Dovetail: AI Agent Skill for Repository Coherence Audits

Product Description

Dovetail is an AI Agent Skill designed for conducting repository coherence audits. It systematically checks whether a repository agrees with itself, identifying various discrepancies and issues such as broken links, orphaned files, duplicate content, and more.

What this skill does

• Conducts a thorough scan of the repository to find inconsistencies, utilizing Python for precise findings such as broken links and duplicate contents.
• Identifies both exact findings (computed in Python) and judged findings (evaluated by reviewers) covering contradictions, semantic staleness, and drift between specifications and code.
• Presents findings in a structured JSON format for further analysis, categorizing results into `findings`, `suppressed`, `counts`, `failed_checks`, `profile`, `file_count`, and `edge_count`.
• Ensures that findings are presented with clarity on whether they are exact or judged to support transparent auditing processes.

Who it is for

Dovetail is suitable for developers and teams utilizing AI coding agents such as Claude Code, Cursor, and Codex who are focused on ensuring the internal consistency and coherence of their code repositories.

Use cases

• Performing regular audits of code repositories to maintain documentation consistency with the actual code.
• Integrating into development workflows to ensure compliance with stated repository conventions.
• Assisting codebase management by identifying semantic drifts and outdated translations.

Technical details

• Compatible with Python to compute exact findings related to links, anchors, orphans, duplicates, and more.
• Employs a structured review process for judged findings to evaluate non-Python dead code and potential contradictions.
• Utilizes JSON format to present scan results, ensuring detailed output for further processing or integration into automated workflows.
• Operates without network dependency and does not modify the target repository, emphasizing secure and read-only evaluations.

For authorised security testing, defensive research and educational use only.

Source & Licence

This package is built on open-source work published by dbhq-uk (dbhq-uk/dovetail-skill) 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.