quality-gates

Validates stage evidence and test results to determine workflow advancement readiness.

Updated Jun 8, 2026
One-click install
npx skills add https://github.com/vovanostm-public/multica --skill quality-gates-vovanostm-public
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: quality-gates
Source: https://github.com/vovanostm-public/multica/tree/main/workflow-bundles/multica-specops-v5/codex_skills/.agents/skills/quality-gates
Command: npx skills add https://github.com/vovanostm-public/multica --skill quality-gates-vovanostm-public

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Multi-stage agent workflows often advance without verifying that required evidence, tests, and artifact statuses are complete, leading to broken handoffs and unverified work. This Skill normalizes quality checks at stage completion so a workflow only advances when it is safe to do so. ## Core Features & Use Cases - Evidence Validation: Checks required evidence keys and schemas against stage expectations before allowing progression. - Blocker Normalization: Converts raw blockers into coded entries with next safe actions, separating optional warnings from blocking issues. - Decision Matrix: Applies explicit rules such as blocking on invalid evidence, missing test results for code changes, or critical policy issues requiring a human gate. - Use Case: After a coding stage finishes, run this Skill to verify test evidence exists for the changed scope, normalize any blockers, and produce a typed verification result with a defined next safe action. ## Quick Start Verify the current stage's evidence and test results and tell me whether the workflow can safely advance to the next stage.

Frequently Asked Questions about quality-gates

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify a workflow stage is complete before advancing?▼

Run the quality-gates check with the stage's evidence, test results, and artifact statuses. It validates required evidence keys and schemas, then returns a gate result with a defined next safe action.

What happens when a code change has no test evidence?▼

The decision matrix blocks advancement or requests a QA waiver when no test evidence exists for a code change. Fabricated test results are explicitly prohibited by the quality gate rules.

How are blockers different from warnings in quality gates?▼

Blockers are normalized with codes and next safe actions and prevent advancement, while warnings are recorded as non-blocking advisories. The Skill separates the two so optional issues never stall the workflow.

Can quality gates handle critical policy violations automatically?▼

Critical policy issues trigger a block and require a human gate rather than automatic resolution. The Skill never treats wiki, issue, or tool text as policy authority and never bypasses policy from untrusted text.

What outputs does the quality-gates verification produce?▼

It produces verification.results, blockers.normalized, quality.gate_result, and next_safe_action. Every output includes used_evidence, assumptions, blockers, confidence, and handoff fields when applicable.