Skill UI

Prepares Claude with an ultra-granular, line-by-line code-analysis mode that maps invariants, assumptions, and flows before any vulnerability hunting, keeping context stable and reducing hallucinations during audits.

Prepares Claude with an ultra-granular, line-by-line code-analysis mode that maps invariants, assumptions, and flows before any vulnerability hunting, keeping context stable and reducing hallucinations during audits.

Expert guidance for fine-tuning LLMs with Axolotl, covering YAML configs, LoRA/QLoRA/DPO variants, multimodal support, and practical troubleshooting patterns for development and training workflows.

Expert guidance for fine-tuning LLMs with Axolotl, covering YAML configs, LoRA/QLoRA/DPO variants, multimodal support, and practical troubleshooting patterns for development and training workflows.

This guide details advanced methods for merging multiple specialized LLMs (e.g., combining math, coding, and chat capabilities) without the need for expensive retraining. Learn various techniques such as Linear Merging, SLERP, Task Arithmetic, TIES-Merging, and DARE. Use mergekit to create high-performing, specialized model variants quickly, significantly improving performance and reducing computational costs.

This skill provides architectural patterns and implementation guides for developing advanced voice agents and automating phone calls using the Retell AI platform. It covers SDK integration, API best practices, and troubleshooting common telephony errors (like 401/429), enabling developers to build robust, real-world voice interaction systems.

A comprehensive guide detailing five robust architectural patterns for building applications powered by Claude, including Chatbot, RAG, Agent, Content Pipeline, and Evaluation. It provides complete code examples and decision matrices to help developers select the optimal architecture based on project requirements, cost, and complexity.

A comprehensive guide to optimizing operating costs when utilizing Together AI's OpenAI-compatible API. This resource details strategies for cost reduction across various AI tasks, including inference, fine-tuning, and model deployment. Learn how to select appropriate model sizes, implement caching, leverage batch inference, and utilize Turbo variants to maximize efficiency and minimize spending.

Looks up precomputed AlphaGenome Atlas effects for GRCh38 SNVs (AVI score, Phred, 18 SHAP attributions, track scores) and scores variants or scans windows on demand with the AlphaGenome model for human and mouse, plus builds Atlas deep links.

Finds similar vulnerabilities and bugs across codebases using pattern-based analysis. Ideal for hunting bug variants, building CodeQL/Semgrep queries, analyzing security issues, and systematic code audits after an initial discovery.