Browse Skills

Analyzing Kubernetes Audit Logs parses audit events to find suspicious API activity such as exec, secret access, and RBAC changes. Use it to build timelines, detection rules, and SOC handoff notes for Kubernetes investigations.

Nessus Vulnerability Scanning runs authorized Nessus assessments, validates findings, and produces prioritized remediation guidance. Use it for authenticated scans, false-positive triage, and rescan verification.

Automates verification that empirical research tables are correct by comparing them against the underlying data and analysis code through an adversarial, regression-gated review pipeline. Use when you need to audit whether numbers in LaTeX tables match computed results.

Prepares human-readable adjudication sheets from LLM pipeline outputs, recovering full evidence and handling Excel cell limits, multi-line text, and truncation issues to ensure valid human rulings.

Verifies LLM model consistency before resuming a paused batch-scoring campaign by comparing fresh responses to cached outputs. Detects silent model drift from alias repoints or serving revisions to prevent splicing different model versions into one measure.

When adding 'cupy64' backend to pyfixest, fully absorbed regressors are not dropped, producing garbage coefficient rows. This skill guides verification: diff outputs, ignore absurd estimates, and ensure headline coefficients remain correct.

Design, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use when defining agent evals, datasets, graders, trajectory review, regression analysis, release gates, production traces, or privacy-aware telemetry.

Analyze unknown binary files (PE, ELF, Mach-O) using a deterministic CLI that wraps Ghidra. Perform triage, decompile functions, trace call paths, and produce structured evidence reports.

A disciplined operating model that guides AI agents through non-trivial software changes—from discovery and design to verified delivery—by enforcing evidence gates and escalation rules.

Scans incomplete requirements from PM, UIUX, backend, frontend, and QA perspectives to surface gaps, edge cases, and ambiguities before a PRD is written. Best for brand-new features, take-home design challenges, or unfamiliar domains.

Generates structured test cases from PRD Acceptance Criteria, covering normal, boundary, negative, concurrency, permission, and security paths. Output includes prioritized, independently executable test steps for QA teams.

Evidence-first performance engineering workflow for coding agents that combines portable .NET diagnostics with platform-native profiling, BenchmarkDotNet, application benchmarking, and statistical validation across deployment, container, graphics, and GPU procedures.