Self-validating QA loop extracted from AutoClaude - reviews acceptance criteria and auto-fixes issues until approval or escalation.
/plugin marketplace add DNYoussef/context-cascade/plugin install dnyoussef-context-cascade@DNYoussef/context-cascadeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Before writing ANY code, you MUST check:
.claude/library/catalog.json.claude/docs/inventories/LIBRARY-PATTERNS-GUIDE.mdD:\Projects\*| Match | Action |
|---|---|
| Library >90% | REUSE directly |
| Library 70-90% | ADAPT minimally |
| Pattern exists | FOLLOW pattern |
| In project | EXTRACT |
| No match | BUILD (add to library after) |
Run a self-validating QA loop that reviews implementation against acceptance criteria, auto-fixes issues, and iterates until approval or human escalation.
D:\Projects\life-os-dashboard\backendimplementation_plan.json containing acceptance criteriaValidation Check
QA Reviewer Session
implementation_plan.json with qa_signoff statusIssue Analysis
QA Fixer Session (if rejected)
Iteration Loop
from app.qa import run_wired_qa_loop, quick_qa_check
# Full QA loop with infrastructure wired
success = await run_wired_qa_loop(
project_dir=Path("D:/Projects/my-project"),
spec_dir=Path("D:/Projects/my-project/.specs/feature-x"),
model="sonnet",
verbose=True,
)
# Quick single-iteration check
result = await quick_qa_check(
project_dir=Path("D:/Projects/my-project"),
spec_dir=Path("D:/Projects/my-project/.specs/feature-x"),
)
print(f"Status: {result['status']}")
# Run QA validation
python -c "
import asyncio
from pathlib import Path
from app.qa import run_wired_qa_loop
asyncio.run(run_wired_qa_loop(
Path('D:/Projects/my-project'),
Path('D:/Projects/my-project/.specs/feature-x'),
verbose=True
))
"
implementation_plan.json - Updated with qa_signoffQA_REPORT.md - Detailed review findingsQA_FIX_REQUEST.md - Human-readable fix requestsQA_ESCALATION.md - Created if recurring issues detectedMANUAL_TEST_PLAN.md - For no-test projectsConfidence: 0.85 (ceiling: observation 0.95) - Skill documented based on implemented QA pipeline infrastructure.
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.