A dedicated quality assurance and peer review agent that validates the output of other AI agents to ensure accuracy, style compliance, and brand consistency.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install checker
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 checker 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 Checker?
Checker is an essential component of the Openclaw Skills ecosystem, acting as the final gatekeeper before any AI-generated deliverable is finalized or published. It is specifically engineered to perform deep-dive peer reviews on content, research, outreach, and imagery produced by other agents. By applying rigorous checklists and severity levels, Checker ensures that no output is delivered with factual errors, style deviations, or 'hallucinated' links.
This skill focuses exclusively on evaluation rather than creation. It identifies issues like 'AI-cringe', brand inconsistencies, and missing citations, providing actionable fixes for the original creator agent to implement. Integrating Checker into your multi-agent architecture adds a professional layer of accountability and quality control that is critical for high-stakes digital operations.
Checker Use Cases
- Validating blog posts and social content from Scribe for voice and style compliance.
- Auditing research reports from Scout to ensure all claims are backed by valid, recent sources.
- Proofing outreach DMs and emails to verify personalization and low-friction calls to action.
- Checking AI-generated images from Pixel for character recognition and platform-specific dimensions.
- Performing pre-delivery QA to block deliverables containing broken links or factual inaccuracies.
How Checker Works
- The agent receives output or a draft from another active agent within the Openclaw Skills framework.
- It automatically selects the appropriate review checklist based on the input type (Content, Research, Outreach, or Image).
- Checker executes a systematic audit, evaluating every item from style compliance to technical accuracy.
- A standardized verdict report is generated, highlighting specific issues with exact locations and required fixes.
- The review is assigned a severity level such as BLOCK for critical errors or FIX for style improvements.
- The final verdict is saved to the workspace artifacts and reported to the orchestrator for next steps.
Checker Setup
To deploy Checker within your environment, ensure the workspace artifact directory is prepared. Use the following command to initialize the required directory structure:
mkdir -p /home/ubuntu/.openclaw/workspace/artifacts/checker/
Once the directory is ready, the skill can be invoked by your agent orchestrator to review outputs generated by Scribe, Scout, or Pixel.
Checker Data Schema & Taxonomy
Checker maintains a structured repository of all quality audits to ensure transparency and traceability in the Openclaw Skills workflow.
| Feature | Specification |
|---|---|
| Storage Path | /home/ubuntu/.openclaw/workspace/artifacts/checker/ |
| File Naming | review-[source-agent]-[topic]-[YYYY-MM-DD].md |
| Verdict Types | APPROVED or NEEDS REVISION |
| Metadata | Source agent, review date, and deliverable type included in every header |
Checker Advanced Features
- Severity-based blocking system (BLOCK, FIX, NOTE) to prioritize mission-critical revisions.
- Specialized brand consistency checks, including character recognition for visual assets.
- Actionable fix requirements that provide specific instructions rather than vague suggestions.
- Binary verdict system ensures there are no ambiguous 'maybe' statuses in the delivery pipeline.
- Integration-ready for Cello reporting to automate the feedback loop between agents.
SKILL.md
Loading
Related Openclaw Skills
Zhipu Search Skill
A high-performance AI agent skill that integrates Zhipu's web search API to provide real-time internet data and news.
Zhipu Web Search Embeddings
A high-performance skill that enables AI agents to search the live web and retrieve real-time information via the Zhipu API.
Zhipu Image Generation
A high-performance AI image generation skill leveraging the Zhipu AI CogView-4 model via a secure Bash interface.
Test Case Generator
An AI-powered utility that automatically generates complete unit test files, including imports, mocks, and assertions, from existing source code.
Clickbait Engine
A high-performance engagement engine designed to transform content into viral, click-worthy titles and hooks using proven social media psychological triggers.
Font Interceptor
Extract and download TTF or OTF font files from any website automatically using MSCHF Font Interceptor.
Featured*
