Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate comprehensive quality report with metrics and verification. Produces final CHAPTER_XX_VERIFICATION.md and quality_metrics.json for deployment approval.
.claude/skills/aiskillstore-quality-report-generate/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 140% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 75% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 148% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 253% | 0% |
This skill generates the final quality report documenting everything about a chapter's generation and validation. The report:
This is the final skill before validation gates, producing the evidence needed to approve or reject a chapter for deployment.
validation_structure.json (Gate 1 results)validation_semantic.json (Gate 2 results)consolidation_log.json (consolidation data)chapter_XX.html fileoutput/chapter_XX/chapter_artifacts/CHAPTER_XX_VERIFICATION.mdoutput/chapter_XX/chapter_artifacts/quality_metrics.jsonValidation reports (from previous gates):
validation_structure.json - HTML structure validation resultsvalidation_semantic.json - Semantic validation resultsconsolidation_log.json - Page consolidation metadataChapter content:
chapter_XX.html - Final consolidated HTMLpage_artifacts/page_YY/*.html - Individual page HTML (optional, for analysis)Reference data (optional):
page_artifacts/page_YY/02_page_XX.png - Original PDF pages (for visual comparison)base_score = 100
# Deduct for structure issues
if structure_errors > 0:
base_score -= (structure_errors * 10)
# Deduct for semantic issues
if semantic_errors > 0:
base_score -= (semantic_errors * 5)
# Deduct for warnings
warning_count = structure_warnings + semantic_warnings
base_score -= (warning_count * 2)
# Bonus for semantic classes
if semantic_classes_ratio > 0.8:
base_score += 5
overall_score = max(0, min(100, base_score))expected_pages = last_page - first_page + 1
pages_with_content = count_pages_with_substantial_content()
completeness_percent = (pages_with_content / expected_pages) * 100checks_passed = structure_validation_checks_passed
checks_total = structure_validation_checks_total
compliance_percent = (checks_passed / checks_total) * 100required_classes = [
'page-container', 'page-content', 'chapter-header',
'section-heading', 'paragraph', 'bullet-list'
]
found_classes = [c for c in required_classes if c in html]
compliance_percent = (len(found_classes) / len(required_classes)) * 100Path: output/chapter_XX/chapter_artifacts/CHAPTER_XX_VERIFICATION.md
Example structure:
markdown# Chapter 2 HTML Accuracy Verification Report ## Summary **Status**: ✅ **VERIFIED ACCURATE** The Chapter 2 HTML document has been thoroughly verified for accuracy and quality. All validation gates passed successfully. --- ## Overall Quality Metrics | Metric | Value | Target | Status | |--------|-------|--------|--------| | **Overall Quality Score** | 96/100 | ≥85 | ✅ PASS | | **Structure Validation** | 100% | 100% | ✅ PASS | | **Semantic Validation** | 98% | ≥90% | ✅ PASS | | **Content Completeness** | 100% | 100% | ✅ PASS | | **Visual Accuracy** | 94% | ≥85% | ✅ PASS | --- ## Content Summary ### Pages - **Book Pages**: 16-29 (14 pages) - **PDF Indices**: 15-28 - **Chapter**: 2 - Rights in Real Estate ### Content Elements - **Total Paragraphs**: 156 - **Total Headings**: 28 (1 h1, 4 h2, 23 h4) - **Total Lists**: 12 (132 total items) - **Total Tables/Exhibits**: 3 - **Total Images**: 5 - **Total Words**: 12,547 --- ## Validation Results ### ✅ HTML Structure Validation (PASSED) All structural checks passed: - ✓ HTML5 DOCTYPE valid - ✓ `<html>`, `<head>`, `<body>` tags properly formed - ✓ Meta charset and viewport tags present - ✓ Title tag with descriptive content - ✓ CSS stylesheet linked correctly - ✓ `<div class="page-container">` wrapper present - ✓ `<main class="page-content">` structure valid - ✓ All tags properly matched and closed - ✓ No unclosed or improperly nested tags **Errors**: 0 **Warnings**: 0 ### ✅ Semantic Validation (PASSED) All semantic checks passed: - ✓ Required CSS classes present and correct - ✓ Heading hierarchy valid (no jumps, logical flow) - ✓ All paragraphs properly formatted - ✓ All lists correctly structured - ✓ Tables properly formatted - ✓ Semantic class usage consistent throughout - ✓ Page maintains continuous format (no pagination) **Errors**: 0 **Warnings**: 0 ### ✅ Visual Accuracy Check (PASSED) Comparison with original PDF pages: - Overall similarity: 94% - Page-by-page average: 94% - All pages ≥ 85% threshold - Layout matches original - Content positioning accurate - Text rendering correct --- ## Consolidation Details **Chapter Opening**: Page 16 (Chapter header and navigation included) **Consolidation**: Pages 16-29 merged into single continuous document **Pages Merged**: 14 **Page Headers Removed**: 13 (continuation pages) **Duplicate Content**: None detected **Consolidation Log**:
