A specialized skill for triggering automated subagent code reviews to ensure quality and requirement alignment during development.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install requesting-code-review
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install requesting-code-review using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Requesting Code Review?
This skill empowers developers using Openclaw Skills to maintain high code quality by automating the review process. By dispatching a dedicated code-reviewer subagent, it systematically evaluates new implementations against original requirements and best practices. It acts as a preventative gatekeeper, ensuring that technical debt and bugs are caught early in the development lifecycle rather than after deployment.
The core principle of this skill is to review early and often. By integrating an AI-driven reviewer into your daily workflow, you can catch cascading issues before they become deeply embedded in the codebase. Whether you are implementing a major feature or fixing a complex bug, this skill provides the structure needed to verify work objectively.
Requesting Code Review Use Cases
- Mandatory verification after each task in subagent-driven development cycles.
- Final audit before merging feature branches into the main production branch.
- Gaining a fresh perspective when stuck on a complex implementation or logic error.
- Establishing a technical baseline before performing major code refactoring.
- Verifying the integrity of a fix after resolving complex bugs.
How Requesting Code Review Works
- Identify the relevant Git SHAs to define the scope of the review (typically the difference between origin/main and your current HEAD).
- Dispatch the superpowers:code-reviewer subagent using the Task tool.
- Populate the code-reviewer.md template with context, including the implementation details and original requirements.
- Receive a structured assessment from the subagent highlighting strengths and categorized issues (Critical, Important, Minor).
- Remediate issues based on priority: fix Critical and Important issues immediately, and note Minor issues for future technical debt management.
Requesting Code Review Setup
To use this skill within Openclaw Skills, ensure your environment is configured for git-based tracking.
Before requesting a review, you must identify your commit range:
# Get the base SHA (e.g., the commit before your changes or origin/main)
BASE_SHA=$(git rev-parse HEAD~1)
# Get the current head SHA
HEAD_SHA=$(git rev-parse HEAD)
Ensure the code-reviewer.md template is present in your project directory to facilitate the subagent dispatch.
Requesting Code Review Data Schema & Taxonomy
The skill utilizes a structured template to provide context to the reviewer. The following metadata fields are required:
| Field | Description |
|---|---|
| WHAT_WAS_IMPLEMENTED | A detailed list of the features or logic built. |
| PLAN_OR_REQUIREMENTS | Reference to the design docs or task requirements. |
| BASE_SHA | The starting git commit hash for the diff. |
| HEAD_SHA | The ending git commit hash for the diff. |
| DESCRIPTION | A brief high-level summary of the changes. |
Requesting Code Review Advanced Features
- Subagent-Driven Development Integration: Automate reviews after every single task completion to prevent issue compounding.
- Batch Review Logic: Optimize workflows by reviewing groups of tasks (e.g., every 3 tasks) during plan execution.
- Technical Reasoning Protocols: Includes a framework for pushing back against AI feedback with code or tests if the reviewer's assessment is incorrect.
- Prioritized Remediation: Built-in classification of issues to ensure developers focus on Critical and Important blockers first.
SKILL.md
Loading
Related Openclaw Skills
Finishing a Development Branch
A structured workflow for finalizing development work, ensuring all tests pass before automating merges or pull request creation.
Dispatching Parallel Agents
A sophisticated orchestration pattern for running multiple AI agents concurrently to solve independent technical problems without shared state interference.
Brainstorming
A collaborative design skill that refines project ideas into structured technical specifications through iterative dialogue.
Philidor
An institutional-grade DeFi intelligence tool for analyzing vault risk, yields, and portfolios across multiple blockchain networks.
Subagent-Driven Development
A high-velocity execution framework that dispatches specialized subagents for independent tasks with automated two-stage reviews.
Using Git Worktrees
A specialized skill for creating and managing isolated Git workspaces with automated safety checks and environment setup.
Featured*
