consistent, repeatable AI-assisted workflows. Instead of explaining the same tasks repeatedly, prompts provide standardized instructions that work reliably every time. ### Reusability and Efficiency Prompt documents can be dragged into Cursor chat sessions and executed immediately. This saves time and ensures tasks are performed consistently across different sessions and users. ### Quality and Reliability Well-structured prompts include validation checklists, error handling, and best practices. This reduces errors and ensures high-quality results. ### Knowledge Preservation Prompts document how to perform complex tasks, preserving institutional knowledge and making it accessible to anyone who needs to perform the task. ### Integration with Project Systems Prompts are designed to work with Tendril's phase documentation system, KB system, and Gitea workflows, providing seamless integration with existing project infrastructure. ## Technical Details ### Prompt Document Structure All prompts follow a consistent structure: 1. **Title and Purpose** - Clear description of what the prompt does 2. **How to Use** - Instructions for using the prompt 3. **CRITICAL: Information Gathering** - Required information section 4. **Step-by-Step Process** - Phased execution instructions 5. **Error Handling** - Common issues and solutions 6. **Validation Checklist** - Completion verification 7. **Important Notes** - Critical instructions for AI assistant ### Naming Convention Prompts follow strict naming: - 00-09: Core system prompts - 10-19: Phase management prompts - 20-29: KB system prompts - 30-39: Workflow and automation prompts - 40-49: Documentation prompts - 50+: Project-specific prompts ### Customization for Tendril All prompts and guides are customized for: - **Project Name**: Tendril (not "pairs" or placeholders) - **Platform**: Gitea (not GitHub) - **Repository**: https://git.parkingmeter.info/Mycelium/tendril - **Directory Structure**: tendril/phases/, kb/ with category directories - **Workflows**: Gitea Actions (with GitHub Actions compatibility notes) ### Integration Points Prompts integrate with: - **Phase Documentation**: tendril/phases/phase-XX-name/ files - **KB System**: kb/ directory with index and category structure - **Workflows**: .github/workflows/ (Gitea Actions) - **Documentation**: docs/ directory structure ## Files Added - docs/PROMPTS/LLM-Usage-Guide.md - LLM execution instructions (~400 lines) - docs/PROMPTS/Prompt-Creation-Guide.md - Prompt creation guide (~600 lines) - docs/PROMPTS/00-Project-Status-Check-Prompt.md - Status check prompt (~180 lines) - docs/PROMPTS/01-KB-Content-Search-Prompt.md - KB search prompt (~240 lines) - docs/PROMPTS/02-Phase-Documentation-Sync-Prompt.md - Documentation sync prompt (~250 lines) **Total**: 5 files, ~1,670 lines of prompt documentation ## Validation All Phase 4 requirements met: - ✅ LLM Usage Guide created and comprehensive - ✅ Prompt Creation Guide created with complete template - ✅ Three initial prompt documents created - ✅ All prompts follow naming convention - ✅ All prompts include required sections - ✅ All files reference "Tendril" (42 references found) - ✅ All files use "Gitea" terminology (10 references, no GitHub) - ✅ Examples relevant to Tendril project structure - ✅ Documentation is clear and actionable ## Next Steps Phase 4 complete. LLM Usage Guides system is ready for use. Prompts can be dragged into Cursor chat sessions to perform standardized tasks. Ready for Phase 5: Validation and Testing. ## Related - Phase 4 Plan: kb/_guides/PROJECT-SETUP-GUIDE/PHASE-4-PLAN.md - Replication Guide: kb/_guides/PROJECT-SETUP-GUIDE/COMPLETE-SYSTEM-REPLICATION-GUIDE.md - Gitea LLM Guidelines: docs/GITEA/LLM-Gitea-Guidelines.md
7.2 KiB
KB Content Search Prompt
Purpose: Search the Knowledge Base (KB) system for relevant content matching specified criteria (topics, tags, phase relevance, or keywords).
How to Use: Drag this entire document into a Cursor chat session, then provide search criteria (topics, tags, phase, or keywords). The AI assistant will search the KB index and relevant files to find matching content.
