A sophisticated code review skill that employs multiple parallel subagents to identify bugs, security flaws, and best practice violations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install iterative-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 iterative-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 Iterative Code Review?
The Iterative Code Review skill is designed to provide professional-grade code analysis by leveraging independent subagents. It operates in a structured, round-based format where different AI personas focus on specific domains: functional correctness, code quality, and security. As part of the Openclaw Skills ecosystem, it ensures high standards of code integrity by simulating a multi-developer peer review process.
By default, the skill operates in Safety Mode, requiring explicit user confirmation for every identified issue and suggested fix. However, it can be configured for high-velocity environments with automated fixing and continuation capabilities, making it a versatile tool for both critical production systems and rapid prototyping.
Iterative Code Review Use Cases
- Reviewing complex Pull Requests or individual code files.
- Automating code quality checks in localized development environments.
- Identifying deep-seated security vulnerabilities and edge cases through parallel analysis.
- Ensuring functional correctness and test coverage before merging changes.
- Scaling code review processes using Openclaw Skills subagents.
How Iterative Code Review Works
- Pre-flight Checks: The skill confirms model selection, validates the maximum spawn depth, and assesses the scale of changes.
- Parallel Reviewing: Three independent subagents analyze the code simultaneously, focusing on functional correctness, quality/best practices, and security.
- Problem Aggregation: Issues are collected and ranked by severity (P0 to P3).
- User Confirmation: The user reviews the aggregated report and decides whether to proceed with fixes.
- Automated Fixing (Optional): If approved or configured for autoFix, a dedicated subagent applies the necessary code changes.
- Iterative Loops: The process repeats for up to 10 rounds or until no significant issues remain for two consecutive rounds.
- Final Validation: A mandatory 'Full Review' round is executed, including build and test verification (e.g., npm test) to ensure total system stability.
Iterative Code Review Setup
To integrate this review capability into your Openclaw Skills workflow, ensure you have the required CLI tools installed.
# Ensure dependencies are met
# Required: git, gh (GitHub CLI), jq, node/npm
# Clone or download the skill into your openclaw environment
# Configure optional automation in references/automation.md
# Set severity thresholds and maxRounds (default 10)
Iterative Code Review Data Schema & Taxonomy
The skill organizes review data and results using a structured taxonomy to maintain history and avoid duplicate findings.
| Data Component | Description |
|---|---|
| Review Rounds | Metadata tracking the history of each review iteration. |
| Issue Severity | Categorization from P0 (Critical) to P3 (Low). |
| Review Modes | Supports 'Full Review' (complete scan) and 'Delta Review' (changes only). |
| PR History | Log of previously identified and fixed issues to prevent regression. |
| Exit Criteria | Boolean logic based on round count and severity threshold. |
Iterative Code Review Advanced Features
- Multi-Agent Orchestration: Spawns three distinct reviewer subagents to maximize problem discovery.
- Automation Mode: Optional support for
autoFixandautoContinuefor hands-off code refinement. - Full Spectrum Validation: Final round mandatory
npm run buildandnpm testverification. - PR History Intelligence: Uses past review data to avoid re-reporting issues that have already been addressed.
- Customizable Thresholds: Adjustable severity levels and max spawn depths for flexible Openclaw Skills integration.
SKILL.md
Loading
Related Openclaw Skills
Drama Generator
An automated system that transforms written scripts into professional short-form drama videos with multi-character AI voices and cinematic transitions.
AkShare Stock Market Analysis
A comprehensive quantitative analysis tool for the A-share market that retrieves stock quotes, financial reports, and sector data using the AkShare library.
AI Competitive Competitor Analyzer
An automated intelligence framework designed to generate professional-grade competitive analysis reports with high ROI.
Magic Image2Video
A professional AI video generation skill that converts text descriptions and static images into dynamic video content via remote API integration.
moses-roles
A multi-agent governance skill that enforces a strict response hierarchy and sequencing between Primary, Secondary, and Observer agents.
Prospect Research
An advanced intelligence-gathering skill that builds comprehensive pre-meeting briefs on companies and decision-makers.
Featured*
