double-check

An easy way to force agent to think again if it's statement that the "Job is done and production ready" is actually done - usually it's not. This skill ensures that that the AI agent verifies their task and user does not have to check after the agent if they did their job.

⭐5stars🔀1forks📁View on GitHub🕐Updated Jan 11, 2026

When & Why to Use This Skill

The Double-Check skill implements a rigorous self-verification protocol for AI agents, ensuring that tasks are truly production-ready before final delivery. By forcing the agent to pause, redefine 'completion' in context, and evaluate its work from multiple angles, it significantly reduces hallucinations and the need for manual user oversight in complex workflows.

Use Cases

  • Software Development: Automatically auditing generated code or refactors to ensure they meet all functional requirements and edge cases before the agent claims the job is done.
  • Test Validation: Ensuring that newly created or fixed test suites are actually executed and passing, using successful execution as the primary metric for task completion.
  • Quality Assurance: Performing a 'deep-think' review of complex tasks to verify that the final output aligns perfectly with the original user intent and project goals.
  • Error Reduction: Preventing premature task termination by requiring the agent to approach the solution from different perspectives to identify potential flaws.
namedouble-check
descriptionAn easy way to force agent to think again if it's statement that the "Job is done and production ready" is actually done - usually it's not. This skill ensures that that the AI agent verifies their task and user does not have to check after the agent if they did their job.

When to use

  • After a task is completed and before reporting completion details to the user
  • After generating tests
  • After fixing tests

Skill

Please double check your work and what you generated.

  • Is it really complete?
  • Did you approach it from different angles?

Define first at what angles you can approach it. Reiterate on the goal and what it means and what is required to achieve it. Define what "complete" means in this context.

If the task was to generate tests or fix failing tests, run the tests to make sure they are successful. This is the only definition for "complete"

Proceed with the double check only after you are sure you have done all of the above.

Ultrathink!