Diagnose AI workflows across prompt quality, context efficiency, tool health, architecture fitness, and safety.
npx skills add https://github.com/voidrot/agents --skill diagnose-voidrot
Please help me install this Agent Skill. Skill: diagnose Source: https://github.com/voidrot/agents/tree/main/skills/meta/diagnose Command: npx skills add https://github.com/voidrot/agents --skill diagnose-voidrot
This Skill helps identify and diagnose potential issues in AI workflows, focusing on quality, efficiency, and safety, enabling users to proactively improve their workflows.
Use the diagnose skill to evaluate the prompt quality of your current AI workflow.
High-intent search queries and answers about installing and using this skill.
To run an AI workflow diagnostic scan, evaluate prompt quality, context efficiency, tool health, architecture fitness, and safety to generate a detailed report with prioritized remediation suggestions for your production workflows.
An AI workflow safety audit checks for potential safety risks and architecture fitness issues across your workflows, providing scored reports and detailed checklists to help you proactively identify and address reliability vulnerabilities.
You evaluate prompt quality and context efficiency by performing a diagnostic scan that analyzes these specific dimensions, providing actionable examples and templates to identify inefficiencies and improve your overall AI workflow performance.
You should conduct an AI workflow audit when preparing a new workflow for production or when conducting ongoing audits of existing workflows to ensure their continued reliability, efficiency, and safety across different scales and complexities.
Yes, this diagnostic process is suitable for both production-ready workflows and ongoing audit processes, generating scalable scored reports with prioritized remediation actions that adapt to different workflow sizes and complexities.
The best way to identify context efficiency issues is to perform a comprehensive diagnostic scan that specifically evaluates this dimension, generating a scored report with in-depth guidance and prioritized remediation actions to resolve inefficiencies.
OWASPAssess LLM application security risks against the OWASP Top 10 for LLMs 2025.
kinnerkarmanishOptimize prompts through an iterative meta-prompt loop with evaluation metrics.
AndyAnh174Evaluates LLM-powered systems using automated metrics, human feedback, and benchmarking.
nielpattinScan frontend projects for accessibility, performance, theming, responsive design, and anti-pattern issues.
