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.
When & Why to Use This Skill
The 'double-check' skill acts as a critical quality assurance layer for AI agents, preventing premature task completion claims. It forces the agent to rigorously verify its own output, define 'completeness' in context, and approach problems from multiple angles to ensure that 'production-ready' work is truly functional and reliable.
Use Cases
- Software Development: Automatically verifying that generated code or bug fixes pass all relevant tests before the agent reports the task as finished.
- Quality Control: Ensuring that complex, multi-step instructions have been fully executed without skipped steps or hallucinations.
- Test Validation: Forcing the agent to run and confirm the success of newly generated test suites to guarantee code coverage and reliability.
- Edge Case Analysis: Prompting the agent to re-evaluate its solution from different perspectives to identify potential logic flaws or missing requirements.
| name | double-check |
|---|---|
| description | 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. |
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!