Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mohitagw15856/code-review-checklist
Generate a tailored code review checklist for any pull request based on the language, type of change, and risk level.
Passed 15 of 22 test cases with the skill, and 6 of 22 without it.
and 8 more in the full report
9 fixed6 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need a tailored code review checklist for a Python and FastAPI backend pull request. The PR adds a new payment integration feature and is considered medium risk. Could you give me an evaluation with a time estimate, language-specific correctness points, feature-specific checks, risk considerations, test coverage validation, an approval or rejection framework, and potential traps to watch out for?
| Checked | Without skill | With skill |
|---|---|---|
| Includes Python-specific checks for asynchronous endpoint execution. | Passed | Passed |
| Includes risk considerations for rollback procedures. | Missed | Passed |
| Specifies conditions required for approving the pull request. | Passed | Passed |
The instructions your model reads when the skill loads.
Produce una lista de verificación de revisión de código personalizada para una solicitud de cambios específica — escalada al lenguaje, tipo de cambio y nivel de riesgo. No es una plantilla genérica.
Solicita al usuario estos datos si no los proporciona:
git diff; mejora significativamente la especificidad de la lista)Evaluación del alcance: [Pequeño / Medio / Grande / Demasiado grande — debería dividirse] Profundidad de revisión recomendada: [Rápida / Estándar / Profunda] Tiempo estimado de revisión: [p. ej. 20–30 min — usa aproximadamente 5 min por cada 50 líneas de diff como guía]
Comprobaciones de corrección específicas del lenguaje — elige según el lenguaje indicado:
Para TypeScript/JavaScript:
any implícito en código de no-pruebaPara Python:
test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.