review-code-and-pr — review-code-and-pr install review-code-and-pr, gostructure, community, review-code-and-pr install, ide skills, review-code-and-pr for Go developers, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Code Review Agents needing structured analysis and feedback generation for pull requests. review-code-and-pr is a template repository for initiating Go services, emphasizing separation of business logic and infrastructure for enhanced testability and maintainability.

Features

Separates business logic code from infrastructure for easier testing and modification
Includes common boilerplate files for streamlined development
Outputs review verdicts in a structured format, including APPROVE or REQUEST_CHANGES
Provides a summary of changes and how they meet review criteria
Lists blockers that must be resolved before merging

# Core Topics

daominah daominah
[0]
[0]
Updated: 3/7/2026

Agent Capability Analysis

The review-code-and-pr skill by daominah 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. Optimized for review-code-and-pr install, review-code-and-pr for Go developers.

Ideal Agent Persona

Perfect for Code Review Agents needing structured analysis and feedback generation for pull requests.

Core Value

Empowers agents to provide detailed code reviews using standardized templates, including verdicts, summaries, blockers, suggestions, and nitpicks, all while leveraging output formats like JSON for seamless integration with development workflows.

Capabilities Granted for review-code-and-pr

Standardizing code review processes
Automating pull request feedback generation
Improving code quality through structured analysis

! Prerequisites & Limits

  • Requires access to code repositories
  • Limited to Go services and infrastructure
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-code-and-pr

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

SKILL.md
Readonly

Output Format

Output the review with these sections in order:

  • Verdict: APPROVE or REQUEST_CHANGES.
  • Summary: one paragraph describing what the change does and how it meets the review criteria.
  • Blockers: issues that must be resolved before merging. Only present when verdict is REQUEST_CHANGES.
  • Suggestions: improvements worth tracking as follow-ups. Not blocking: the PR still solves the business need without them.
  • Nitpicks: minor observations that do not affect correctness or functionality.

Omit Blockers, Suggestions, and Nitpicks if they have no items.

Review Criteria

Code Meets Business Need

  • The PR must link to its ticket (Linear/Jira), Slack thread, plan, etc. if not linked: ask to link as a blocker.
  • Verify the PR describes the client pain point or use case being solved.
  • Verify the sources (ticket, report message, plan) are clear, self-consistent, and consistent with each other.
  • For bugs: check whether we know how to reproduce it, How confirmed the root cause, is there a test that reproduces the bug. if not: blocker. Optional: symptom of a deeper issue? Check similar past bugs.

Code Works as Intended

  • Every new, modified, or affected function must have a test proving it works.
  • For bug fixes: a test that reproduces the bug and passes after the fix.
  • For new features: tests must cover the main use case. Edge cases are optional but encouraged.
  • Test comments use GIVEN (precondition) / WHEN (action) / THEN (result) to describe business behavior, readable by non-technical stakeholders.

Do Not Break Existing Behavior

  • Existing tests may not cover all behaviors. Check for changes that could break untested code paths.
  • Purely additive changes can still degrade performance. Check for slow queries, missing indexes, or unnecessary load on shared resources.
  • If the PR is too large to review confidently, note it as process feedback to prefer smaller PRs in future work.

Observable Output

  • Check that the change has observable output the user can verify, for example through the UI or a public API response.
  • Long-running functions or background jobs provide a way to inspect progress through metrics, a dashboard, a status endpoint, logs, or database records.
  • Support for cancellation is a nice to have.

Security Considerations

  • Check for hardcoded secrets, credentials, or real customer data in the code.
  • Review risks from user inputs: is validation sufficient?
  • Check if the change exposes sensitive data in API responses or error messages.

Code Quality

  • Code should be easy to read, change, and debug by someone who didn't write it.
  • Improve the codebase where you touch it. Keep cleanup in separate commits from feature work for easier review and revert.
  • Label nitpicks clearly so the author knows what is blocking vs optional.

Process Feedback

If the review finds serious problems, such as vague requirements that led to solving the wrong need, contradictory source materials, or the wrong approach, add recommendations to prevent similar issues in future work:

  • Requirements should be clear and agreed on before coding starts.
  • The solution approach should be confirmed before implementation.
  • This prevents misalignment earlier in future work.

FAQ & Installation Steps

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

? Frequently Asked Questions

What is review-code-and-pr?

Perfect for Code Review Agents needing structured analysis and feedback generation for pull requests. review-code-and-pr is a template repository for initiating Go services, emphasizing separation of business logic and infrastructure for enhanced testability and maintainability.

How do I install review-code-and-pr?

Run the command: npx killer-skills add daominah/gostructure/review-code-and-pr. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for review-code-and-pr?

Key use cases include: Standardizing code review processes, Automating pull request feedback generation, Improving code quality through structured analysis.

Which IDEs are compatible with review-code-and-pr?

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-code-and-pr?

Requires access to code repositories. Limited to Go services and infrastructure.

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 daominah/gostructure/review-code-and-pr. 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-code-and-pr immediately in the current project.

Related Skills

Looking for an alternative to review-code-and-pr 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