Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Best practices for building robust PyTorch training loops. Use when generating or reviewing ML training code.

Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.

Multi-GPU and distributed training patterns with PyTorch DDP. Use when scaling training across GPUs.

Optimize data loading pipeline to prevent GPU starvation. Use when setting up DataLoader or data preprocessing.

Structured methodology for comprehensive literature review following PRISMA guidelines. Use during literature search and screening stages.

Statistical methods for combining results across multiple studies. Use when aggregating cross-study or cross-experiment results.

Best practices for object detection tasks. Use when working on COCO, VOC, or detection architectures like YOLO and DETR.

Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.

Implementation details for EF Core SaveChanges and the update pipeline. Use when changing CommandBatchPreparer, UpdateSqlGenerator, ModificationCommand, or related classes.

Implementation details for the EF Core dotnet-ef CLI and tooling. Use when changing dotnet-ef commands, the ef wrapper, EFCore.Tools (PMC), or EFCore.Tasks MSBuild integration.

Provides authoritative guidance for Lynx development involving pages, templates, components, CSS, layouts, elements, web migration, rendering or styling bugs, and code review. Applies to *.ttml, Lynx *.tsx, and all Lynx-specific files, and requires searching the installed API docs before acting.

Pull together briefing materials before a scheduled meeting

Generate SEO/GEO dashboards: rankings, traffic, backlinks, AI visibility for stakeholders. SEO报告/绩效仪表盘

Persist SEO/GEO campaign context across Claude sessions with automatic hot-list, active work, and archive tiers. 项目记忆/跨会话

Refresh outdated posts with current stats, new sections, freshness signals to restore rankings. 内容更新/排名恢复

Find content gaps: topics and keywords competitors cover that you don't, with editorial calendar. 内容缺口/选题规划