A technical protocol for AI agents to process code review feedback through rigorous verification and evidence-based implementation rather than blind agreement.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install receiving-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 receiving-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 Receiving Code Review?
The Receiving Code Review skill is designed to transform how AI agents interact with feedback by enforcing a framework of technical rigor. Instead of providing performative or polite responses like "You're absolutely right," the agent follows a strict verification cycle to ensure that every suggested change is technically sound for the specific codebase. This Openclaw Skills implementation ensures that agents maintain high coding standards by checking for regressions, verifying platform compatibility, and questioning suggestions that lack context.
By prioritizing technical correctness over social comfort, this skill prevents the common pitfall of AI agents implementing incorrect or unnecessary code simply because a reviewer suggested it. It integrates deeply with development workflows to ensure that every action taken is deliberate, tested, and aligned with the project's architectural goals.
Receiving Code Review Use Cases
- Processing feedback from human partners on active Pull Requests.
- Evaluating suggestions from external automated reviewers or third-party security audits.
- Handling ambiguous or multi-part feedback where partial understanding could lead to errors.
- Managing technical pushback when suggested changes conflict with existing codebase constraints or YAGNI principles.
How Receiving Code Review Works
- Read the entire feedback block thoroughly without providing an immediate reaction.
- Understand and restate the technical requirement in the agent's own words to confirm alignment.
- Verify the suggested changes against the live codebase to ensure they are applicable and won't break existing features.
- Evaluate the suggestion based on the specific stack, platform versions, and project context.
- Respond with a technical acknowledgment or a reasoned pushback supported by code evidence.
- Implement verified items one by one, performing individual tests for each fix to prevent regressions.
Receiving Code Review Setup
To integrate this protocol into your agent's workflow, include the markdown definition in your project's instruction set or skill library.
# Example of adding the skill to an AI-ready project
mkdir -p .ai/skills
cp receiving-code-review.md .ai/skills/
Receiving Code Review Data Schema & Taxonomy
The skill organizes feedback processing into a structured hierarchy to ensure systematic implementation:
| Priority | Type | Description |
|---|---|---|
| 1. Blocking | Security/Breaking | Critical issues that prevent the application from running or compromise data. |
| 2. Simple | Typos/Imports | Low-risk changes that improve code cleanliness without altering logic. |
| 3. Complex | Refactoring/Logic | Significant architectural changes that require deep testing and verification. |
It also utilizes specific response templates to avoid performative language and maintain a technical tone.
Receiving Code Review Advanced Features
- Source-Aware Logic: Differentiates between trusted human partners and external reviewers to adjust skepticism levels.
- Automated YAGNI Verification: Automatically greps the codebase to check if suggested "professional" features are actually utilized before implementation.
- GitHub Thread Integration: Supports direct replies to specific comment IDs via the GitHub API to maintain conversation context.
- Architectural Signaling: Includes specific phrases to signal discomfort with architectural decisions that might require human intervention.
- Multi-Item Dependency Check: Prevents partial implementation of multi-step feedback to ensure consistency across the codebase.
SKILL.md
Loading
Related Openclaw Skills
Executing Plans
A systematic protocol for AI agents to execute complex implementation plans through batch processing and mandatory review checkpoints.
RAGFlow Knowledge Base Q&A
An AI-driven skill that integrates RAGFlow Knowledge Base APIs to provide technical answers and actionable system operations guidance.
World Room
A real-time 3D virtual environment where AI agents collaborate as animated avatars using Nostr-backed communication.
A-Share Real-time Market Monitor & Technical Analysis
A comprehensive A-share monitoring skill offering real-time data, advanced technical analysis, and smart investment advisory without the need for API keys.
Mood Sticker
An intelligent emotion-sensing skill that enables AI agents to autonomously share relevant stickers and memes based on conversation context.
App Legal Pages
Automate the creation and deployment of professional Privacy Policy and Terms of Service static sites directly from your app feature documentation.
Featured*
