Score project artifacts against a confidence rubric and return PASS/WARN/BLOCK JSON results.
npx skills add https://github.com/vTRKA/supervibe --skill confidence-scoring
Please help me install this Agent Skill. Skill: confidence-scoring Source: https://github.com/vTRKA/supervibe/tree/main/skills/confidence-scoring Command: npx skills add https://github.com/vTRKA/supervibe --skill confidence-scoring
It prevents AI coding workflows from progressing on artifacts that lack verifiable evidence by scoring outputs against a rubric and enforcing confidence gates.
evidence-found plus explicit gaps and remediation steps for missing proof.Have your AI call the scoring command in chat to score a specific artifact type and path, then use the returned status to decide whether to proceed.
High-intent search queries and answers about installing and using this skill.
You gate AI coding workflows by scoring project artifacts against a confidence rubric to prevent unsupported claims. This process enforces workflow gating by returning a PASS, WARN, or BLOCK status based on computed weighted dimensions.
Rubric validation for agent outputs is a scoring mechanism that evaluates artifacts against evidence-required criteria. It produces a numeric score and returns explicit gaps plus remediation steps for missing proof.
You automate decision gating by applying threshold logic to rubric scores during review-phase exits. This converts the computed scores into PASS, WARN, or BLOCK JSON results to safely control workflow progression.
Yes, confidence scoring works without external dependencies. It operates independently by loading the matching rubric, reading the artifact and optional prior confidence log, then computing weighted dimension scores.
You should use evidence verification to block workflow progression whenever AI coding outputs lack required receipts, commands, or proofs. This ensures durable progress claims are only allowed when verifiable evidence is present.
FVossebeldAutomate LLM output evaluation with scoring, pairwise comparisons, and bias mitigation.
jaskaranhundalAnalyze CI/CD security findings and recommend gate actions and remediation steps.
Emz1998Generate interactive single-file HTML prototypes from UX specifications.
OneWave-AIReview code for security vulnerabilities, performance bottlenecks, and maintainability issues.