DocGrad: AI-Powered Documentation Audit & Improvement Tool

DocGrad: AI-Powered Documentation Audit & Improvement Tool

DocGrad is an AI-powered tool designed to audit, grade, and improve a repository's documentation, ensuring it meets targeted quality standards. By evaluating documentation through a six-dimension star rating system—completeness, correctness, freshness, linkage, consistency, economy—DocGrad assists in systematically enhancing documentation quality until specified benchmarks are achieved.

What this skill does

• Audits and scores documentation across six dimensions: completeness, correctness, freshness, linkage, consistency, and economy.
• Conducts a comprehensive documentation health check, identifying issues such as dead links, orphaned content, or outdated information.
• Facilitates a continuous improvement loop, progressively enhancing documentation until target ratings are met.
• Converges documentation systems to serve as context sources for AI agents like Claude Code, Cursor, and Codex.

Who it is for

• Developers seeking to ensure high-quality documentation in AI-powered environments.
• Teams using AI coding agents like Claude Code, Cursor, and Codex who require robust documentation systems.
• Individuals responsible for maintaining and improving project documentation quality in local markdown file trees.

Use cases

• Regularly auditing and grading project documentation to maintain high standards in collaborative environments.
• Assisting development teams in identifying and rectifying documentation issues before they impact AI coding agent performance.
• Improving legacy documentation systems to meet modern AI agent integration requirements.

Technical details

• Requires documentation formatted as local markdown file trees; incompatible with wikis and remote documentation sources.
• Stores configurations using a `.docgrad.yml` file in the target repository root.
• Does not include prose style linting or code review functionalities, focusing solely on documentation quality metrics.

Source & Licence

This package is built on open-source work published by redtear1115 (redtear1115/docgrad) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.