Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 +...
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create...
Learning roadmaps and career progression tracking - personalized development plans with milestone tracking
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured...
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents,...
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI...
CliftonStrengths analysis with individual coaching, team comparison, and multi-format output (markdown, HTML, slides)
文本转语音工具 - 支持脚本解析、情绪标记和后处理，基于 Edge TTS
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with...
Self-Evolving Development Loop - Dynamic skill generation with learning and evolution
Complementary health reference - evidence-based information on holistic wellness practices as complementary to conventional medicine
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node...
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
音频关键字过滤工具 - 根据关键字配置自动识别并删除音频中的指定内容
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy....
Implement comprehensive observability for LLM applications including tracing (Langfuse/Helicone), cost tracking, token optimization, RAG evaluation metrics (RAGAS), hallucination detection, and...
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Help users build and scale design systems. Use when someone is creating a component library, establishing design tokens, scaling brand consistency, or deciding when to invest in a design system.