review-and-qa — community review-and-qa, monoblok, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for Code Review Agents needing comprehensive pull request analysis and quality assurance capabilities. The Storyblok OSS monorepo

storyblok storyblok
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The review-and-qa skill by storyblok is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Ideal for Code Review Agents needing comprehensive pull request analysis and quality assurance capabilities.

Core Value

Empowers agents to perform two-phase reviews, including code quality analysis and manual test case creation, ensuring adherence to best practices and validating behavior through protocols like PR checklists and test-driven development.

Capabilities Granted for review-and-qa

Automating code reviews for monorepo projects
Generating manual test cases for new functionality
Validating pull request compliance with required checklists

! Prerequisites & Limits

  • Requires access to code repositories
  • Limited to review of code changes, not full project audits
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

review-and-qa

Install review-and-qa, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Review Changes

Review the changes for: $ARGUMENTS.

Instructions

Perform a two-phase review:

  1. Code review - Review quality, architecture, and best practices.
  2. QA review - Create manual test cases to validate behavior.

Phase 1: Code review

Analyze the code changes for:

PR checklist

Required for all PRs

  • Small diff - One logical change. If the PR does multiple things, split it.
  • Tests included - New functionality has tests. Bug fixes have regression tests.
  • No secrets - No tokens, passwords, or credentials in the code.

If user-facing changes

  • Docs updated - The README or relevant documentation reflects the change.
  • Examples work - Code examples in the documentation are tested and copy-paste ready.
  • Error messages helpful - New errors explain what went wrong and how to fix it.

If breaking changes

  • Migration notes - Provide clear before and after examples showing how to upgrade.
  • Changelog entry - Follow conventional commits for release notes.
  • Deprecation warnings - If keeping an old API temporarily, warn users.

If adding dependencies

  • Justified - No existing solution exists in the codebase.
  • License compatible - Use MIT or a compatible license.
  • Maintained - Use an active project with recent updates.
  • Size reasonable - Avoid adding significant bundle weight.

Quality and clean code

  • Functions are small and single-purpose.
  • Variable and function names are descriptive.
  • No dead code or commented-out blocks exist.
  • No magic numbers exist (use constants).
  • Error messages are helpful.

Architecture and design

  • Changes fit existing patterns in the codebase.
  • No unnecessary coupling exists between modules.
  • Proper separation of concerns exists (actions vs. commands vs. utils).
  • Types and interfaces are defined appropriately.

Reusability and centralization

  • Duplicated logic is extracted to shared utilities.
  • Existing helpers are used where applicable.
  • New utilities are generic enough for reuse.
  • Constants are centralized (not scattered).

Best practices

  • Async and await are used consistently (no mixed patterns).
  • Errors are propagated correctly (not swallowed).
  • Edge cases are handled (null, empty, invalid input).
  • No security issues exist (injection, secrets exposure).

Output format (code review)

markdown
1## Code review summary 2 3[LGTM / Needs changes / Blocking issues] 4 5## Issues found 6 7### [Critical/Major/Minor]: Issue title 8 9**File:** `path/to/file.ts:123` 10**Problem:** Description. 11**Suggestion:** How to fix.

Phase 2: QA review

Test case structure

Refer to the Test Plan Template and the Test Plan Example for test plan structure guidance.

Coverage requirements

Create test cases for:

  1. Happy path - Normal successful operation.
  2. Negative cases - Invalid input, unauthorized access, and missing data.
  3. Edge cases - Empty input, large input, and special characters.
  4. Error recovery - What happens when things fail mid-operation.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is review-and-qa?

Ideal for Code Review Agents needing comprehensive pull request analysis and quality assurance capabilities. The Storyblok OSS monorepo

How do I install review-and-qa?

Run the command: npx killer-skills add storyblok/monoblok/review-and-qa. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for review-and-qa?

Key use cases include: Automating code reviews for monorepo projects, Generating manual test cases for new functionality, Validating pull request compliance with required checklists.

Which IDEs are compatible with review-and-qa?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for review-and-qa?

Requires access to code repositories. Limited to review of code changes, not full project audits.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add storyblok/monoblok/review-and-qa. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use review-and-qa immediately in the current project.

Related Skills

Looking for an alternative to review-and-qa or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI