GitHub CLI (gh) installation and authenticated operations in Claude.ai containers. Use when user needs to create issues, PRs, view repos, or perform GitHub operations beyond raw API calls.
Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) strategies for AI-powered search visibility in ChatGPT, Perplexity, Google AI Overviews, and other AI search platforms.
The systematic discipline of reviewing AI-generated and human-written marketing content for quality, accuracy, consistency, and effectiveness. This isn't proofreading—it's strategic quality...
Orchestrate autonomous AI development with task-based workflow and QA gates
Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.
>
Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.
Delegate tasks to Codex CLI to save Claude context
Guides agents to create context prompts for AI assistants in JSON or markdown frontmatter format. Enforces mandatory context gathering through structured questions and validates compliance with...
|
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use...
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses...
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s...
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M...
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2...
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image...
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster...
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII...
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM...