Skill UI

This framework addresses the gap between academic benchmarks and real-world production performance for LLM agents. It teaches advanced quality engineering practices, such as behavioral contract testing, adversarial testing, and statistical analysis, ensuring agents maintain reliability and robustness when deployed. It helps developers move beyond simple pass/fail rates to comprehensive capability assessment.

This skill provides advanced, dual-use security techniques for analyzing protected binaries, including malware and proprietary software. It is strictly intended for authorized security professionals, such as those conducting penetration testing, malware analysis, or academic security research (CTFs). Users must exercise extreme caution, confirm explicit written authorization, and ensure all activities remain within defined legal and ethical scopes to prevent misuse and legal violations.

This skill provides advanced, dual-use security techniques for analyzing protected binaries, including malware and proprietary software. It is strictly intended for authorized security professionals, such as those conducting penetration testing, malware analysis, or academic security research (CTFs). Users must exercise extreme caution, confirm explicit written authorization, and ensure all activities remain within defined legal and ethical scopes to prevent misuse and legal violations.

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.

Guides diagnosing Buttercup CRS Kubernetes issues across the crs namespace by triaging pod states, analyzing logs, checking resource pressure, monitoring Redis, and inspecting queues for cascading failures in services such as redis, build-bot, scheduler, and UI.

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.

A practical, jargon-free guide to fp-ts functional programming - the 80/20 approach that gets results without the academic overhead. Use when writing TypeScript with fp-ts library.

Identifies and rewrites AI-generated phrasing by removing inflated claims, promotional language, formulaic structures, and robotic cadence so reviewed prose sounds natural, varied, and personality-driven.

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.

Guides teams through assessing legacy systems, planning incremental strangler-fig migrations, coding facades, and validating behavior to modernize without disrupting production.

Guides teams through building Lokalise integrations with a production-ready, layered project layout, reusable client wrappers, translation facades, and configuration policies; ideal for planning new Lokalise apps and establishing architecture standards.

A comprehensive toolkit designed for Product Heads to define, cascade, and align Objectives and Key Results (OKRs) across the entire organization. This tool supports quarterly strategic planning, allowing users to define company-wide goals, decompose them into product objectives, and further cascade them to specific team goals. It measures critical alignment scores (vertical, horizontal) and generates structured roadmaps for maximizing organizational excellence and strategic focus.