Data analysis, machine learning, LLM apps, and prompt design (8.9K skills)
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
The English summary is being prepared. Showing the original description.
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
The English summary is being prepared. Showing the original description.
Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.
The English summary is being prepared. Showing the original description.
Brand-consistent asset sets from DESIGN.md — hero, section illustrations, icon sets, OG image — generated through whichever channel the user actually has (grok build image_gen, Codex $imagegen, Gemini, xAI/Recraft/OpenAI keys) as recorded by omd:setup, with a provenance and cost ledger. No channel → prompt pack + manual queue, never stock. Trigger: '이미지 세트 만들어', '에셋 생성', 'generate assets', 'hero image', '아이콘 세트', 'OG 이미지'.
The English summary is being prepared. Showing the original description.
One-prompt autonomous product design and implementation. Use automatically for broad greenfield UI requests such as 'from scratch', '새 제품/화면을 알아서 만들어줘', or requests that delegate DESIGN.md creation. It decides whether to reuse, establish, refresh, or skip a project design system; asks at most one consequential question batch; then builds and verifies the real surface. Use omd:harness instead only when the user explicitly asks for guided checkpoints.
The English summary is being prepared. Showing the original description.
Brand-consistent asset sets from DESIGN.md — hero, section illustrations, icon sets, OG image — generated through whichever channel the user actually has (grok build image_gen, Codex $imagegen, Gemini, xAI/Recraft/OpenAI keys) as recorded by omd:setup, with a provenance and cost ledger. No channel → prompt pack + manual queue, never stock. Trigger: '이미지 세트 만들어', '에셋 생성', 'generate assets', 'hero image', '아이콘 세트', 'OG 이미지'.
The English summary is being prepared. Showing the original description.
One-prompt autonomous product design and implementation. Use automatically for broad greenfield UI requests such as 'from scratch', '새 제품/화면을 알아서 만들어줘', or requests that delegate DESIGN.md creation. It decides whether to reuse, establish, refresh, or skip a project design system; asks at most one consequential question batch; then builds and verifies the real surface. Use omd:harness instead only when the user explicitly asks for guided checkpoints.
The English summary is being prepared. Showing the original description.
Create and use Claude Code slash commands - quick prompts, bash execution, file references
The English summary is being prepared. Showing the original description.
Create and configure Claude Code sub-agents with custom prompts, tools, and models
The English summary is being prepared. Showing the original description.
Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.
The English summary is being prepared. Showing the original description.
Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.
The English summary is being prepared. Showing the original description.
SaaS analytics event taxonomy, metric formulas (MRR, churn, LTV), provider-agnostic tracking, funnel analysis, cohort setup, and privacy-respecting instrumentation.
The English summary is being prepared. Showing the original description.
Use RepoPrompt CLI for token-efficient codebase exploration
The English summary is being prepared. Showing the original description.
Data structure selection, pub/sub patterns, Lua scripting, pipelining, and cluster topology strategies.
The English summary is being prepared. Showing the original description.
Chunking strategies, embedding model selection, hybrid search, reranking, eval metrics
The English summary is being prepared. Showing the original description.
Prompt templates, few-shot examples, chain-of-thought, structured output, evals
The English summary is being prepared. Showing the original description.
Product analytics - event taxonomy, funnel analysis, A/B testing, retention metrikleri.
The English summary is being prepared. Showing the original description.
LLM Tuning Patterns
The English summary is being prepared. Showing the original description.
Marketing analytics - UTM, attribution, CAC, ROAS, conversion tracking.
The English summary is being prepared. Showing the original description.
Structured data extraction - tables, pricing, products, API endpoints with schema
The English summary is being prepared. Showing the original description.
GDPR compliance - data subject rights, lawful basis, DPIA, privacy by design, breach notification, consent management, cross-border transfers, PII masking
The English summary is being prepared. Showing the original description.
ETL/ELT patterns, batch vs streaming, idempotency, data quality framework, and pipeline orchestration
The English summary is being prepared. Showing the original description.
Gorev tipine gore dusunme modu secimi. 5 mod -- analytical (derin analiz), creative (yaratici cozum), systematic (adim adim), rapid (hizli aksiyon), debug (hata izleme). Her mod farkli prompt stratejisi ve karar agaci kullanir.
The English summary is being prepared. Showing the original description.
AI art direction system. Claude directs image generation models (Gemini, DALL-E, Flux) via structured prompts. Generate banners, diagrams, logos, screenshots, and social media visuals without leaving the terminal.
The English summary is being prepared. Showing the original description.