Download

Skill UI

Browse and discover 7044+ curated skills

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

Total 728 skills

Default Newest Most Downloaded

Serpapi Automation With Rube

serpapi-automation

ComposioHQ/awesome-claude-skills

Orchestrates Serpapi searches through Composio's Rube MCP by discovering current tool schemas, validating the connection, and executing schema-compliant calls with session reuse and explicit memory placeholders to keep automation workflows reliable.

Experiment Tracking Setup

setting-up-experiment-tracking

jeremylongshore/claude-code-plugins-plus-skills

Automates the setup of ML experiment tracking with MLflow or W&B, configures the environment, initializes servers, and supplies snippets for logging parameters, metrics, and artifacts so runs stay reproducible and easy to compare.

SGLang Structured Inference Service

Orchestra-Research/AI-Research-SKILLs

SGLang is a high-performance serving framework for LLMs and VLMs that uses RadixAttention prefix caching to deliver structured outputs (JSON/regex/grammar) and agentic workflows with function calls, providing up to 5× faster inference than vLLM across multi-GPU production deployments.

Implementing Similarity Search Patterns

similarity-search-patterns

sickn33/antigravity-awesome-skills

This skill provides comprehensive patterns and best practices for implementing efficient similarity search mechanisms using vector databases. It is essential for building advanced AI systems such as semantic search engines, implementing Retrieval-Augmented Generation (RAG), and developing recommendation systems. Use this when optimizing retrieval performance or scaling to massive volumes of vectors.

Simple Preference Optimization for LLM Alignment

Orchestra-Research/AI-Research-SKILLs

SimPO (Simple Preference Optimization) is a state-of-the-art, reference-free method designed for aligning Large Language Models (LLMs) using human preference data. It is an efficient alternative to DPO and PPO, notably outperforming DPO without requiring a separate reference model. It is ideal for practitioners who need faster, simpler, and more resource-efficient fine-tuning for preference alignment.

Claude Skill Stocktake

skill-stocktake

affaan-m/everything-claude-code

Provides a slash command that audits every Claude skill and command using an AI-assisted checklist plus multi-mode scanning to catch regressions or outdated references before they ship.

Skyfire Automation Guide

skyfire-automation

ComposioHQ/awesome-claude-skills

Documented steps to automate Skyfire operations through Composio’s Rube MCP endpoints, covering tool discovery, connection checks, execution patterns, and schema compliance for reliable workflows.

SLIME RL Training

slime-rl-training

Orchestra-Research/AI-Research-SKILLs

Guides post-training of GLM-class LLMs with Megatron-LM and SGLang, focusing on GRPO rollout generation, custom data buffers, and tight RL scaling workflows for research and production use.

SNS Topic Config

sns-topic-config

jeremylongshore/claude-code-plugins-plus-skills

Automates SNS topic configuration tasks within AWS, offering guidance, best practices, code generation, and validation for compute, storage, networking, and serverless scenarios.

Solana Vulnerability Audit

solana-vulnerability-scanner

trailofbits/skills

Scans Solana and Anchor programs for six critical security vulnerabilities—arbitrary CPI, improper PDA validation, missing signer/ownership checks, sysvar spoofing, and instruction introspection issues—to support audits and pre-launch reviews.

Sparse Autoencoders for Model Interpretability

sparse-autoencoder-training

Orchestra-Research/AI-Research-SKILLs

SAELens provides a framework for training and analyzing Sparse Autoencoders (SAEs). SAEs decompose the dense, often polysemantic activations of large language models into sparse, monosemantic features. Use this when you need to discover the discrete, interpretable concepts a model has learned, study feature superposition, or analyze specific safety-relevant behaviors (like bias or deception) within deep neural networks.

Speak Conversation Workflow

speak-core-workflow-a

jeremylongshore/claude-code-plugins-plus-skills

Drive Speak's AI-powered conversation practice workflow with real-time pronunciation feedback, grammar guidance, and session summaries for adaptive language tutoring scenarios.

Prev 1 2 3...32 33 343536 37 38...59 60 61 Next

Language