Skill UI

Provide qualitative, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with local quality controls. Not for ranking people or high-stakes decisions.

This pattern defines a robust, continuous loop structure for autonomous agents. It integrates crucial components like quality gates, evaluation harnesses, and explicit recovery controls. It guides complex workflows by defining decision paths (e.g., PR control, RFC decomposition) and includes strategies to mitigate common failure modes such as infinite loop churn or cost drift, ensuring measurable progress in autonomous systems.

This guide covers the mandatory Open Science appendix for high-level security research. It instructs authors on enumerating all artifacts (code, datasets, configurations), documenting data withholding decisions, and implementing engineering controls (like environment pinning and version tracking) to ensure that published results are independently and reliably reproducible.

Expert advisor for CIS Controls v8: implementation group scoping, gap assessments, safeguard guidance, and mapping to NIST CSF, ISO 27001, SOC 2, and CMMC. Supports prioritized cyber hygiene for any organization size.

An expert advisor on the NIST Cybersecurity Framework (CSF) 2.0 and 1.1. This skill assists security, risk, and compliance teams with comprehensive risk management consulting. Use it for gap assessments, profile creation (Current vs. Target), implementation roadmaps, tier advancement guidance, and mapping to other standards like ISO 27001 and CIS Controls.

This skill enables structured AI red team exercises to test for jailbreak resistance, data exfiltration risks, and harmful output controls. It helps discover exploitable failure modes before attackers do, suitable for new LLM features, third-party model evaluation, and security audits. Includes Python scripts for automated testing against various attack vectors like prompt injection and tool abuse.