{ "pages_merged": 14, "pages_include": ...], "heading_hierarchy": { "h1": 1, "h2": 4, "h4": 23 }, "content_statistics": { "paragraphs": 156, "lists": 12, "tables": 3, "images": 5, "total_words": 12547 } }
---
## CSS Classes Used
**Core Structure**: page-container, page-content, chapter-header (6 classes)
**Content**: section-heading, subsection-heading, paragraph, bullet-list, bullet-item (12 classes)
**Exhibits**: exhibit, exhibit-table, exhibit-title, exhibit-header (4 classes)
**Navigation**: section-navigation, nav-item (2 classes)
**Special**: section-divider, page-footer (2 classes)
**Total unique classes**: 26
**Classes found as required**: 6/6 (100%)
---
## Issues & Findings
### ✅ No Critical Issues Found
- ✓ No missing sections
- ✓ No missing content
- ✓ No structural problems
- ✓ No broken internal links
- ✓ No invalid HTML
- ✓ No semantic violations
### ⚠️ Minor Notes
- None - all validation gates passed
---
## Generation Process
**Extraction**: Rich data extracted from PDF pages (text, fonts, images)
**ASCII Preview**: Structural layout created for AI reference
**AI Generation**: Individual pages generated using 3-input approach:
- Visual reference (PNG rendering of PDF)
- Parsed text data (JSON with metadata)
- Layout structure (ASCII preview)
**Structure Validation**: HTML5 compliance verified
**Consolidation**: Pages merged into continuous chapter
**Semantic Validation**: Structure and classes verified
**Quality Report**: Final metrics and status
---
## Accuracy Assessment
| Criterion | Result | Assessment |
|-----------|--------|------------|
| **Content Completeness** | 100% | All sections present |
| **Page Coverage** | 14/14 | All pages included |
| **Heading Accuracy** | ✅ | Correct hierarchy |
| **List Accuracy** | ✅ | All items present |
| **Table Accuracy** | ✅ | Proper formatting |
| **Image References** | ✅ | Correct paths |
| **Semantic Structure** | ✅ | Proper classes |
| **Visual Fidelity** | 94% | Matches original layout |
---
## Recommendation
✅ **APPROVED FOR DEPLOYMENT**
This chapter has passed all quality gates:
1. ✓ HTML structure is valid
2. ✓ Semantic requirements met
3. ✓ Content is complete and accurate
4. ✓ Visual appearance matches original
5. ✓ Ready for production use
**Next Steps**:
- Deploy to production website
- Monitor user feedback
- Archive validation artifacts
- Proceed with next chapter
---
## Technical Details
**Generated**: 2025-11-08T14:40:00Z
**Generator**: Calypso Quality Report System
**Report Version**: 2.0
**Chapter**: 2
**Status**: ✅ PASSED ALL GATES
{ "report_metadata": { "chapter": 2, "generated_at": "2025-11-08T14:40:00Z", "validation_status": "PASS", "overall_score": 96, "deployable": true } }
---
**Report prepared by**: Calypso Verification Pipeline
**Quality Standards Version**: 2025-11-08
**Verification Status**: ✅ PASSEDPath: output/chapter_XX/chapter_artifacts/quality_metrics.json
json{ "chapter": 2, "title": "Rights in Real Estate", "book_pages": "16-29", "pdf_indices": "15-28", "report_generated_at": "2025-11-08T14:40:00Z", "overall_status": "PASS", "overall_quality_score": 96, "deployment_approved": true, "validation_results": { "structure_validation": { "status": "PASS", "checks_passed": 10, "checks_failed": 0, "checks_total": 10, "compliance_percent": 100, "errors": [], "warnings": [] }, "semantic_validation": { "status": "PASS", "checks_passed": 8, "checks_failed": 0, "checks_total": 8, "compliance_percent": 100, "errors": [], "warnings": [] }, "visual_accuracy": { "status": "PASS", "overall_similarity": 0.94, "threshold": 0.85, "page_results": [ { "page": 16, "similarity": 0.96, "status": "PASS" }, { "page": 17, "similarity": 0.93, "status": "PASS" } // ... all pages ] } }, "content_metrics": { "total_pages": 