Material Review is a specialized AI agent skill designed to audit data sharing catalogs and ensure consistency between documentation and platform records.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install material-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 material-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 Material Review?
Material Review serves as an intelligent audit assistant for data sharing lists and catalog verification. It streamlines the review of submission materials against standardized templates, focusing on field completeness, platform consistency, and rule compliance. By bridging the gap between static documentation and live system data, it ensures that every shared data resource is accurately cataloged and ready for operational use.
Built as a component of the Openclaw Skills ecosystem, this tool helps organizations maintain high-quality data governance. It rigorously checks business-related data tables, filters out irrelevant logs or configuration files, and provides actionable feedback for any discrepancies found during the six-step audit process.
Material Review Use Cases
- Reviewing Data Sharing Lists during trial operation phases to ensure all mandatory fields are populated.
- Verifying platform consistency by comparing document submissions against actual system entries.
- Generating traceable issue lists for data providers to correct errors in their submissions.
- Filtering business data tables from administrative or log-heavy databases to reduce maintenance overhead.
How Material Review Works
- Scope Confirmation: Identifies the audit boundaries, system names, and contact information while ensuring the correct template version is used.
- Field Completeness Check: Validates that all mandatory fields (excluding remarks) are filled and checks for common omissions like system launch dates.
- Special Rule Validation: Applies specific logic to high-frequency rejection items, such as data increment rules and Chinese description requirements.
- Data Table Screening: Filters out non-business tables (logs, configs) and marks empty tables for deletion or confirmation.
- Platform Consistency Verification: Cross-references materials with the live platform to identify mapping errors or outdated entries.
- Issue List Generation: Outputs a categorized report including the location of the error, the rule violated, and specific corrective actions.
Material Review Setup
To use the automated audit capabilities, ensure you have the required dependencies and run the provided Python script:
# Install required dependencies
npm install -g markdownlint-cli2
# Execute the material review audit script
python material-review/scripts/material_review_audit.py \
--submission "pending_material.docx" \
--template "material-review/data_sharing_template.docx" \
--rules "material-review/audit_rules.docx" \
--output-dir "material-review/output"
Material Review Data Schema & Taxonomy
The skill organizes its audit results into a structured directory for easy tracking and reporting:
| File Name | Description |
|---|---|
structured_data.json |
The extracted, structured version of the raw submission data. |
issues.json |
A machine-readable list of all identified audit issues. |
audit_report.md |
A human-readable Markdown report ready for distribution to stakeholders. |
All issues are indexed by field name, table name, or system name for precise traceability.
Material Review Advanced Features
- Traceable Issue Mapping: Every issue generated includes the specific location, current status, rule basis, and a correction suggestion.
- Multi-step Automated Workflow: Integrated Python scripts convert unstructured documents into structured JSON data for deep analysis.
- Platform Cross-Referencing: Built-in logic to detect discrepancies between documentation and live backend/frontend system data.
- Incremental Data Logic: Advanced rules that trigger mandatory field requirements only when specific data volume thresholds (e.g., >10,000 records) are met.
SKILL.md
Loading
Related Openclaw Skills
Movie Search
An AI agent skill to search and retrieve Baidu and Quark cloud storage links for various multimedia content.
Kingpeng Intelligent Vehicle Diagnostics
A comprehensive diagnostic and management tool for Kingpeng intelligent three-wheelers powered by Openclaw Skills.
uhomes Student Housing Skill
An AI-powered skill designed to find and compare verified international student housing exclusively via the uhomes platform.
Link Checker
A high-performance CLI utility for auditing web pages to detect broken links, track redirects, and monitor URL health via automated status checks.
OpenBook
An open-source platform for recording and searching real-time, structured observations about physical businesses and locations.
TRON Account Profiling
A comprehensive analytical tool for profiling TRON addresses, covering assets, resources, staking, and on-chain behavior.
Featured*
