Skip to main content
skill CX Codex

Verification & Quality Assurance — Claude Code skill

Verification & Quality Assurance is a Claude Code skill that checks code and agent outputs with reliability scores (0–1.0), reverting failed changes.

no license ★ 850 updated 2026-10-26

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ruvnet/agentic-flow --skill 'verification-&-quality-assurance' -a claude-code
Open on GitHub

What Verification & Quality Assurance does

The system evaluates code across five categories: syntax and logic correctness, adherence to best practices and SOLID principles, vulnerability and secret detection, algorithmic complexity and memory patterns, and documentation completeness. Default threshold is 0.95: pass means production-ready, fail triggers a rollback to the last known good state. Rollback executes in under one second using git; you can roll back only corrupted files while preserving good changes.

Outputs metrics in table format, JSON for CI/CD pipelines, or HTML with charts. Watch mode tracks changes live, and time windows (hour, day, week) narrow the data slice. Requires Node.js 18+, a git repository, and Claude Flow (npx claude-flow@alpha).

What it helps with

  • verify code quality before committing
  • find files that failed security checks
  • revert recent changes if they broke tests
  • track agent reliability trend over a day or week
  • export metrics to a CI/CD pipeline

Example prompts for the agent

  • Show current reliability scores for all files
  • Check src/app.js and rollback if the score is below 0.98
  • Run verification in watch mode and export metrics every hour

How to install Verification & Quality Assurance

1Skills CLI (Vercel)

npx skills add ruvnet/agentic-flow --skill 'verification-&-quality-assurance' -a claude-code

2Manually: put the files in place

~/.claude/skills/verification-quality/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/verification-quality/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about Verification & Quality Assurance

How do I install Verification & Quality Assurance in Claude Code?

Run npx skills add ruvnet/agentic-flow --skill verification-quality -a claude-code, then open ~/.claude/skills/verification-quality/SKILL.md. You need Node.js 18+ and a git repository.

What does this skill do?

It checks code for correctness, security, best practices, performance, and documentation, assigns a reliability score from 0 to 1.0, and reverts changes that fall below the threshold (default 0.95).

What is the default threshold, and can I change it?

The default is 0.95. You can set a custom threshold using the --threshold flag, for example npx claude-flow@alpha verify check --threshold 0.98 for stricter validation.

Similar skills

All skills for Code review and refactoring →

From the same set76

The whole set →
performance-optimizer The performance-optimizer subagent finds system bottlenecks and helps tune resource distribution, load balancing, and computational performance. CX Codex ★ 850repo stars pseudocode A subagent for the Pseudocode stage of SPARC: it turns a finished spec into an algorithm draft and works out the complexity. CX Codex ★ 850repo stars context-synthesizer context-synthesizer synthesizes multidimensional context across task constraints, domain patterns, and past execution memory. Helps maintain clear situational awareness during complex execution. CX Codex ★ 850repo stars pattern-matcher The pattern-matcher subagent breaks down tasks, finds related solutions in ReasoningBank, and adapts them to a new context. CX Codex ★ 850repo stars memory-optimizer memory-optimizer is a Claude Code, Codex, and Cursor subagent that merges similar ReasoningBank memories and removes stale or conflicting patterns. It also checks memory quality. CX Codex ★ 850repo stars sync-coordinator sync-coordinator coordinates version alignment, cross-package dependencies, and documentation updates across multiple repositories using an agent swarm. CX Codex ★ 850repo stars reasoning-optimized The reasoning-optimized subagent selects a reasoning strategy based on the task and coordinates five specialist agents. Use it when a task calls for context synthesis, pattern reuse, or curation of results. CX Codex ★ 850repo stars experience-curator experience-curator — a Claude subagent that screens finished task runs and keeps only verified lessons in ReasoningBank memory. CX Codex ★ 850repo stars

Project sponsors

Companies that keep this analytics open