refactor: optimize test generation with ROI-based approach #91
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
Implement 3-layer quality filtering to prevent over-generation: - Behavior-First: Filter implementation details at AC level - Two-Pass Generation: ROI-based candidate selection - Budget Enforcement: Hard limits (max 3 integration, 1-2 E2E/feature) Changes: - acceptance-test-generator.md: Add ROI calculation, budget system, skip reporting - technical-designer.md: Add Behavior-First Principle with 3-check process Impact: Expected 60-75% test reduction with 3-5x ROI improvement 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
Remove skip information tracking from acceptance-test-generator:
- Remove skip report from test files and generation reports
- Remove skip tracking from mandatory compliance section
- Remove maxSkippedROI from roiMetrics
- Focus only on selected tests to reduce context pollution
Simplify technical-designer AC scoping section:
- Remove verbose 3-check process (duplicated with acceptance-test-generator)
- Remove domain-specific examples (bcrypt, Redis, authentication)
- Use generic, domain-agnostic examples
- Remove upstream/downstream references (violates agent independence)
Unify latest information research guidelines:
- Add Mandatory/Recommended distinction for better decision-making
- Dynamically fetch current year with date command
- Replace hardcoded "2024" with {current_year} placeholder
- Apply to technical-designer and document-reviewer
Benefits:
- Reduced token consumption and context pollution
- Eliminated redundancy between agent files
- Future-proof search queries (no year hardcoding)
- Improved LLM generation precision
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <[email protected]>
shinpr
added a commit
to shinpr/claude-code-workflows
that referenced
this pull request
Nov 7, 2025
…ject-boilerplate Implement 3-layer quality filtering to prevent test over-generation: - Behavior-First: Filter implementation details at AC level - Two-Pass Generation: ROI-based candidate selection - Budget Enforcement: Hard limits (max 3 integration, 1-2 E2E/feature) Changes: - acceptance-test-generator.md: Add ROI calculation, budget system, detailed reporting - document-reviewer.md: Add dynamic year detection for future-proof searches - technical-designer.md: Add AC examples (implementation vs behavior), dynamic year detection Source: shinpr/ai-coding-project-boilerplate#91 Impact: Expected 60-75% test reduction with improved maintainability 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
6 tasks
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.
Implement 3-layer quality filtering to prevent over-generation:
Changes:
Impact: Expected 60-75% test reduction with 3-5x ROI improvement
🤖 Generated with Claude Code