dag-confidence-scorer
About
The dag-confidence-scorer skill assigns calibrated confidence estimates to agent outputs by analyzing factors like source quality, consistency, and reasoning depth. Use it when you need to assess output reliability via triggers like "confidence score" or "how confident." It's designed to pair with other DAG skills for quality control, not for validation or hallucination detection.
Quick Install
Claude Code
Recommendednpx skills add majiayu000/claude-skill-registry -a claude-code/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/dag-confidence-scorerCopy and paste this command in Claude Code to install this skill
GitHub Repository
Related Skills
Verification & Quality Assurance
OtherThis skill provides automated quality verification for code and agent outputs using truth scoring and quality checks. It automatically rolls back changes that fall below a 0.95 accuracy threshold, ensuring codebase reliability. Use it for CI/CD integration and maintaining high-quality standards in development workflows.
Verification & Quality Assurance
OtherThis skill provides automated verification and quality assurance for code and agent outputs, including truth scoring and validation checks. It enables automatic rollback for failed quality checks and integrates with CI/CD pipelines. Use it to validate code changes before merging or to ensure the correctness of generated outputs.
testability-scoring
OtherThis skill provides AI-powered testability assessment for web applications using Playwright and optional Vibium integration. It evaluates applications against 10 intrinsic testability principles like Observability and Controllability to identify improvement areas. Use it when assessing software testability, evaluating test readiness, or generating testability reports.
quick-quality-check
TestingQuick Quality Check runs parallel command execution for lightning-fast code quality feedback in under 30 seconds. It simultaneously performs theater detection, linting, security scans, and basic tests, aggregating results by severity. Use this skill for instant, actionable feedback during rapid development cycles in Claude Code.