CRITICAL: Information Gathering
Required Information (You should provide this)
Before starting, ASK THE USER for the following information if not already provided:
-
Search criteria (REQUIRED - at least one)
- Format: Topics (array), Tags (array), Phase relevance (string), or Keywords (string)
- Examples:
- Topics:
["workflows", "automation"] - Tags:
["gitea", "actions"] - Phase:
"phase-03"or"phase-3" - Keywords:
"KB system setup"
- Topics:
- Why it's needed: Determines what content to search for
-
Search scope (OPTIONAL)
- Format: Specific category or "all"
- Examples:
"01_projects","02_systems","all" - Default: "all" (search all KB categories)
- Why it's needed: Limits search to specific KB categories if desired
If Information is Missing
ALWAYS ASK for missing required information before proceeding. Do not make assumptions about:
- What the user wants to search for
- Which KB categories to search
- Search criteria format
Step-by-Step Process
Phase 1: Read KB Index
-
Read the KB index file:
- Path:
kb/_index.md - Extract: File listings, topics index, tags index, phase relevance index
- Path:
-
Validation:
- Verify
kb/_index.mdexists - Confirm index is readable
- Check index structure is valid
- Verify
Phase 2: Parse Search Criteria
-
Identify search type:
- Topics search: If topics array provided
- Tags search: If tags array provided
- Phase search: If phase relevance provided
- Keyword search: If keywords string provided
- Combined: If multiple criteria provided
-
Prepare search parameters:
- Normalize topics/tags (lowercase, trim)
- Normalize phase format (ensure
phase-XXformat) - Prepare keyword search terms
-
Validation:
- Search criteria are valid
- Format is correct
- At least one search criterion is provided
Phase 3: Execute Search
-
Search by topics (if provided):
- Check topics index in
kb/_index.md - Find files matching topic(s)
- Collect file paths
- Check topics index in
-
Search by tags (if provided):
- Check tags index in
kb/_index.md - Find files matching tag(s)
- Collect file paths
- Check tags index in
-
Search by phase (if provided):
- Check phase relevance index in
kb/_index.md - Find files relevant to specified phase
- Collect file paths
- Check phase relevance index in
-
Search by keywords (if provided):
- Search file titles in index
- Search summaries in index
- Optionally: Search file contents (if index includes content)
- Collect file paths
-
Combine results (if multiple criteria):
- Merge results from different search types
- Remove duplicates
- Apply search scope filter if specified
-
Validation:
- Search executed successfully
- Results collected
- Duplicates removed
Phase 4: Read Matching Files
For each matching file found:
-
Read the KB file:
- Path:
kb/[category]/[filename].md - Extract: Title, summary, topics, tags, phase relevance, key content
- Path:
-
Extract relevant information:
- Frontmatter metadata
- Key takeaways (if present)
- Summary section
- Relevant content sections
-
Validation:
- File exists and is readable
- Metadata extracted correctly
- Content is relevant to search
Phase 5: Present Search Results
-
Organize results:
- Group by category (if multiple categories)
- Sort by relevance (if possible)
- List file paths and titles
-
Create summary:
- Total matches found
- Matches by category
- Matches by search type
-
Present detailed results:
- For each match:
- File path
- Title
- Summary
- Matching topics/tags/phases
- Key takeaways (if available)
- Link to full file
- For each match:
-
Validation:
- All matches are included
- Information is accurate
- Results are organized clearly
Error Handling
Common Issues
KB Index Not Found
- Error message: "File not found: kb/_index.md"
- Fix:
- Check if
kb/_index.mdexists - Run
kb/scripts/generate-index.shto generate index - Verify KB system is set up correctly
- Check if
- Prevention: Ensure KB index is generated before searching
Invalid Search Criteria Format
- Error message: "Invalid search criteria format"
- Fix:
- Verify criteria format matches expected format
- Check topics/tags are arrays
- Verify phase format is
phase-XX - Ask user to clarify format
- Prevention: Validate format before searching
No Matches Found
- Error message: "No matching KB files found"
- Fix:
- Verify search criteria are correct
- Check if KB files exist in specified categories
- Try broader search criteria
- Check index is up to date
- Prevention: Provide helpful message suggesting alternative searches
KB File Read Error
- Error message: "Error reading KB file: [path]"
- Fix:
- Verify file exists at specified path
- Check file permissions
- Verify file has valid frontmatter
- Skip file and continue with others
- Prevention: Handle file read errors gracefully
Index Out of Date
- Error message: "Index may be out of date"
- Fix:
- Run
kb/scripts/generate-index.shto update index - Re-run search after index update
- Note that results may be incomplete
- Run
- Prevention: Keep index updated regularly
Validation Checklist
Before completing, verify:
- KB index read successfully
- Search criteria parsed correctly
- Search executed for all provided criteria
- Matching files identified
- All matching files read (or errors noted)
- Results organized clearly
- Summary includes match counts
- Detailed results include all relevant information
- File paths are correct and accessible
- Results are relevant to search criteria
Important Notes for AI Assistant
- Use the index first: Always read
kb/_index.mdbefore searching individual files - Handle missing index: If index doesn't exist, offer to generate it or search files directly
- Be flexible with matching: Match topics/tags case-insensitively, handle variations
- Provide context: Include why files match (which topic/tag/phase matched)
- Limit results if needed: If too many matches, suggest refining search criteria
- Handle empty results: Provide helpful suggestions if no matches found
- Respect search scope: If scope specified, only search within that category
- Use Tendril terminology: Reference "Tendril" project and KB system correctly
- Note index freshness: Mention if index might be out of date
Location: docs/PROMPTS/01-KB-Content-Search-Prompt.md
Related:
kb/_index.md- KB index filekb/README.md- KB system documentationkb/scripts/generate-index.sh- Index generation scriptdocs/PROMPTS/LLM-Usage-Guide.md- LLM execution guidelines