Discover testing security llm ai skills, compare source repositories and read the instructions for each workflow.
Natural Language Processing utilities for PyTorch (Legacy). Includes tokenizers, vocabulary building, and DataPipe-based dataset handling for text processing pipelines. (torchtext, tokenizer, vocab, datapipe, r...
Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed responses. Covers VertexAiRagRetrieval t...
Techniques for ensuring LLM responses adhere to strict JSON schemas, utilizing Pydantic models, JSON mode, and schema-based refusals. Triggers: structured-output, pydantic, json-schema, json-mode, llm-response-...
Deploying fine-tuned models for production inference using native kernel optimization, vLLM, or SGLang. Triggers: inference, serving, vllm, sglang, for_inference, model merging, openai api.
Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M context), MiniMax-M2. Use for document Q&A, knowledge bases, and agentic RAG. Co...
Core fundamentals of Unsloth for fast LLM fine-tuning, covering FastLanguageModel setup, optimized gradient checkpointing, and native inference acceleration (triggers: unsloth, FastLanguageModel, from_pretraine...
Exporting fine-tuned models to GGUF format for deployment in llama.cpp, Ollama, and local serving tools. Triggers: gguf, quantization export, llama.cpp, ollama, save_pretrained_gguf, modelfile.
Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool routing) for LLM systems. Use when building or debugging agent workflows, tool-use loops, or m...
Guidance on selecting and configuring supported model architectures like Llama 4, DeepSeek-R1, and Qwen3. Triggers: llama 4, deepseek-r1, qwen3, gemma 3, model selection, instruct vs base.
Define and run tool-calling patterns for LLMs (schema design, call loops, validation, parallel calls). Use when building function/tool calling workflows or debugging tool selection and arguments; triggers: tool...
Evaluation framework patterns for RAG and LLMs, including faithfulness metrics, synthetic dataset generation, and LLM-as-a-judge patterns. Triggers: ragas, deepeval, llm-eval, faithfulness, hallucination-check,...
Building LLM agents with LangChain and LangGraph, covering tool-calling model initialization, state management, and observability with LangSmith. Triggers: langchain, langgraph, langsmith, agent-executor, chat-...
Fine-tuning Text-to-Speech (TTS) models with Unsloth for voice cloning and synthetic speech (triggers: TTS, text-to-speech, voice cloning, Orpheus-TTS, audio fine-tuning, speech synthesis).
Integration patterns for web search grounding, including query operator usage, API-based search orchestration, and citation metadata mapping. Triggers: google-search, grounding, search-api, citations, search-op...
Supervised fine-tuning using SFTTrainer, instruction formatting, and multi-turn dataset preparation with triggers like sft, instruction tuning, chat templates, sharegpt, alpaca, conversation_extension, and SFTT...
Fine-tuning multimodal vision-language models (Llama 3.2 Vision, Qwen2.5 VL) using optimized vision layers (triggers: vision models, multimodal, Llama 3.2 Vision, Qwen2.5 VL, UnslothVisionDataCollator, finetune...
Strategies for continued pretraining and domain adaptation in Unsloth (triggers: continued pretraining, CPT, domain adaptation, lm_head, embed_tokens, rsLoRA, embedding_learning_rate).
Implementation of Group Relative Policy Optimization (GRPO) for training reasoning models, optimized for 8x memory savings (triggers: GRPO, reasoning, DeepSeek-R1, reinforcement learning, RLVR, GRPOTrainer, thi...
Fine-tuning Speech-to-Text models like Whisper using Unsloth's optimized LoRA pipeline. Triggers: stt, whisper, transcription, audio fine-tuning, speech-to-text, audio normalization.
Design vector database ingestion and retrieval pipelines (points + payloads, filtered similarity search, multi-stage hybrid retrieval, index maintenance). Use when building RAG/vector search flows or debugging...
Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.
Standardizing and formatting datasets for Unsloth, including chat template conversion and synthetic data generation (triggers: chat templates, ShareGPT, Alpaca, conversation_extension, add_new_tokens, standardi...
Use this skill when working in the context of the Switchboard platform. Provides context, general instructions, and guidance for completing tasks in the context of Switchboard.
Apply structured, reflective problem-solving for complex tasks requiring multi-step analysis, revision capability, and hypothesis verification. Use for complex problem decomposition, adaptive planning, analysis...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.