feat: Task listing fixes, upgrade support, and duplicate prevention #62
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Fixed tasks command to properly fetch and display GitHub issues - Added rich formatting with priority indicators (🔴🟠🟡🟢) - Added effort indicators (📏 L, 📐 M, 📌 S) - Enhanced status command to show health check and available tasks - Improved error handling and user feedback - Added task summary with counts (total, unassigned, assigned) - Better JSON parsing to prevent silent failures The commands now provide clear, colorful output that helps agents quickly understand available work and priorities.
- Enhanced conductor-init.sh to detect existing installations and offer upgrade/reinstall options - Added intelligent version checking with current vs new version comparison - Implemented backup/restore mechanism for user configurations during upgrades - Made setup steps conditional - skip role config, demo tasks, etc. for upgrades - Added environment selection skip for upgrade path - Created comprehensive upgrade documentation (UPGRADE.md) - Added Claude Code automation prompts (CLAUDE_CODE_PROMPT.md) - Updated README with upgrade instructions and new section - Preserved user configurations: config.yaml, CLAUDE.md files - Added upgrade-specific success messages showing what was updated/preserved The upgrade process is now seamless - users just run the same install command and choose 'Upgrade' when prompted. All their configurations and work are preserved while core scripts are updated.
ryanmac
changed the title
- Added check-duplicate-issues.py script with smart similarity detection - Uses title similarity (70% weight) and keyword overlap (30% weight) - Configurable similarity threshold (default 60%) - Searches both open and closed issues - Enhanced conductor script: - Added 'check-dup' command for easy duplicate checking - Modified demo task creation to check for existing similar issues - Prevents creating duplicate starter tasks - Updated CLAUDE.md with comprehensive duplicate prevention instructions - Clear guidelines for AI agents before creating issues - Example commands and search strategies - Emphasis on semantic similarity checking - Created detailed DUPLICATE_PREVENTION.md guide: - Why duplicate prevention matters - Step-by-step process for checking - Common duplicate patterns to watch for - AI agent-specific guidelines - Updated README.md best practices to include duplicate prevention This helps maintain cleaner issue tracking and prevents wasted effort on duplicate work.
ryanmac
changed the title
- Transformed CLAUDE_CODE_PROMPT.md into a marketing-focused guide - Added compelling headlines: 'Upgrade Your Project to Agentic Development' - Emphasized speed and parallelization benefits - Used action-oriented language: 'I need to move faster' - Highlighted transformation: 'single-threaded to massively parallel' - Enhanced all prompt sections: - New Projects: 'Ship 10x Faster' - Upgrades: 'Zero downtime. Zero configuration loss.' - Full Automation: 'revolutionize how we build' - Environment-specific: 'multi-agent powerhouse' - Updated README.md: - Added prominent Claude Code section near the top - Enhanced upgrade section with marketing language - Better call-to-action with link to power prompts The prompts now sell the value proposition while maintaining all technical functionality. Users can paste and go, with Claude Code understanding both the 'why' and the 'how'.
- Updated CLAUDE.md with 'Managing Your Todo List' section - Instructions to check for similar todos before adding new ones - Guidance to consolidate related items - Examples of good vs bad todo management - Enhanced DUPLICATE_PREVENTION.md with AI Agent Todo List Management - Todo list hygiene practices - Sync between internal todos and GitHub issues - Regular cleanup recommendations This ensures AI agents maintain clean internal task tracking alongside preventing duplicate GitHub issues.
- Analyzed 20 different prompt variations to find the most effective - Selected: 'Ultrathink: What task will create the most value? Find it, claim it, complete it.' - Key benefits: - Triggers deep analysis with 'ultrathink' keyword - Question format engages strategic thinking - Memorable 3-step rhythm: find → claim → complete - Value-focused rather than just task-focused - Universal across all roles and project types - Updated documentation: - conductor-init.sh: Updated Conductor app setup prompt - README.md: Added 'The Perfect Kickoff Prompt' section - CLAUDE.md: Added 'Universal Kickoff Prompt' in quick start - CLAUDE_CODE_PROMPT.md: Updated productivity mode prompt - Recommended for text expanders (e.g., ;ustart) for instant agent activation This prompt helps AI agents think more deeply about task selection and focus on delivering maximum value rather than just completing any available work.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
This PR includes five major improvements:
Part 1: Task Listing Fixes
Fixed the
tasksandstatuscommands to properly display GitHub issues with rich formatting including priority indicators (🔴🟠🟡🟢) and effort sizing.Part 2: Upgrade Support
Enhanced conductor-init.sh with intelligent upgrade detection, backup/restore of configurations, and selective file updates. Added UPGRADE.md documentation.
Part 3: Duplicate Issue Prevention
check-duplicate-issues.pyscript with smart similarity detection./conductor check-dup "title"command for easy checkingPart 4: Marketing-Enhanced Claude Code Prompts
Rewrote CLAUDE_CODE_PROMPT.md with compelling headlines like "🚀 Upgrade Your Project to Agentic Development" and action-oriented language: "I need to move faster."
Part 5: Universal Kickoff Prompt
After analyzing 20 different variations, selected the optimal prompt for starting AI agents:
Why This Prompt Works:
Documentation Updates:
Users can add this to text expanders (e.g.,
;ustart) for instant agent activation.Testing
Benefits
This comprehensive update improves the developer experience, prevents duplicate work, makes Code Conductor more appealing, and ensures AI agents focus on maximum value delivery.