14, "total_headings": 28, "heading_breakdown": { "h1": 1, "h2": 4, "h3": 0, "h4": 23 }, "total_paragraphs": 156, "total_lists": 12, "total_list_items": 132, "total_tables": 3, "total_images": 5, "total_words": 12547, "estimated_reading_time_minutes": 45 }, "structure_metrics": { "css_classes_found": 26, "required_classes_present": 6, "required_classes_total": 6, "page_container_valid": true, "page_content_valid": true, "continuous_format": true, "heading_hierarchy_valid": true }, "content_completeness": { "expected_pages": 14, "pages_with_content": 14, "completeness_percent": 100, "sections_verified": [ "Chapter Header", "Real Property Rights", "Physical Characteristics", "Interdependence", "Government Rights", "Regulations and Licensing" ] }, "quality_assessment": { "accuracy_level": "HIGH", "confidence_level": "HIGH", "ready_for_deployment": true, "requires_manual_review": false, "requires_fixes": false } }
Generate report using Python script:
bashcd Calypso/tools # Generate quality report python3 generate_quality_report.py \ --chapter 2 \ --html-file "../output/chapter_02/chapter_artifacts/chapter_02.html" \ --validation-structure "../output/chapter_02/chapter_artifacts/validation_structure.json" \ --validation-semantic "../output/chapter_02/chapter_artifacts/validation_semantic.json" \ --consolidation-log "../output/chapter_02/chapter_artifacts/consolidation_log.json" \ --output-dir "../output/chapter_02/chapter_artifacts"
The markdown report includes:
✓ Markdown report created with comprehensive information ✓ JSON metrics valid and machine-parseable ✓ Quality score calculated correctly ✓ All validation results aggregated ✓ Content metrics accurate ✓ Deployment recommendation provided ✓ Report ready for stakeholder review
For stakeholders: Read markdown report for human-friendly overview For CI/CD: Parse JSON metrics for automated decisions For archival: Both formats saved for audit trail For monitoring: JSON feeds quality dashboards
Once quality report is generated:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 11,797 | 6,792 | -42% | 1 | 1 | 0% | 2,183 | 5,243 | +140% | 0 | 0 | — |
case-01 | fail→pass | 23,714 | 13,264 | -44% | 1 | 1 | 0% | 4,918 | 6,940 | +41% | 0 | 0 | — |
case-02 | fail→fail | 16,204 | 5,669 | -65% | 1 | 1 | 0% | 2,997 | 4,237 | +41% | 0 | 0 | — |
case-03 | fail→pass | 22,644 | 16,292 | -28% | 1 | 1 | 0% | 4,429 | 7,743 | +75% | 0 | 0 | — |
case-05 | fail→pass | 11,901 | 5,001 | -58% | 1 | 1 | 0% | 1,941 | 4,820 | +148% | 0 | 0 | — |
case-06 | fail→fail | 9,649 | 4,483 | -54% | 1 | 1 | 0% | 1,655 | 4,757 | +187% | 0 | 0 | — |
case-07 | fail→pass | 9,775 | 9,577 | -2% | 1 | 1 | 0% | 1,607 | 5,679 | +253% | 0 | 0 | — |
case-08 | fail→pass | 10,890 | 7,782 | -29% | 1 | 1 | 0% | 1,895 | 5,426 | +186% | 0 | 0 | — |
case-09 | fail→fail | 10,514 | 10,171 | -3% | 1 | 1 | 0% | 1,599 | 5,496 | +244% | 0 | 0 | — |
case-10 | fail→pass | 5,952 | 3,830 | -36% | 1 | 1 | 0% | 1,183 | 4,761 | +302% | 0 | 0 | — |
case-11 | fail→pass | 10,894 | 2,892 | -73% | 1 | 1 | 0% | 1,984 | 4,482 | +126% | 0 | 0 | — |
case-12 | fail→pass | 3,896 | 4,128 | +6% | 1 | 1 | 0% | 663 | 4,689 | +607% | 0 | 0 | — |
case-13 | fail→pass | 13,100 | 10,923 | -17% | 1 | 1 | 0% | 2,154 | 5,851 | +172% | 0 | 0 | — |
case-14 | pass→pass | 3,621 | 3,539 | -2% | 1 | 1 | 0% | 756 | 4,589 | +507% | 0 | 0 | — |
case-15 | pass→pass | 6,766 | 4,254 | -37% | 1 | 1 | 0% | 1,209 | 4,722 | +291% | 0 | 0 | — |
case-16 | fail→pass | 7,245 | 2,548 | -65% | 1 | 1 | 0% | 1,202 | 4,368 | +263% | 0 | 0 | — |
case-17 | fail→pass | 9,105 | 4,987 | -45% | 1 | 1 | 0% | 1,711 | 4,878 | +185% | 0 | 0 | — |
case-18 | fail→pass | 8,780 | 5,772 | -34% | 1 | 1 | 0% | 1,772 | 4,952 | +179% | 0 | 0 | — |
case-19 | fail→pass | 4,732 | 9,553 | +102% | 1 | 1 | 0% | 179 | 5,796 | +3138% | 0 | 0 | — |
case-20 | pass→pass | 5,266 | 16,215 | +208% | 1 | 1 | 0% | 926 | 7,409 | +700% | 0 | 0 | — |
case-21 | pass→pass | 14,112 | 14,308 | +1% | 1 | 1 | 0% | 3,175 | 7,164 | +126% | 0 | 0 | — |
case-22 | pass→pass | 13,054 | 12,218 | -6% | 1 | 1 | 0% | 2,641 | 6,572 | +149% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 20 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +64 percentage points is the difference between those two pass rates over the 20 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.