AI Agent Skill: Done-Check for Code Verification

AI Agent Skill: Done-Check for Code Verification

The AI Agent Skill: Done-Check for Code Verification supports developers and teams in ensuring code tasks are thoroughly verified before being deemed complete. It generates a verification report accompanied by evidence, helping users to confirm task completion confidently.

What this skill does

Done-Check for Code Verification performs a structured series of checks to prevent false completion scenarios. The process includes:

• Defining completion criteria: Summarizes the original task completion criteria in a concise statement. If criteria are unclear, the process halts for clarification.
• Running existing tests: Locates and executes tests outlined in files such as package.json, Makefile, or CI settings. Outputs the last 10 lines for validation. Declares if no tests are available.
• Executing a manual happy path: Verifies core functionality by executing real commands (e.g., using curl) and includes actual output evidence.
• Testing at least two edge cases: Checks scenarios like empty input or non-existent files and records expected versus actual outcomes.
• Checking for new warnings or errors: Reviews outputs from previous steps to ensure no new issues are present.
• Reviewing code differences (diff): Utilizes git diff --stat to ensure no debug code or unrelated changes are present, and that the scope is appropriate for the task size.
• Final critical assessment: Encourages reflection on whether a senior engineer would approve the code change, documenting any hesitations.

Who it is for

This skill is designed for developers and development teams using AI coding agents like Claude Code, Cursor, or Codex. It benefits those seeking consistency and thoroughness in code validation workflows.

Use cases

• Development teams implementing CI/CD pipelines requiring structured pre-commit verification.
• Individual developers aiming to enhance the robustness of their coding practices.
• Project managers or team leaders requiring detailed reporting before code merges.

Technical details

The skill integrates with tools such as git and various testing frameworks, leveraging configuration files like package.json and CI tools. It fits seamlessly within environments using AI solutions like Claude Code, Cursor, and Codex.

Source & Licence

This package is built on open-source work published by curtischoutw (curtischoutw/claude-institution) 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.