Skill UI

Enforces a hard-edged prose contract for Claude prompts, delivering forceful, concrete, drama-free English ideal for essays or rewrites that must avoid modern AI cadence, filler, and therapy tones.

Evaluates large language models across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag) with standardized prompts and metrics, making it easy to benchmark HuggingFace or API models, compare releases, and track training progress.

LitGPT provides clean, readable, and production-ready implementations for over 20 state-of-the-art LLMs (including Llama, Gemma, Phi, Mistral). It supports comprehensive workflows, including full fine-tuning, efficient LoRA/QLoRA adaptation, and pretraining from scratch. Ideal for developers needing academic understanding or robust, deployable model architectures.

Creates customized Cascade agent configurations for domain-specific tasks using Windsurf tools, covering system prompts, context sources, activation triggers, and validation workflows for specialized AI behavior.

Windsurf Debugging AI uses Cascade to analyze stack traces, error logs, and context so developers can identify root causes, apply fixes, and document prevention steps during troubleshooting.

Documents how to apply Windsurf Cascade reliability patterns—circuit breakers, idempotency, narrow prompts, checkpoints, tests, and ignores—to keep AI integrations resilient and reviewable.

Guides security teams through cybersecurity assessments of oil and gas OT environments, covering refineries, pipelines, and production facilities while aligning with API 1164, TSA directives, IEC 62443, and NIST CSF requirements.

Generates structured peer-review quality critiques of academic papers, covering summaries, methodology scrutiny, contribution evaluation, literature positioning, and recommendations across domains whenever a user requests reviews, analyses, or summaries of research publications.