Download

Skill UI

Browse and discover 19764+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search Variant , found 14 results

Default Newest Most Downloaded

Ultra-Granular Context Audit

audit-context-building

trailofbits/skills

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.

Ultra-Granular Context Audit

audit-context-building

trailofbits/skills

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.

Axolotl LLM Fine-Tuning

Orchestra-Research/AI-Research-SKILLs

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.

Axolotl LLM Fine-Tuning

Orchestra-Research/AI-Research-SKILLs

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.

Selective State Space Model

mamba-architecture

Orchestra-Research/AI-Research-SKILLs

Mamba is a selective state-space model architecture delivering O(n) inference for million-token sequences, offering hardware-aware Mamba-1 and Mamba-2 variants that beat Transformers on speed without KV cache overhead.

Advanced Model Merging Techniques Guide

Orchestra-Research/AI-Research-SKILLs

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.

Retell AI Voice Agent Architecture Patterns

retellai-architecture-variants

jeremylongshore/claude-code-plugins-plus-skills

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.

Claude Application Architecture Patterns

clade-architecture-variants

jeremylongshore/claude-code-plugins-plus-skills

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.

Optimize AI Costs Using Together AI

together-cost-tuning

jeremylongshore/claude-code-plugins-plus-skills

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.

Gemini AI Literature Search

wanshuiyin/Auto-claude-code-research-in-sleep

This skill leverages Google Gemini to conduct broad literature discovery for research papers. Unlike traditional API searches, it decomposes topics into sub-problems and explores naming variants to find relevant papers missed by keyword matching. Supports filtering by year, venue, and code availability via MCP tools.

Harness Policy Evolution

Run @metaharness/darwin evolve to mutate a harness's seven policy surfaces, sandbox-score each variant, and promote only measured wins. Use when readiness scores are flat and you need empirical configuration discovery.

AlphaGenome Variant Effect Prediction

K-Dense-AI/scientific-agent-skills

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.

Language